From 496796b91af818d008895df7761d8e85fe95f894 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Wed, 4 Nov 2026 13:21:59 +0000 Subject: [PATCH] chore: sync model metadata --- .changeset/sync-models.md | 9 + packages/ai-llmgateway/src/model-meta.ts | 124 +- packages/ai-neon/src/model-meta.ts | 5 + packages/ai-openai/src/model-meta.ts | 98 + packages/ai-openrouter/src/model-meta.ts | 2425 +- packages/ai-vercel-gateway/src/model-meta.ts | 280 +- scripts/.sync-models-last-run | 2 +- scripts/llmgateway.models.json | 20771 ++++++++++++----- scripts/lovable-gateway.models.json | 929 +- scripts/neon.models.json | 476 +- scripts/openrouter.models.json | 14950 ++++++------ scripts/openrouter.video-models.json | 39 +- scripts/vercel-gateway.models.json | 2808 ++- 13 files changed, 27919 insertions(+), 14997 deletions(-) create mode 100644 .changeset/sync-models.md diff --git a/.changeset/sync-models.md b/.changeset/sync-models.md new file mode 100644 index 0000000000..c6e2fa732e --- /dev/null +++ b/.changeset/sync-models.md @@ -0,0 +1,9 @@ +--- +'@tanstack/ai-llmgateway': patch +'@tanstack/ai-neon': patch +'@tanstack/ai-openai': patch +'@tanstack/ai-openrouter': patch +'@tanstack/ai-vercel-gateway': patch +--- + +Update model metadata from OpenRouter API diff --git a/packages/ai-llmgateway/src/model-meta.ts b/packages/ai-llmgateway/src/model-meta.ts index aef107e318..822502031c 100644 --- a/packages/ai-llmgateway/src/model-meta.ts +++ b/packages/ai-llmgateway/src/model-meta.ts @@ -34,8 +34,8 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'deepseek-v4-pro', 'deepseek-v4.1-flash', 'deepseek-v4.1-flash-1017', + 'deepseek-v4.1-flash-cyber', 'devstral-2512', - 'ernie-4.5-vl-424b-a47b', 'fugu-max', 'fugu-ultra', 'fugu-ultra-v2.0', @@ -70,7 +70,6 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'glm-4.6v', 'glm-4.6v-flashx', 'glm-4.7', - 'glm-4.7-flash', 'glm-4.7-flashx', 'glm-5', 'glm-5-turbo', @@ -80,14 +79,11 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'glm-5.3', 'glm-5.3-fast', 'glm-5.3-flash', + 'glm-5.3-flashx', 'glm-5v-turbo', 'glm-image', - 'gpt-3.5-turbo', - 'gpt-4', - 'gpt-4-turbo', 'gpt-4.1', 'gpt-4.1-mini', - 'gpt-4.1-nano', 'gpt-4o', 'gpt-4o-mini', 'gpt-4o-mini-transcribe', @@ -116,6 +112,7 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'gpt-6-luna', 'gpt-6-sol', 'gpt-6.1-sol', + 'gpt-6.1-terra', 'gpt-live-transcribe', 'gpt-oss-120b', 'gpt-oss-20b', @@ -126,7 +123,6 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'gpt-transcribe', 'granite-4.2-8b', 'grok-4', - 'grok-4-1-fast-non-reasoning', 'grok-4-1-fast-reasoning', 'grok-4-20-beta-0309-non-reasoning', 'grok-4-20-beta-0309-reasoning', @@ -147,19 +143,18 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'kimi-k2.6', 'kimi-k2.7-code', 'kimi-k2.7-code-highspeed', + 'kimi-k2.8-preview', 'kimi-k3', 'kimi-k3-fast', + 'kimi-k3.1-pro', + 'kimi-k3.1-pro-highspeed', 'ling-3.0-flash', 'ling-3.0-flash-vl', - 'llama-3-70b-instruct', 'llama-3.1-70b-instruct', 'llama-3.2-11b-instruct', - 'llama-3.2-3b-instruct', 'llama-3.3-70b-instruct', 'llama-4-maverick-17b-instruct', 'llama-4-scout-17b-instruct', - 'mimo-v2.5', - 'mimo-v2.5-pro', 'mimo-v2.6-flash', 'mimo-v2.6-pro', 'minimax-m2', @@ -189,10 +184,7 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'muse-spark-1.3-contributor', 'muse-wonder-1.0', 'nemotron-3-ultra-550b', - 'o1', 'o3', - 'o3-mini', - 'o4-mini', 'qwen-flash', 'qwen-image-2.1-pro', 'qwen-image-2.1-turbo', @@ -202,19 +194,10 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'qwen-plus', 'qwen-plus-latest', 'qwen3-14b', - 'qwen3-235b-a22b-fp8', - 'qwen3-235b-a22b-instruct-2507', - 'qwen3-235b-a22b-thinking-2507', 'qwen3-30b-a3b', 'qwen3-32b', - 'qwen3-coder-30b-a3b-instruct', - 'qwen3-coder-480b-a35b-instruct', 'qwen3-coder-flash', - 'qwen3-coder-next', - 'qwen3-max', - 'qwen3-next-80b-a3b-instruct', 'qwen3-vl-235b-a22b-instruct', - 'qwen3-vl-235b-a22b-thinking', 'qwen3-vl-30b-a3b-instruct', 'qwen3-vl-plus', 'qwen3.5-122b-a10b', @@ -233,6 +216,7 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'Qwen3.8-27B', 'qwen3.8-flash', 'qwen3.8-max', + 'qwen3.8-omni-flash', 'qwen35-397b-a17b', 'reka-edge-2603', 'seed-1-6-250615', @@ -251,6 +235,7 @@ export const LLMGATEWAY_CHAT_MODELS = [ 'smart', 'sonar', 'step-3.7-flash', + 'step-5-preview', ] as const export type LLMGatewayChatModels = (typeof LLMGATEWAY_CHAT_MODELS)[number] @@ -286,8 +271,8 @@ export type LLMGatewayModelInputModalitiesByName = { 'deepseek-v4-pro': readonly ['text'] 'deepseek-v4.1-flash': readonly ['text', 'image'] 'deepseek-v4.1-flash-1017': readonly ['text', 'image'] + 'deepseek-v4.1-flash-cyber': readonly ['text', 'image'] 'devstral-2512': readonly ['text'] - 'ernie-4.5-vl-424b-a47b': readonly ['text', 'image'] 'fugu-max': readonly ['text', 'image'] 'fugu-ultra': readonly ['text', 'image'] 'fugu-ultra-v2.0': readonly ['text', 'image'] @@ -322,7 +307,6 @@ export type LLMGatewayModelInputModalitiesByName = { 'glm-4.6v': readonly ['text', 'image'] 'glm-4.6v-flashx': readonly ['text', 'image'] 'glm-4.7': readonly ['text'] - 'glm-4.7-flash': readonly ['text'] 'glm-4.7-flashx': readonly ['text'] 'glm-5': readonly ['text'] 'glm-5-turbo': readonly ['text'] @@ -332,14 +316,11 @@ export type LLMGatewayModelInputModalitiesByName = { 'glm-5.3': readonly ['text'] 'glm-5.3-fast': readonly ['text'] 'glm-5.3-flash': readonly ['text', 'image'] + 'glm-5.3-flashx': readonly ['text', 'image'] 'glm-5v-turbo': readonly ['text', 'image'] 'glm-image': readonly ['text'] - 'gpt-3.5-turbo': readonly ['text'] - 'gpt-4': readonly ['text'] - 'gpt-4-turbo': readonly ['text', 'image'] 'gpt-4.1': readonly ['text', 'image'] 'gpt-4.1-mini': readonly ['text', 'image'] - 'gpt-4.1-nano': readonly ['text', 'image'] 'gpt-4o': readonly ['text', 'image'] 'gpt-4o-mini': readonly ['text', 'image'] 'gpt-4o-mini-transcribe': readonly ['text', 'audio'] @@ -368,6 +349,7 @@ export type LLMGatewayModelInputModalitiesByName = { 'gpt-6-luna': readonly ['text', 'image'] 'gpt-6-sol': readonly ['text', 'image'] 'gpt-6.1-sol': readonly ['text', 'image'] + 'gpt-6.1-terra': readonly ['text', 'image'] 'gpt-live-transcribe': readonly ['text', 'audio'] 'gpt-oss-120b': readonly ['text'] 'gpt-oss-20b': readonly ['text'] @@ -378,7 +360,6 @@ export type LLMGatewayModelInputModalitiesByName = { 'gpt-transcribe': readonly ['text', 'audio'] 'granite-4.2-8b': readonly ['text'] 'grok-4': readonly ['text', 'image'] - 'grok-4-1-fast-non-reasoning': readonly ['text', 'image'] 'grok-4-1-fast-reasoning': readonly ['text', 'image'] 'grok-4-20-beta-0309-non-reasoning': readonly ['text', 'image'] 'grok-4-20-beta-0309-reasoning': readonly ['text', 'image'] @@ -399,19 +380,18 @@ export type LLMGatewayModelInputModalitiesByName = { 'kimi-k2.6': readonly ['text', 'image'] 'kimi-k2.7-code': readonly ['text', 'image'] 'kimi-k2.7-code-highspeed': readonly ['text', 'image'] + 'kimi-k2.8-preview': readonly ['text', 'image'] 'kimi-k3': readonly ['text', 'image'] 'kimi-k3-fast': readonly ['text', 'image'] + 'kimi-k3.1-pro': readonly ['text', 'image'] + 'kimi-k3.1-pro-highspeed': readonly ['text', 'image'] 'ling-3.0-flash': readonly ['text'] 'ling-3.0-flash-vl': readonly ['text', 'image'] - 'llama-3-70b-instruct': readonly ['text'] 'llama-3.1-70b-instruct': readonly ['text'] 'llama-3.2-11b-instruct': readonly ['text'] - 'llama-3.2-3b-instruct': readonly ['text'] 'llama-3.3-70b-instruct': readonly ['text'] 'llama-4-maverick-17b-instruct': readonly ['text', 'image'] 'llama-4-scout-17b-instruct': readonly ['text', 'image'] - 'mimo-v2.5': readonly ['text', 'image', 'audio'] - 'mimo-v2.5-pro': readonly ['text'] 'mimo-v2.6-flash': readonly ['text', 'image', 'audio'] 'mimo-v2.6-pro': readonly ['text', 'image', 'audio'] 'minimax-m2': readonly ['text'] @@ -441,10 +421,7 @@ export type LLMGatewayModelInputModalitiesByName = { 'muse-spark-1.3-contributor': readonly ['text', 'image'] 'muse-wonder-1.0': readonly ['text', 'image'] 'nemotron-3-ultra-550b': readonly ['text', 'image'] - o1: readonly ['text', 'image'] o3: readonly ['text', 'image'] - 'o3-mini': readonly ['text'] - 'o4-mini': readonly ['text', 'image'] 'qwen-flash': readonly ['text'] 'qwen-image-2.1-pro': readonly ['text', 'image'] 'qwen-image-2.1-turbo': readonly ['text', 'image'] @@ -454,19 +431,10 @@ export type LLMGatewayModelInputModalitiesByName = { 'qwen-plus': readonly ['text'] 'qwen-plus-latest': readonly ['text'] 'qwen3-14b': readonly ['text'] - 'qwen3-235b-a22b-fp8': readonly ['text'] - 'qwen3-235b-a22b-instruct-2507': readonly ['text'] - 'qwen3-235b-a22b-thinking-2507': readonly ['text'] 'qwen3-30b-a3b': readonly ['text'] 'qwen3-32b': readonly ['text'] - 'qwen3-coder-30b-a3b-instruct': readonly ['text'] - 'qwen3-coder-480b-a35b-instruct': readonly ['text'] 'qwen3-coder-flash': readonly ['text'] - 'qwen3-coder-next': readonly ['text'] - 'qwen3-max': readonly ['text', 'image'] - 'qwen3-next-80b-a3b-instruct': readonly ['text'] 'qwen3-vl-235b-a22b-instruct': readonly ['text', 'image'] - 'qwen3-vl-235b-a22b-thinking': readonly ['text', 'image'] 'qwen3-vl-30b-a3b-instruct': readonly ['text', 'image'] 'qwen3-vl-plus': readonly ['text', 'image'] 'qwen3.5-122b-a10b': readonly ['text', 'image'] @@ -485,6 +453,7 @@ export type LLMGatewayModelInputModalitiesByName = { 'Qwen3.8-27B': readonly ['text', 'image'] 'qwen3.8-flash': readonly ['text', 'image'] 'qwen3.8-max': readonly ['text', 'image'] + 'qwen3.8-omni-flash': readonly ['text', 'image', 'audio'] 'qwen35-397b-a17b': readonly ['text', 'image'] 'reka-edge-2603': readonly ['text', 'image'] 'seed-1-6-250615': readonly ['text', 'image'] @@ -503,6 +472,7 @@ export type LLMGatewayModelInputModalitiesByName = { smart: readonly ['text', 'image'] sonar: readonly ['text'] 'step-3.7-flash': readonly ['text', 'image'] + 'step-5-preview': readonly ['text', 'image'] } export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< @@ -532,8 +502,8 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'deepseek-v4-pro': ['text'] as const, 'deepseek-v4.1-flash': ['text', 'image'] as const, 'deepseek-v4.1-flash-1017': ['text', 'image'] as const, + 'deepseek-v4.1-flash-cyber': ['text', 'image'] as const, 'devstral-2512': ['text'] as const, - 'ernie-4.5-vl-424b-a47b': ['text', 'image'] as const, 'fugu-max': ['text', 'image'] as const, 'fugu-ultra': ['text', 'image'] as const, 'fugu-ultra-v2.0': ['text', 'image'] as const, @@ -568,7 +538,6 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'glm-4.6v': ['text', 'image'] as const, 'glm-4.6v-flashx': ['text', 'image'] as const, 'glm-4.7': ['text'] as const, - 'glm-4.7-flash': ['text'] as const, 'glm-4.7-flashx': ['text'] as const, 'glm-5': ['text'] as const, 'glm-5-turbo': ['text'] as const, @@ -578,14 +547,11 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'glm-5.3': ['text'] as const, 'glm-5.3-fast': ['text'] as const, 'glm-5.3-flash': ['text', 'image'] as const, + 'glm-5.3-flashx': ['text', 'image'] as const, 'glm-5v-turbo': ['text', 'image'] as const, 'glm-image': ['text'] as const, - 'gpt-3.5-turbo': ['text'] as const, - 'gpt-4': ['text'] as const, - 'gpt-4-turbo': ['text', 'image'] as const, 'gpt-4.1': ['text', 'image'] as const, 'gpt-4.1-mini': ['text', 'image'] as const, - 'gpt-4.1-nano': ['text', 'image'] as const, 'gpt-4o': ['text', 'image'] as const, 'gpt-4o-mini': ['text', 'image'] as const, 'gpt-4o-mini-transcribe': ['text', 'audio'] as const, @@ -614,6 +580,7 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'gpt-6-luna': ['text', 'image'] as const, 'gpt-6-sol': ['text', 'image'] as const, 'gpt-6.1-sol': ['text', 'image'] as const, + 'gpt-6.1-terra': ['text', 'image'] as const, 'gpt-live-transcribe': ['text', 'audio'] as const, 'gpt-oss-120b': ['text'] as const, 'gpt-oss-20b': ['text'] as const, @@ -624,7 +591,6 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'gpt-transcribe': ['text', 'audio'] as const, 'granite-4.2-8b': ['text'] as const, 'grok-4': ['text', 'image'] as const, - 'grok-4-1-fast-non-reasoning': ['text', 'image'] as const, 'grok-4-1-fast-reasoning': ['text', 'image'] as const, 'grok-4-20-beta-0309-non-reasoning': ['text', 'image'] as const, 'grok-4-20-beta-0309-reasoning': ['text', 'image'] as const, @@ -645,19 +611,18 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'kimi-k2.6': ['text', 'image'] as const, 'kimi-k2.7-code': ['text', 'image'] as const, 'kimi-k2.7-code-highspeed': ['text', 'image'] as const, + 'kimi-k2.8-preview': ['text', 'image'] as const, 'kimi-k3': ['text', 'image'] as const, 'kimi-k3-fast': ['text', 'image'] as const, + 'kimi-k3.1-pro': ['text', 'image'] as const, + 'kimi-k3.1-pro-highspeed': ['text', 'image'] as const, 'ling-3.0-flash': ['text'] as const, 'ling-3.0-flash-vl': ['text', 'image'] as const, - 'llama-3-70b-instruct': ['text'] as const, 'llama-3.1-70b-instruct': ['text'] as const, 'llama-3.2-11b-instruct': ['text'] as const, - 'llama-3.2-3b-instruct': ['text'] as const, 'llama-3.3-70b-instruct': ['text'] as const, 'llama-4-maverick-17b-instruct': ['text', 'image'] as const, 'llama-4-scout-17b-instruct': ['text', 'image'] as const, - 'mimo-v2.5': ['text', 'image', 'audio'] as const, - 'mimo-v2.5-pro': ['text'] as const, 'mimo-v2.6-flash': ['text', 'image', 'audio'] as const, 'mimo-v2.6-pro': ['text', 'image', 'audio'] as const, 'minimax-m2': ['text'] as const, @@ -687,10 +652,7 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'muse-spark-1.3-contributor': ['text', 'image'] as const, 'muse-wonder-1.0': ['text', 'image'] as const, 'nemotron-3-ultra-550b': ['text', 'image'] as const, - o1: ['text', 'image'] as const, o3: ['text', 'image'] as const, - 'o3-mini': ['text'] as const, - 'o4-mini': ['text', 'image'] as const, 'qwen-flash': ['text'] as const, 'qwen-image-2.1-pro': ['text', 'image'] as const, 'qwen-image-2.1-turbo': ['text', 'image'] as const, @@ -700,19 +662,10 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'qwen-plus': ['text'] as const, 'qwen-plus-latest': ['text'] as const, 'qwen3-14b': ['text'] as const, - 'qwen3-235b-a22b-fp8': ['text'] as const, - 'qwen3-235b-a22b-instruct-2507': ['text'] as const, - 'qwen3-235b-a22b-thinking-2507': ['text'] as const, 'qwen3-30b-a3b': ['text'] as const, 'qwen3-32b': ['text'] as const, - 'qwen3-coder-30b-a3b-instruct': ['text'] as const, - 'qwen3-coder-480b-a35b-instruct': ['text'] as const, 'qwen3-coder-flash': ['text'] as const, - 'qwen3-coder-next': ['text'] as const, - 'qwen3-max': ['text', 'image'] as const, - 'qwen3-next-80b-a3b-instruct': ['text'] as const, 'qwen3-vl-235b-a22b-instruct': ['text', 'image'] as const, - 'qwen3-vl-235b-a22b-thinking': ['text', 'image'] as const, 'qwen3-vl-30b-a3b-instruct': ['text', 'image'] as const, 'qwen3-vl-plus': ['text', 'image'] as const, 'qwen3.5-122b-a10b': ['text', 'image'] as const, @@ -731,6 +684,7 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< 'Qwen3.8-27B': ['text', 'image'] as const, 'qwen3.8-flash': ['text', 'image'] as const, 'qwen3.8-max': ['text', 'image'] as const, + 'qwen3.8-omni-flash': ['text', 'image', 'audio'] as const, 'qwen35-397b-a17b': ['text', 'image'] as const, 'reka-edge-2603': ['text', 'image'] as const, 'seed-1-6-250615': ['text', 'image'] as const, @@ -749,6 +703,7 @@ export const LLMGATEWAY_MODEL_INPUT_MODALITIES: Readonly< smart: ['text', 'image'] as const, sonar: ['text'] as const, 'step-3.7-flash': ['text', 'image'] as const, + 'step-5-preview': ['text', 'image'] as const, } satisfies LLMGatewayModelInputModalitiesByName export type LLMGatewayChatModelProviderOptionsByName = { @@ -775,10 +730,6 @@ const EFFORT_HIGH_TO_MAX = { levels: { high: 'high', xhigh: 'xhigh', max: 'max' }, budget: false, } as const -const EFFORT_LOW_HIGH_MAX = { - levels: { low: 'low', high: 'high', max: 'max' }, - budget: false, -} as const const EFFORT_LOW_MEDIUM_XHIGH = { levels: { low: 'low', medium: 'medium', xhigh: 'xhigh' }, budget: false, @@ -847,6 +798,10 @@ const EFFORT_NONE_LOW_HIGH_MAX = { levels: { off: 'none', low: 'low', high: 'high', max: 'max' }, budget: false, } as const +const EFFORT_NONE_LOW_HIGH_TO_MAX = { + levels: { off: 'none', low: 'low', high: 'high', xhigh: 'xhigh', max: 'max' }, + budget: false, +} as const const EFFORT_NONE_LOW_MEDIUM_XHIGH = { levels: { off: 'none', low: 'low', medium: 'medium', xhigh: 'xhigh' }, budget: false, @@ -899,6 +854,10 @@ const EFFORT_NONE_MINIMAL_TO_XHIGH = { }, budget: false, } as const +const EFFORT_XHIGH_MAX = { + levels: { xhigh: 'xhigh', max: 'max' }, + budget: false, +} as const const LLMGATEWAY_REASONING = { 'claude-fable-5': EFFORT_LOW_TO_MAX, @@ -919,8 +878,9 @@ const LLMGATEWAY_REASONING = { 'claude-sonnet-5-5': EFFORT_LOW_TO_MAX, 'deepseek-v4-flash': EFFORT_NONE_LOW_HIGH_MAX, 'deepseek-v4-pro': EFFORT_NONE_HIGH_MAX, - 'deepseek-v4.1-flash': EFFORT_NONE_LOW_HIGH_MAX, - 'deepseek-v4.1-flash-1017': EFFORT_NONE_LOW_HIGH_MAX, + 'deepseek-v4.1-flash': EFFORT_NONE_MINIMAL_TO_MAX, + 'deepseek-v4.1-flash-1017': EFFORT_NONE_MINIMAL_TO_MAX, + 'deepseek-v4.1-flash-cyber': EFFORT_NONE_LOW_HIGH_TO_MAX, 'fugu-max': EFFORT_HIGH_TO_MAX, 'fugu-ultra': EFFORT_HIGH_TO_MAX, 'fugu-ultra-v2.0': EFFORT_HIGH_TO_MAX, @@ -940,8 +900,9 @@ const LLMGATEWAY_REASONING = { 'glm-5-turbo': EFFORT_LOW_TO_MAX, 'glm-5.1': EFFORT_NONE_MINIMAL_TO_MAX, 'glm-5.2': EFFORT_NONE_HIGH_MAX, - 'glm-5.3': EFFORT_LOW_HIGH_MAX, - 'glm-5.3-flash': EFFORT_LOW_HIGH_MAX, + 'glm-5.3': EFFORT_LOW_TO_MAX, + 'glm-5.3-flash': EFFORT_XHIGH_MAX, + 'glm-5.3-flashx': EFFORT_XHIGH_MAX, 'glm-5v-turbo': EFFORT_LOW_TO_MAX, 'gpt-5': EFFORT_MINIMAL_TO_HIGH, 'gpt-5-mini': EFFORT_MINIMAL_TO_HIGH, @@ -965,6 +926,7 @@ const LLMGATEWAY_REASONING = { 'gpt-6-luna': EFFORT_NONE_LOW_TO_MAX, 'gpt-6-sol': EFFORT_NONE_LOW_TO_MAX, 'gpt-6.1-sol': EFFORT_LOW_TO_MAX, + 'gpt-6.1-terra': EFFORT_NONE_LOW_TO_MAX, 'gpt-oss-120b': EFFORT_LOW_TO_HIGH, 'gpt-oss-20b': EFFORT_LOW_TO_HIGH, 'granite-4.2-8b': EFFORT_NONE_LOW_TO_HIGH, @@ -978,12 +940,13 @@ const LLMGATEWAY_REASONING = { 'kimi-k2.6': EFFORT_NONE_MINIMAL_TO_MAX, 'kimi-k2.7-code': EFFORT_LOW_TO_MAX, 'kimi-k2.7-code-highspeed': EFFORT_LOW_TO_MAX, + 'kimi-k2.8-preview': EFFORT_NONE_MINIMAL_TO_MAX, 'kimi-k3': EFFORT_NONE_MINIMAL_TO_MAX, 'kimi-k3-fast': EFFORT_NONE_LOW_TO_MAX, + 'kimi-k3.1-pro': EFFORT_NONE_MINIMAL_TO_MAX, + 'kimi-k3.1-pro-highspeed': EFFORT_NONE_MINIMAL_TO_MAX, 'ling-3.0-flash': EFFORT_NONE, 'ling-3.0-flash-vl': EFFORT_NONE_LOW_TO_HIGH, - 'mimo-v2.5': EFFORT_NONE_LOW_TO_HIGH, - 'mimo-v2.5-pro': EFFORT_NONE_LOW_TO_HIGH, 'mimo-v2.6-flash': EFFORT_NONE_LOW_TO_HIGH, 'mimo-v2.6-pro': EFFORT_NONE_LOW_TO_HIGH, 'minimax-m2': EFFORT_LOW_TO_MAX, @@ -1002,8 +965,6 @@ const LLMGATEWAY_REASONING = { 'muse-spark-1.3': EFFORT_MINIMAL_TO_XHIGH, 'muse-spark-1.3-contributor': EFFORT_MINIMAL_TO_XHIGH, 'muse-wonder-1.0': EFFORT_MINIMAL_TO_XHIGH, - o1: EFFORT_LOW_TO_HIGH, - 'o4-mini': EFFORT_LOW_TO_HIGH, 'qwen3.5-122b-a10b': EFFORT_NONE_MINIMAL_TO_MAX, 'qwen3.5-27b': EFFORT_NONE_MINIMAL_TO_MAX, 'qwen3.5-35b-a3b': EFFORT_NONE_MINIMAL_TO_MAX, @@ -1017,6 +978,7 @@ const LLMGATEWAY_REASONING = { 'qwen3.8-27b': EFFORT_NONE_LOW_TO_HIGH, 'Qwen3.8-27B': EFFORT_LOW_MEDIUM_XHIGH, 'qwen3.8-flash': EFFORT_NONE_MINIMAL_TO_MAX, + 'qwen3.8-omni-flash': EFFORT_NONE_MINIMAL_TO_MAX, 'qwen35-397b-a17b': EFFORT_NONE_MINIMAL_TO_MAX, 'seed-1-6-250615': EFFORT_MINIMAL_TO_HIGH, 'seed-1-6-250915': EFFORT_MINIMAL_TO_HIGH, diff --git a/packages/ai-neon/src/model-meta.ts b/packages/ai-neon/src/model-meta.ts index a3c9ce29f8..b40b832ff4 100644 --- a/packages/ai-neon/src/model-meta.ts +++ b/packages/ai-neon/src/model-meta.ts @@ -31,6 +31,7 @@ export const NEON_CHAT_MODELS = [ 'gemini-3-7-flash', 'gemini-3-8-flash', 'gemini-3-flash', + 'gemini-4-argon', 'gemma-3-12b', 'glm-5-2', 'glm-5-3', @@ -144,6 +145,7 @@ export const NEON_MODELS_REJECTING_SAMPLING: ReadonlySet = new Set([ 'gemini-3-6-flash', 'gemini-3-7-flash', 'gemini-3-8-flash', + 'gemini-4-argon', 'gpt-5', 'gpt-5-5', 'gpt-5-5-pro', @@ -172,6 +174,7 @@ export const NEON_MODELS_REJECTING_STREAM_OPTIONS: ReadonlySet = 'gemini-3-7-flash', 'gemini-3-8-flash', 'gemini-3-flash', + 'gemini-4-argon', ] as const) /** The input modalities of each chat model. */ @@ -200,6 +203,7 @@ export const NEON_MODEL_INPUT_MODALITIES = { 'gemini-3-7-flash': ['text', 'image', 'document', 'audio', 'video'], 'gemini-3-8-flash': ['text', 'image', 'document', 'audio', 'video'], 'gemini-3-flash': ['text', 'image', 'document', 'audio', 'video'], + 'gemini-4-argon': ['text', 'image', 'document', 'audio', 'video'], 'gemma-3-12b': ['text', 'image'], 'glm-5-2': ['text'], 'glm-5-3': ['text'], @@ -318,6 +322,7 @@ const NEON_REASONING = { 'gemini-3-7-flash': EFFORT_MINIMAL_TO_HIGH, 'gemini-3-8-flash': EFFORT_MINIMAL_TO_HIGH, 'gemini-3-flash': EFFORT_LOW_TO_HIGH, + 'gemini-4-argon': EFFORT_LOW_TO_HIGH, 'glm-5-2': EFFORT_NONE_MINIMAL_TO_HIGH_MAX, 'glm-5-3': EFFORT_LOW_HIGH_MAX, 'glm-5-3-flash': EFFORT_LOW_HIGH_MAX, diff --git a/packages/ai-openai/src/model-meta.ts b/packages/ai-openai/src/model-meta.ts index 3dfd1be779..ac339dc044 100644 --- a/packages/ai-openai/src/model-meta.ts +++ b/packages/ai-openai/src/model-meta.ts @@ -2623,7 +2623,89 @@ const GPT_6_1_SOL_PRO = { OpenAIMetadataOptions > +const GPT_6_1_TERRA = { + name: 'gpt-6.1-terra', + context_window: 1_050_000, + max_output_tokens: 128_000, + supports: { + input: ['image', 'text'], + output: ['text'], + endpoints: ['chat', 'chat-completions'], + features: ['streaming', 'function_calling', 'structured_outputs'], + tools: [ + 'web_search', + 'web_search_preview', + 'file_search', + 'image_generation', + 'code_interpreter', + 'mcp', + 'computer_use', + 'computer', + 'local_shell', + 'shell', + 'apply_patch', + ], + }, + pricing: { + input: { + normal: 1, + cached: 0.05, + }, + output: { + normal: 5, + }, + }, +} as const satisfies ModelMeta< + OpenAIBaseOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions +> + +const GPT_6_1_TERRA_PRO = { + name: 'gpt-6.1-terra-pro', + context_window: 1_050_000, + max_output_tokens: 128_000, + supports: { + input: ['image', 'text'], + output: ['text'], + endpoints: ['chat', 'chat-completions'], + features: ['streaming', 'function_calling', 'structured_outputs'], + tools: [ + 'web_search', + 'web_search_preview', + 'file_search', + 'image_generation', + 'code_interpreter', + 'mcp', + 'computer_use', + 'computer', + 'local_shell', + 'shell', + 'apply_patch', + ], + }, + pricing: { + input: { + normal: 1, + cached: 0.05, + }, + output: { + normal: 5, + }, + }, +} as const satisfies ModelMeta< + OpenAIBaseOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions +> + export const OPENAI_CHAT_MODELS = [ + GPT_6_1_TERRA.name, + GPT_6_1_TERRA_PRO.name, GPT_6_1_SOL.name, GPT_6_1_SOL_PRO.name, GPT_6_LUNA.name, @@ -3059,6 +3141,16 @@ export type OpenAIChatModelProviderOptionsByName = { OpenAIToolsOptions & OpenAIStreamingOptions & OpenAIMetadataOptions + [GPT_6_1_TERRA.name]: OpenAIBaseOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions + [GPT_6_1_TERRA_PRO.name]: OpenAIBaseOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions } /** @@ -3117,6 +3209,8 @@ export type OpenAIChatModelToolCapabilitiesByName = { [GPT_6_SOL_PRO.name]: typeof GPT_6_SOL_PRO.supports.tools [GPT_6_1_SOL.name]: typeof GPT_6_1_SOL.supports.tools [GPT_6_1_SOL_PRO.name]: typeof GPT_6_1_SOL_PRO.supports.tools + [GPT_6_1_TERRA.name]: typeof GPT_6_1_TERRA.supports.tools + [GPT_6_1_TERRA_PRO.name]: typeof GPT_6_1_TERRA_PRO.supports.tools } /** @@ -3187,6 +3281,8 @@ export type OpenAIModelInputModalitiesByName = { [GPT_6_SOL_PRO.name]: typeof GPT_6_SOL_PRO.supports.input [GPT_6_1_SOL.name]: typeof GPT_6_1_SOL.supports.input [GPT_6_1_SOL_PRO.name]: typeof GPT_6_1_SOL_PRO.supports.input + [GPT_6_1_TERRA.name]: typeof GPT_6_1_TERRA.supports.input + [GPT_6_1_TERRA_PRO.name]: typeof GPT_6_1_TERRA_PRO.supports.input } /** @@ -3250,6 +3346,8 @@ export const OPENAI_MODEL_INPUT_MODALITIES: Readonly< [GPT_6_SOL_PRO.name]: GPT_6_SOL_PRO.supports.input, [GPT_6_1_SOL.name]: GPT_6_1_SOL.supports.input, [GPT_6_1_SOL_PRO.name]: GPT_6_1_SOL_PRO.supports.input, + [GPT_6_1_TERRA.name]: GPT_6_1_TERRA.supports.input, + [GPT_6_1_TERRA_PRO.name]: GPT_6_1_TERRA_PRO.supports.input, } satisfies OpenAIModelInputModalitiesByName // Reasoning diff --git a/packages/ai-openrouter/src/model-meta.ts b/packages/ai-openrouter/src/model-meta.ts index 74d79bedf7..655e25262c 100644 --- a/packages/ai-openrouter/src/model-meta.ts +++ b/packages/ai-openrouter/src/model-meta.ts @@ -367,8 +367,8 @@ const _DEEPSEEK_DEEPSEEK_FLASH_LATEST = { pricing: { text: { input: { - normal: 0.07, - cached: 0.008, + normal: 0.032, + cached: 0.005, }, output: { normal: 0.5, @@ -405,8 +405,8 @@ const _DEEPSEEK_DEEPSEEK_PRO_LATEST = { pricing: { text: { input: { - normal: 0.2235, - cached: 0.22, + normal: 0.1035, + cached: 0.1, }, output: { normal: 8, @@ -444,11 +444,11 @@ const _DEEPSEEK_DEEPSEEK_V4_FLASH_LATEST = { pricing: { text: { input: { - normal: 0.0475, - cached: 0.028, + normal: 0.059, + cached: 0.035, }, output: { - normal: 0.1568, + normal: 0.3, }, }, image: 0, @@ -532,6 +532,8 @@ const _MOONSHOTAI_KIMI_LATEST = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -548,11 +550,11 @@ const _MOONSHOTAI_KIMI_LATEST = { pricing: { text: { input: { - normal: 0.238, - cached: 0.228, + normal: 0.152, + cached: 0.15, }, output: { - normal: 16, + normal: 10.1583, }, }, image: 0, @@ -703,11 +705,11 @@ const _OPENAI_GPT_TERRA_LATEST = { pricing: { text: { input: { - normal: 2, - cached: 2.7, + normal: 1, + cached: 1.3, }, output: { - normal: 12, + normal: 5, }, }, image: 0, @@ -749,6 +751,7 @@ const _X_AI_GROK_LATEST = { 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topLogprobs', @@ -795,15 +798,15 @@ const _Z_AI_GLM_FLASH_LATEST = { ], }, context_window: 1048576, - max_output_tokens: 943718, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.0052, - cached: 0.0052, + normal: 0.0269, + cached: 0.0269, }, output: { - normal: 0.1985, + normal: 0.0996, }, }, image: 0, @@ -838,8 +841,8 @@ const _Z_AI_GLM_LATEST = { pricing: { text: { input: { - normal: 0.079, - cached: 0.078, + normal: 0.0699, + cached: 0.0689, }, output: { normal: 1.4, @@ -2117,36 +2120,6 @@ const ANTHROPIC_CLAUDE_SONNET_5_5_BATCH = { }, reasoning: EFFORT_LOW_TO_MAX, } as const -const ARCEE_AI_TRINITY_LARGE_THINKING = { - id: 'arcee-ai/trinity-large-thinking', - name: 'Arcee AI: Trinity Large Thinking', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 80000, - pricing: { - text: { - input: { - normal: 0.25, - cached: 0.06, - }, - output: { - normal: 0.8, - }, - }, - image: 0, - }, - reasoning: EFFORT_MINIMAL_TO_HIGH, -} as const const BYTEDANCE_SEED_SEED_1_6 = { id: 'bytedance-seed/seed-1.6', name: 'ByteDance Seed: Seed 1.6', @@ -2698,7 +2671,7 @@ const DEEPSEEK_DEEPSEEK_CHAT_V3_1 = { ], }, context_window: 163840, - max_output_tokens: 32768, + max_output_tokens: 147456, pricing: { text: { input: { @@ -2762,7 +2735,6 @@ const DEEPSEEK_DEEPSEEK_V3_1_TERMINUS = { 'maxCompletionTokens', 'reasoning', 'responseFormat', - 'stop', 'temperature', 'toolChoice', 'topP', @@ -2807,15 +2779,15 @@ const DEEPSEEK_DEEPSEEK_V3_2 = { ], }, context_window: 163840, - max_output_tokens: 65536, + max_output_tokens: 147456, pricing: { text: { input: { - normal: 0.28, - cached: 0.028, + normal: 0.26, + cached: 0.13, }, output: { - normal: 0.42, + normal: 0.38, }, }, image: 0, @@ -2917,15 +2889,15 @@ const DEEPSEEK_DEEPSEEK_V4_FLASH_0731 = { ], }, context_window: 1048576, - max_output_tokens: 131072, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.44, - cached: 0.014, + normal: 0.059, + cached: 0.035, }, output: { - normal: 1.32, + normal: 0.3, }, }, image: 0, @@ -2994,15 +2966,15 @@ const DEEPSEEK_DEEPSEEK_V4_PRO = { ], }, context_window: 1048576, - max_output_tokens: 384000, + max_output_tokens: 393216, pricing: { text: { input: { - normal: 0.95526, - cached: 0.079605, + normal: 1.6, + cached: 0.135, }, output: { - normal: 1.91052, + normal: 3.2, }, }, image: 0, @@ -3032,15 +3004,15 @@ const DEEPSEEK_DEEPSEEK_V4_PRO_0813 = { ], }, context_window: 1048576, - max_output_tokens: 393216, + max_output_tokens: 943718, pricing: { text: { input: { - normal: 0.66, - cached: 0.022, + normal: 0.115, + cached: 0.11, }, output: { - normal: 1.98, + normal: 4.6, }, }, image: 0, @@ -3058,6 +3030,7 @@ const DEEPSEEK_DEEPSEEK_V4_1_FLASH = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -3074,11 +3047,11 @@ const DEEPSEEK_DEEPSEEK_V4_1_FLASH = { pricing: { text: { input: { - normal: 0.3, - cached: 0.006, + normal: 0.045, + cached: 0.018, }, output: { - normal: 1.2, + normal: 0.5, }, }, image: 0, @@ -4387,15 +4360,15 @@ const GOOGLE_GEMMA_3_4B_IT = { ], }, context_window: 131072, - max_output_tokens: 117964, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.04, - cached: 0.02, + normal: 0.05, + cached: 0, }, output: { - normal: 0.05, + normal: 0.1, }, }, image: 0, @@ -4412,6 +4385,7 @@ const GOOGLE_GEMMA_4_26B_A4B_IT = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', @@ -4424,15 +4398,15 @@ const GOOGLE_GEMMA_4_26B_A4B_IT = { ], }, context_window: 262144, - max_output_tokens: 235929, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.09, - cached: 0.05, + normal: 0.072, + cached: 0.036, }, output: { - normal: 0.3, + normal: 0.217, }, }, image: 0, @@ -4482,6 +4456,7 @@ const GOOGLE_GEMMA_4_31B_IT = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', @@ -4634,41 +4609,6 @@ const GRYPHE_MYTHOMAX_L2_13B = { image: 0, }, } as const -const IBM_GRANITE_GRANITE_4_0_H_MICRO = { - id: 'ibm-granite/granite-4.0-h-micro', - name: 'IBM: Granite 4.0 Micro', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'topLogprobs', - 'topP', - ], - }, - context_window: 131000, - max_output_tokens: 117900, - pricing: { - text: { - input: { - normal: 0.017, - cached: 0, - }, - output: { - normal: 0.112, - }, - }, - image: 0, - }, -} as const const IBM_GRANITE_GRANITE_4_2_8B = { id: 'ibm-granite/granite-4.2-8b', name: 'IBM: Granite 4.2 8B', @@ -4895,8 +4835,8 @@ const INCLUSIONAI_LING_3_1_FLASH = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 235929, + context_window: 1000000, + max_output_tokens: 262144, pricing: { text: { input: { @@ -4976,6 +4916,43 @@ const INFERENCE_NET_SCHEMATRON_V2_TURBO = { image: 0, }, } as const +const LIQUID_LFM_2_5_2_6B = { + id: 'liquid/lfm-2.5-2.6b', + name: 'LiquidAI: LFM2.5-2.6B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 128000, + max_output_tokens: 8192, + pricing: { + text: { + input: { + normal: 0.35, + cached: 0.04, + }, + output: { + normal: 0.5, + }, + }, + image: 0, + }, +} as const const LIQUID_LFM_2_5_2_6B_FREE = { id: 'liquid/lfm-2.5-2.6b:free', name: 'LiquidAI: LFM2.5-2.6B (free)', @@ -4995,6 +4972,7 @@ const LIQUID_LFM_2_5_2_6B_FREE = { 'temperature', 'toolChoice', 'topLogprobs', + 'topP', ], }, context_window: 65536, @@ -5032,6 +5010,7 @@ const LIQUID_LFM_2_5_24B_A2B = { 'temperature', 'toolChoice', 'topLogprobs', + 'topP', ], }, context_window: 128000, @@ -5125,29 +5104,18 @@ const META_LLAMA_LLAMA_3_1_70B_INSTRUCT = { supports: { input: ['text'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], + supports: ['maxCompletionTokens', 'stop', 'temperature', 'topP'], }, context_window: 131072, - max_output_tokens: 16384, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.4, + normal: 0.72, cached: 0, }, output: { - normal: 0.4, + normal: 0.72, }, }, image: 0, @@ -5748,17 +5716,10 @@ const MINIMAX_MINIMAX_M2 = { input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'responseFormat', - 'seed', - 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -5944,31 +5905,38 @@ 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)', +const MINIMAX_MINIMAX_M3_1_FLASH = { + id: 'minimax/minimax-m3.1-flash', + name: 'MiniMax: MiniMax M3.1 Flash', supports: { input: ['text', 'image', 'video'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1000000, + context_window: 1048576, max_output_tokens: 524288, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.15, + cached: 0.015, }, output: { - normal: 0, + normal: 0.6, }, }, image: 0, @@ -6007,39 +5975,6 @@ const MISTRALAI_CODESTRAL_2508 = { image: 0, }, } as const -const MISTRALAI_CODESTRAL_2508_BATCH = { - id: 'mistralai/codestral-2508:batch', - name: 'Mistral: Codestral 2508 (batch)', - supports: { - input: ['text', 'document'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 256000, - max_output_tokens: 204800, - pricing: { - text: { - input: { - normal: 0.15, - cached: 0.015, - }, - output: { - normal: 0.45, - }, - }, - image: 0, - }, -} as const const MISTRALAI_DEVSTRAL_2512 = { id: 'mistralai/devstral-2512', name: 'Mistral: Devstral 2 2512', @@ -6172,39 +6107,6 @@ const MISTRALAI_MINISTRAL_8B_2512 = { image: 0, }, } as const -const MISTRALAI_MINISTRAL_8B_2512_BATCH = { - id: 'mistralai/ministral-8b-2512:batch', - name: 'Mistral: Ministral 3 8B 2512 (batch)', - supports: { - input: ['text', 'image'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 209715, - pricing: { - text: { - input: { - normal: 0.075, - cached: 0.0075, - }, - output: { - normal: 0.075, - }, - }, - image: 0, - }, -} as const const MISTRALAI_MISTRAL_LARGE = { id: 'mistralai/mistral-large', name: 'Mistral Large', @@ -6304,42 +6206,9 @@ const MISTRALAI_MISTRAL_LARGE_2512 = { image: 0, }, } as const -const MISTRALAI_MISTRAL_LARGE_2512_BATCH = { - id: 'mistralai/mistral-large-2512:batch', - name: 'Mistral: Mistral Large 3 2512 (batch)', - supports: { - input: ['text', 'image', 'document'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 209715, - pricing: { - text: { - input: { - normal: 0.25, - cached: 0.025, - }, - output: { - normal: 0.75, - }, - }, - image: 0, - }, -} as const -const MISTRALAI_MISTRAL_LARGE_4_0 = { - id: 'mistralai/mistral-large-4-0', - name: 'Mistral: Mistral Large 4', +const MISTRALAI_MISTRAL_LARGE_4_0 = { + id: 'mistralai/mistral-large-4-0', + name: 'Mistral: Mistral Large 4', supports: { input: ['text', 'image'], output: ['text'], @@ -6363,11 +6232,11 @@ const MISTRALAI_MISTRAL_LARGE_4_0 = { pricing: { text: { input: { - normal: 1.36, - cached: 0.14, + normal: 0.7, + cached: 0.07, }, output: { - normal: 4.18, + normal: 2.1, }, }, image: 0, @@ -6509,39 +6378,6 @@ const MISTRALAI_MISTRAL_MEDIUM_3_1 = { image: 0, }, } as const -const MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH = { - id: 'mistralai/mistral-medium-3.1:batch', - name: 'Mistral: Mistral Medium 3.1 (batch)', - supports: { - input: ['text', 'image', 'document'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 104857, - pricing: { - text: { - input: { - normal: 0.2, - cached: 0.02, - }, - output: { - normal: 1, - }, - }, - image: 0, - }, -} as const const MISTRALAI_MISTRAL_NEMO = { id: 'mistralai/mistral-nemo', name: 'Mistral: Mistral Nemo', @@ -6679,41 +6515,6 @@ const MISTRALAI_MISTRAL_SMALL_2603 = { }, reasoning: EFFORT_NONE_HIGH, } as const -const MISTRALAI_MISTRAL_SMALL_2603_BATCH = { - id: 'mistralai/mistral-small-2603:batch', - name: 'Mistral: Mistral Small 4 (batch)', - supports: { - input: ['text', 'image'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 209715, - pricing: { - text: { - input: { - normal: 0.075, - cached: 0.0075, - }, - output: { - normal: 0.3, - }, - }, - image: 0, - }, - reasoning: EFFORT_NONE_HIGH, -} as const const MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT = { id: 'mistralai/mistral-small-3.1-24b-instruct', name: 'Mistral: Mistral Small 3.1 24B', @@ -6775,11 +6576,11 @@ const MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT = { pricing: { text: { input: { - normal: 0.09375, + normal: 0.075, cached: 0, }, output: { - normal: 0.25, + normal: 0.2, }, }, image: 0, @@ -6982,7 +6783,6 @@ const MOONSHOTAI_KIMI_K2_THINKING = { output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -6991,7 +6791,6 @@ const MOONSHOTAI_KIMI_K2_THINKING = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -7116,11 +6915,11 @@ const MOONSHOTAI_KIMI_K2_7_CODE = { pricing: { text: { input: { - normal: 0.6712, - cached: 0.18, + normal: 0.6, + cached: 0.15, }, output: { - normal: 3.35, + normal: 3.5, }, }, image: 0, @@ -7138,6 +6937,8 @@ const MOONSHOTAI_KIMI_K3 = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -7154,11 +6955,11 @@ const MOONSHOTAI_KIMI_K3 = { pricing: { text: { input: { - normal: 0.239, - cached: 0.21, + normal: 0.192, + cached: 0.182, }, output: { - normal: 11.936, + normal: 16, }, }, image: 0, @@ -7201,6 +7002,41 @@ const MOONSHOTAI_KIMI_K3_BATCH = { }, reasoning: EFFORT_LOW_HIGH_MAX, } as const +const MOONSHOTAI_KIMI_K3_1_PRO = { + id: 'moonshotai/kimi-k3.1-pro', + name: 'MoonshotAI: Kimi K3.1 Pro', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 943718, + pricing: { + text: { + input: { + normal: 2, + cached: 0.2, + }, + output: { + normal: 10, + }, + }, + image: 0, + }, +} as const const MORPH_MORPH_V3_FAST = { id: 'morph/morph-v3-fast', name: 'Morph: Morph V3 Fast', @@ -7324,71 +7160,6 @@ const NEX_AGI_NEX_N2_5_PRO = { }, reasoning: EFFORT_NONE_MEDIUM_HIGH, } as const -const NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B = { - id: 'nousresearch/hermes-3-llama-3.1-405b', - name: 'Nous: Hermes 3 405B Instruct', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 16384, - pricing: { - text: { - input: { - normal: 1, - cached: 0, - }, - output: { - normal: 1, - }, - }, - image: 0, - }, -} as const -const NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B = { - id: 'nousresearch/hermes-3-llama-3.1-70b', - name: 'Nous: Hermes 3 70B Instruct', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 16384, - pricing: { - text: { - input: { - normal: 0.7, - cached: 0, - }, - output: { - normal: 0.7, - }, - }, - image: 0, - }, -} as const const NOUSRESEARCH_HERMES_4_405B = { id: 'nousresearch/hermes-4-405b', name: 'Nous: Hermes 4 405B', @@ -7397,11 +7168,14 @@ const NOUSRESEARCH_HERMES_4_405B = { output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', 'topLogprobs', 'topP', @@ -7413,7 +7187,7 @@ const NOUSRESEARCH_HERMES_4_405B = { text: { input: { normal: 1, - cached: 0, + cached: 0.2, }, output: { normal: 3, @@ -7432,7 +7206,6 @@ const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -7441,7 +7214,6 @@ const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -7451,7 +7223,7 @@ const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { text: { input: { normal: 0.06, - cached: 0, + cached: 0.012, }, output: { normal: 0.24, @@ -7514,8 +7286,8 @@ const NVIDIA_NEMOTRON_3_SUPER_120B_A12B = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 235929, + context_window: 1048576, + max_output_tokens: 262144, pricing: { text: { input: { @@ -7530,38 +7302,6 @@ const NVIDIA_NEMOTRON_3_SUPER_120B_A12B = { }, reasoning: BUDGET_NONE_LOW_MEDIUM, } as const -const NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE = { - id: 'nvidia/nemotron-3-super-120b-a12b:free', - name: 'NVIDIA: Nemotron 3 Super (free)', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 235929, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, - reasoning: BUDGET_NONE_LOW_MEDIUM, -} as const const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B = { id: 'nvidia/nemotron-3-ultra-550b-a55b', name: 'NVIDIA: Nemotron 3 Ultra', @@ -7785,7 +7525,7 @@ const NVIDIA_NEMOTRON_3_5_SUPER_VL = { ], }, context_window: 1048576, - max_output_tokens: 235929, + max_output_tokens: 943718, pricing: { text: { input: { @@ -7830,42 +7570,6 @@ const NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE = { image: 0, }, } as const -const OPENAI_GPT_3_5_TURBO = { - id: 'openai/gpt-3.5-turbo', - name: 'OpenAI: GPT-3.5 Turbo', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 16385, - max_output_tokens: 4096, - pricing: { - text: { - input: { - normal: 0.5, - cached: 0, - }, - output: { - normal: 1.5, - }, - }, - image: 0, - }, -} as const const OPENAI_GPT_3_5_TURBO_0613 = { id: 'openai/gpt-3.5-turbo-0613', name: 'OpenAI: GPT-3.5 Turbo (older v0613)', @@ -7913,7 +7617,6 @@ const OPENAI_GPT_3_5_TURBO_16K = { 'logitBias', 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', @@ -7933,125 +7636,17 @@ const OPENAI_GPT_3_5_TURBO_16K = { cached: 0, }, output: { - normal: 4, - }, - }, - image: 0, - }, -} as const -const OPENAI_GPT_3_5_TURBO_INSTRUCT = { - id: 'openai/gpt-3.5-turbo-instruct', - name: 'OpenAI: GPT-3.5 Turbo Instruct', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'topLogprobs', - 'topP', - ], - }, - context_window: 4095, - max_output_tokens: 3685, - pricing: { - text: { - input: { - normal: 1.5, - cached: 0, - }, - output: { - normal: 2, - }, - }, - image: 0, - }, -} as const -const OPENAI_GPT_3_5_TURBO_BATCH = { - id: 'openai/gpt-3.5-turbo:batch', - name: 'OpenAI: GPT-3.5 Turbo (batch)', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 16385, - max_output_tokens: 4096, - pricing: { - text: { - input: { - normal: 0.25, - cached: 0, - }, - output: { - normal: 0.75, - }, - }, - image: 0, - }, -} as const -const OPENAI_GPT_4 = { - id: 'openai/gpt-4', - name: 'OpenAI: GPT-4', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 8191, - max_output_tokens: 4096, - pricing: { - text: { - input: { - normal: 30, - cached: 0, - }, - output: { - normal: 60, + normal: 4, }, }, image: 0, }, } as const -const OPENAI_GPT_4_TURBO = { - id: 'openai/gpt-4-turbo', - name: 'OpenAI: GPT-4 Turbo', +const OPENAI_GPT_4 = { + id: 'openai/gpt-4', + name: 'OpenAI: GPT-4', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', @@ -8068,16 +7663,16 @@ const OPENAI_GPT_4_TURBO = { 'topP', ], }, - context_window: 128000, + context_window: 8191, max_output_tokens: 4096, pricing: { text: { input: { - normal: 10, + normal: 30, cached: 0, }, output: { - normal: 30, + normal: 60, }, }, image: 0, @@ -8218,7 +7813,6 @@ const OPENAI_GPT_4_1_NANO = { input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'responseFormat', 'seed', @@ -8228,12 +7822,12 @@ const OPENAI_GPT_4_1_NANO = { ], }, context_window: 1047576, - max_output_tokens: 32768, + max_output_tokens: 942818, pricing: { text: { input: { normal: 0.1, - cached: 0.025, + cached: 0.03, }, output: { normal: 0.4, @@ -8350,7 +7944,6 @@ const OPENAI_GPT_4O_2024_05_13 = { 'logitBias', 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', @@ -10507,6 +10100,124 @@ const OPENAI_GPT_6_1_SOL_BATCH = { image: 0, }, } as const +const OPENAI_GPT_6_1_TERRA = { + id: 'openai/gpt-6.1-terra', + name: 'OpenAI: GPT-6.1 Terra', + supports: { + input: ['document', 'image', 'text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + '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_TERRA_PRO = { + id: 'openai/gpt-6.1-terra-pro', + name: 'OpenAI: GPT-6.1 Terra Pro', + supports: { + input: ['document', 'image', 'text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + '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_TERRA_PRO_BATCH = { + id: 'openai/gpt-6.1-terra-pro:batch', + name: 'OpenAI: GPT-6.1 Terra 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: 0.5, + cached: 0.65, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const +const OPENAI_GPT_6_1_TERRA_BATCH = { + id: 'openai/gpt-6.1-terra:batch', + name: 'OpenAI: GPT-6.1 Terra (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: 0.5, + cached: 0.65, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const const OPENAI_GPT_AUDIO = { id: 'openai/gpt-audio', name: 'OpenAI: GPT Audio', @@ -10629,11 +10340,11 @@ const OPENAI_GPT_OSS_120B = { pricing: { text: { input: { - normal: 0.15, - cached: 0.075, + normal: 0.025, + cached: 0.022, }, output: { - normal: 0.6, + normal: 0.092, }, }, image: 0, @@ -10699,15 +10410,15 @@ const OPENAI_GPT_OSS_20B = { ], }, context_window: 131072, - max_output_tokens: 32768, + max_output_tokens: 117964, pricing: { text: { input: { - normal: 0.018, - cached: 0.009, + normal: 0.03, + cached: 0.03, }, output: { - normal: 0.09, + normal: 0.13, }, }, image: 0, @@ -10783,60 +10494,6 @@ const OPENAI_GPT_OSS_SAFEGUARD_20B = { }, reasoning: EFFORT_LOW_TO_HIGH, } as const -const OPENAI_O1 = { - id: 'openai/o1', - name: 'OpenAI: o1', - supports: { - input: ['text', 'image', 'document'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'toolChoice', - ], - }, - context_window: 200000, - max_output_tokens: 100000, - pricing: { - text: { - input: { - normal: 15, - cached: 7.5, - }, - output: { - normal: 60, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const -const OPENAI_O1_PRO = { - id: 'openai/o1-pro', - name: 'OpenAI: o1-pro', - supports: { - input: ['text', 'image', 'document'], - output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'responseFormat', 'seed'], - }, - context_window: 200000, - max_output_tokens: 100000, - pricing: { - text: { - input: { - normal: 150, - cached: 0, - }, - output: { - normal: 600, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const const OPENAI_O3 = { id: 'openai/o3', name: 'OpenAI: o3', @@ -10867,66 +10524,6 @@ const OPENAI_O3 = { }, reasoning: EFFORT_OFF_HIGH, } as const -const OPENAI_O3_MINI = { - id: 'openai/o3-mini', - name: 'OpenAI: o3 Mini', - supports: { - input: ['text', 'document'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'toolChoice', - ], - }, - context_window: 200000, - max_output_tokens: 100000, - pricing: { - text: { - input: { - normal: 1.1, - cached: 0.55, - }, - output: { - normal: 4.4, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const -const OPENAI_O3_MINI_HIGH = { - id: 'openai/o3-mini-high', - name: 'OpenAI: o3 Mini High', - supports: { - input: ['text', 'document'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'toolChoice', - ], - }, - context_window: 200000, - max_output_tokens: 100000, - pricing: { - text: { - input: { - normal: 1.1, - cached: 0.55, - }, - output: { - normal: 4.4, - }, - }, - image: 0, - }, - reasoning: EFFORT_HIGH, -} as const const OPENAI_O3_MINI_BATCH = { id: 'openai/o3-mini:batch', name: 'OpenAI: o3 Mini (batch)', @@ -11006,50 +10603,20 @@ const OPENAI_O3_BATCH = { pricing: { text: { input: { - normal: 1, - cached: 0.25, - }, - output: { - normal: 4, - }, - }, - image: 0, - }, - reasoning: EFFORT_MINIMAL_TO_HIGH, -} as const -const OPENAI_O4_MINI = { - id: 'openai/o4-mini', - name: 'OpenAI: o4 Mini', - supports: { - input: ['image', 'text', 'document'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'responseFormat', - 'seed', - 'toolChoice', - ], - }, - context_window: 200000, - max_output_tokens: 100000, - pricing: { - text: { - input: { - normal: 1.1, - cached: 0.275, + normal: 1, + cached: 0.25, }, output: { - normal: 4.4, + normal: 4, }, }, image: 0, }, - reasoning: EFFORT_OFF_HIGH, + reasoning: EFFORT_MINIMAL_TO_HIGH, } as const -const OPENAI_O4_MINI_HIGH = { - id: 'openai/o4-mini-high', - name: 'OpenAI: o4 Mini High', +const OPENAI_O4_MINI_BATCH = { + id: 'openai/o4-mini:batch', + name: 'OpenAI: o4 Mini (batch)', supports: { input: ['image', 'text', 'document'], output: ['text'], @@ -11066,46 +10633,52 @@ const OPENAI_O4_MINI_HIGH = { pricing: { text: { input: { - normal: 1.1, - cached: 0.275, + normal: 0.55, + cached: 0.1375, }, output: { - normal: 4.4, + normal: 2.2, }, }, image: 0, }, - reasoning: EFFORT_HIGH, + reasoning: EFFORT_MINIMAL_TO_HIGH, } as const -const OPENAI_O4_MINI_BATCH = { - id: 'openai/o4-mini:batch', - name: 'OpenAI: o4 Mini (batch)', +const PARTICLE_AI_PARTICLE_1 = { + id: 'particle-ai/particle-1', + name: 'Particle AI: Particle-1', supports: { - input: ['image', 'text', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 1048576, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.55, - cached: 0.1375, + normal: 0.05, + cached: 0.003, }, output: { - normal: 2.2, + normal: 0.5, }, }, image: 0, }, - reasoning: EFFORT_MINIMAL_TO_HIGH, } as const const PERCEPTRON_PERCEPTRON_MK1 = { id: 'perceptron/perceptron-mk1', @@ -11321,105 +10894,46 @@ const PERPLEXITY_SONAR_REASONING_PRO = { }, reasoning: EFFORT_OFF_HIGH, } as const -const POOLSIDE_LAGUNA_S_2_1 = { - id: 'poolside/laguna-s-2.1', - name: 'Poolside: Laguna S 2.1', - supports: { - input: ['text'], - output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], - }, - context_window: 1048576, - max_output_tokens: 131072, - pricing: { - text: { - input: { - normal: 0.09, - cached: 0.009, - }, - output: { - normal: 0.18, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const -const POOLSIDE_LAGUNA_S_2_1_FREE = { - id: 'poolside/laguna-s-2.1:free', - name: 'Poolside: Laguna S 2.1 (free)', - supports: { - input: ['text'], - output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], - }, - context_window: 262144, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const -const POOLSIDE_LAGUNA_XS_2_1 = { - id: 'poolside/laguna-xs-2.1', - name: 'Poolside: Laguna XS 2.1', - supports: { - input: ['text'], - output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], - }, - context_window: 262144, - max_output_tokens: 32768, - pricing: { - text: { - input: { - normal: 0.06, - cached: 0.03, - }, - output: { - normal: 0.12, - }, - }, - image: 0, - }, - reasoning: EFFORT_OFF_HIGH, -} as const -const POOLSIDE_LAGUNA_XS_2_1_FREE = { - id: 'poolside/laguna-xs-2.1:free', - name: 'Poolside: Laguna XS 2.1 (free)', +const PRISM_ML_TERNARY_BONSAI_2_27B = { + id: 'prism-ml/ternary-bonsai-2-27b', + name: 'PrismML: Ternary Bonsai 2 27B', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], }, context_window: 262144, max_output_tokens: 32768, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.075, + cached: 0.0375, }, output: { - normal: 0, + normal: 0.5, }, }, image: 0, }, - reasoning: EFFORT_OFF_HIGH, + reasoning: EFFORT_NONE_MEDIUM_XHIGH, } as const -const PRISM_ML_TERNARY_BONSAI_2_27B = { - id: 'prism-ml/ternary-bonsai-2-27b', - name: 'PrismML: Ternary Bonsai 2 27B', +const PRISM_ML_TERNARY_BONSAI_2_9B = { + id: 'prism-ml/ternary-bonsai-2-9b', + name: 'PrismML: Ternary Bonsai 2 9B', supports: { input: ['text', 'image'], output: ['text'], @@ -11439,20 +10953,19 @@ const PRISM_ML_TERNARY_BONSAI_2_27B = { ], }, context_window: 262144, - max_output_tokens: 32768, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.075, - cached: 0.0375, + normal: 0.08, + cached: 0.04, }, output: { - normal: 0.5, + normal: 0.13, }, }, image: 0, }, - reasoning: EFFORT_NONE_MEDIUM_XHIGH, } as const const QWEN_QWEN_2_5_72B_INSTRUCT = { id: 'qwen/qwen-2.5-72b-instruct', @@ -11684,15 +11197,15 @@ const QWEN_QWEN3_235B_A22B_2507 = { ], }, context_window: 262144, - max_output_tokens: 16384, + max_output_tokens: 117964, pricing: { text: { input: { - normal: 0.09, - cached: 0, + normal: 0.14, + cached: 0.05, }, output: { - normal: 0.55, + normal: 0.8, }, }, image: 0, @@ -11793,8 +11306,8 @@ const QWEN_QWEN3_30B_A3B_INSTRUCT_2507 = { pricing: { text: { input: { - normal: 0.09, - cached: 0, + normal: 0.1, + cached: 0.1, }, output: { normal: 0.3, @@ -11850,7 +11363,6 @@ const QWEN_QWEN3_CODER = { supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -11858,7 +11370,6 @@ const QWEN_QWEN3_CODER = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -11898,11 +11409,11 @@ const QWEN_QWEN3_CODER_30B_A3B_INSTRUCT = { pricing: { text: { input: { - normal: 0.07, + normal: 0.15, cached: 0, }, output: { - normal: 0.28, + normal: 0.6, }, }, image: 0, @@ -12001,56 +11512,19 @@ const QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT = { ], }, context_window: 262144, - max_output_tokens: 16384, - pricing: { - text: { - input: { - normal: 0.09, - cached: 0, - }, - output: { - normal: 1.1, - }, - }, - image: 0, - }, -} as const -const QWEN_QWEN3_NEXT_80B_A3B_THINKING = { - id: 'qwen/qwen3-next-80b-a3b-thinking', - name: 'Qwen: Qwen3 Next 80B A3B 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: 235929, pricing: { text: { input: { - normal: 0.15, - cached: 0, + normal: 0.1, + cached: 0.07, }, output: { - normal: 1.2, + normal: 1.1, }, }, image: 0, }, - reasoning: EFFORT_MINIMAL_TO_HIGH, } as const const QWEN_QWEN3_VL_235B_A22B_INSTRUCT = { id: 'qwen/qwen3-vl-235b-a22b-instruct', @@ -12219,11 +11693,11 @@ const QWEN_QWEN3_5_122B_A10B = { pricing: { text: { input: { - normal: 0.4, + normal: 0.26, cached: 0, }, output: { - normal: 3.2, + normal: 2.08, }, }, image: 0, @@ -12253,15 +11727,15 @@ const QWEN_QWEN3_5_27B = { ], }, context_window: 262144, - max_output_tokens: 65536, + max_output_tokens: 81920, pricing: { text: { input: { - normal: 0.27, - cached: 0.27, + normal: 0.26, + cached: 0, }, output: { - normal: 2.16, + normal: 2.6, }, }, image: 0, @@ -12355,6 +11829,7 @@ const QWEN_QWEN3_5_9B = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', @@ -12367,15 +11842,15 @@ const QWEN_QWEN3_5_9B = { ], }, context_window: 262144, - max_output_tokens: 65536, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.08, - cached: 0.04, + normal: 0.17, + cached: 0, }, output: { - normal: 0.13, + normal: 0.25, }, }, image: 0, @@ -12518,11 +11993,11 @@ const QWEN_QWEN3_6_27B = { pricing: { text: { input: { - normal: 0.25, - cached: 0.025, + normal: 0.45, + cached: 0, }, output: { - normal: 2, + normal: 2.7, }, }, image: 0, @@ -12557,10 +12032,10 @@ const QWEN_QWEN3_6_35B_A3B = { text: { input: { normal: 0.1, - cached: 0.05, + cached: 0.025, }, output: { - normal: 0.95, + normal: 0.9, }, }, image: 0, @@ -12809,7 +12284,7 @@ const QWEN_QWEN3_8_2_4T_A95B = { ], }, context_window: 1048576, - max_output_tokens: 909000, + max_output_tokens: 131072, pricing: { text: { input: { @@ -12846,16 +12321,16 @@ const QWEN_QWEN3_8_27B = { 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 1024000, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.04, - cached: 0.018, + normal: 0.15, + cached: 0.0375, }, output: { - normal: 1.35, + normal: 1.875, }, }, image: 0, @@ -13066,12 +12541,12 @@ const REFLECTION_BEAM_1_0_501B_A23B = { ], }, context_window: 1048576, - max_output_tokens: 943718, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.3, - cached: 0.04, + normal: 0.25, + cached: 0.05, }, output: { normal: 1, @@ -13397,12 +12872,42 @@ const SCALEDOWN_SUMMARIZE = { output: ['text'], supports: ['maxCompletionTokens'], }, - context_window: 1000000, - max_output_tokens: 4000, + context_window: 1000000, + max_output_tokens: 4000, + pricing: { + text: { + input: { + normal: 0.04, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const +const STEALTH_CROUTON_ALPHA = { + id: 'stealth/crouton-alpha', + name: 'Crouton Alpha', + 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: 0.04, + normal: 0, cached: 0, }, output: { @@ -13488,7 +12993,6 @@ const STEPFUN_STEP_5_PREVIEW = { output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', @@ -13702,6 +13206,37 @@ const TENCENT_HY3_PREVIEW = { }, reasoning: EFFORT_NONE_LOW_HIGH, } as const +const TENCENT_HY4 = { + id: 'tencent/hy4', + name: 'Tencent: Hy4', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + ], + }, + context_window: 1048576, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.417, + cached: 0.021, + }, + output: { + normal: 1.2505, + }, + }, + image: 0, + }, +} as const const TENCENT_HY4_PREVIEW = { id: 'tencent/hy4-preview', name: 'Tencent: Hy4 preview', @@ -13711,8 +13246,10 @@ const TENCENT_HY4_PREVIEW = { supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -13720,6 +13257,7 @@ const TENCENT_HY4_PREVIEW = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, @@ -13855,7 +13393,6 @@ const THINKINGMACHINES_INKLING = { 'maxCompletionTokens', 'presencePenalty', 'reasoning', - 'seed', 'stop', 'temperature', 'toolChoice', @@ -13913,72 +13450,6 @@ const THINKINGMACHINES_INKLING_SMALL = { }, reasoning: EFFORT_NONE_MINIMAL_TO_HIGH_MAX, } as const -const THINKINGMACHINES_INKLING_SMALL_FREE = { - id: 'thinkingmachines/inkling-small:free', - name: 'Thinking Machines: Inkling Small (free)', - supports: { - input: ['text', 'image', 'audio'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 1048576, - max_output_tokens: 262144, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, - reasoning: EFFORT_NONE_MINIMAL_TO_HIGH_MAX, -} as const -const THINKINGMACHINES_INKLING_FREE = { - id: 'thinkingmachines/inkling:free', - name: 'Thinking Machines: Inkling (free)', - supports: { - input: ['text', 'image', 'audio'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 1048576, - max_output_tokens: 262144, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, - reasoning: EFFORT_NONE_MINIMAL_TO_HIGH_MAX, -} as const const UNBIASED_PARETO_26_10 = { id: 'unbiased/pareto-26.10', name: 'Pareto 26.10', @@ -14100,40 +13571,6 @@ const UPSTAGE_SOLAR_MINI4 = { }, reasoning: EFFORT_NONE_MINIMAL_TO_MAX, } as const -const UPSTAGE_SOLAR_PRO_3 = { - id: 'upstage/solar-pro-3', - name: 'Upstage: Solar Pro 3', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'parallelToolCalls', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 117964, - pricing: { - text: { - input: { - normal: 0.15, - cached: 0.015, - }, - output: { - normal: 0.6, - }, - }, - image: 0, - }, - reasoning: EFFORT_NONE_MINIMAL_TO_HIGH, -} as const const UPSTAGE_SOLAR_PRO4 = { id: 'upstage/solar-pro4', name: 'Upstage: Solar Pro 4', @@ -14395,6 +13832,39 @@ const X_AI_GROK_4_6 = { }, reasoning: EFFORT_LOW_TO_XHIGH, } as const +const X_AI_GROK_4_6_BATCH = { + id: 'x-ai/grok-4.6:batch', + name: 'SpaceXAI: Grok 4.6 (batch)', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 500000, + max_output_tokens: 450000, + pricing: { + text: { + input: { + normal: 1.6, + cached: 0.4, + }, + output: { + normal: 4.8, + }, + }, + image: 0, + }, +} as const const X_AI_GROK_4_7 = { id: 'x-ai/grok-4.7', name: 'SpaceXAI: Grok 4.7', @@ -14407,6 +13877,7 @@ const X_AI_GROK_4_7 = { 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topLogprobs', @@ -14429,6 +13900,39 @@ const X_AI_GROK_4_7 = { }, reasoning: EFFORT_LOW_TO_XHIGH, } as const +const X_AI_GROK_4_7_BATCH = { + id: 'x-ai/grok-4.7:batch', + name: 'SpaceXAI: Grok 4.7 (batch)', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 500000, + max_output_tokens: 450000, + pricing: { + text: { + input: { + normal: 1.6, + cached: 0.4, + }, + output: { + normal: 4.8, + }, + }, + image: 0, + }, +} as const const X_AI_GROK_BUILD_0_1 = { id: 'x-ai/grok-build-0.1', name: 'SpaceXAI: Grok Build 0.1', @@ -14475,23 +13979,22 @@ const XIAOMI_MIMO_V2_5 = { 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 1050000, - max_output_tokens: 945000, + context_window: 1000000, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.119, - cached: 0.00255, + normal: 0.4, + cached: 0.08, }, output: { - normal: 0.238, + normal: 2, }, }, image: 0, @@ -14505,14 +14008,11 @@ const XIAOMI_MIMO_V2_5_PRO = { input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', 'temperature', 'toolChoice', 'topLogprobs', @@ -14520,15 +14020,15 @@ const XIAOMI_MIMO_V2_5_PRO = { ], }, context_window: 1050000, - max_output_tokens: 945000, + max_output_tokens: 235929, pricing: { text: { input: { - normal: 0.3045, - cached: 0.0028, + normal: 0.48, + cached: 0.096, }, output: { - normal: 0.609, + normal: 1.8, }, }, image: 0, @@ -14546,6 +14046,7 @@ const XIAOMI_MIMO_V2_6_FLASH = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -14802,11 +14303,11 @@ const Z_AI_GLM_4_6 = { pricing: { text: { input: { - normal: 0.55, - cached: 0.11, + normal: 0.5, + cached: 0.1, }, output: { - normal: 2.2, + normal: 2, }, }, image: 0, @@ -14873,11 +14374,11 @@ const Z_AI_GLM_4_7 = { pricing: { text: { input: { - normal: 0.54, - cached: 0.099, + normal: 0.6, + cached: 0.11, }, output: { - normal: 1.98, + normal: 2.2, }, }, image: 0, @@ -15056,11 +14557,11 @@ const Z_AI_GLM_5_2 = { pricing: { text: { input: { - normal: 0.0341, - cached: 0.033, + normal: 0.006, + cached: 0.005, }, output: { - normal: 7, + normal: 6.8, }, }, image: 0, @@ -15095,11 +14596,11 @@ const Z_AI_GLM_5_3 = { pricing: { text: { input: { - normal: 0.079, - cached: 0.078, + normal: 0.08, + cached: 0.076, }, output: { - normal: 1.4, + normal: 3.6, }, }, image: 0, @@ -15130,15 +14631,15 @@ const Z_AI_GLM_5_3_FLASH = { ], }, context_window: 1048576, - max_output_tokens: 943718, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.0052, - cached: 0.0052, + normal: 0.0269, + cached: 0.0269, }, output: { - normal: 0.1985, + normal: 0.0996, }, }, image: 0, @@ -15156,14 +14657,45 @@ const Z_AI_GLM_5_3_FLASH_BATCH = { 'logitBias', 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.05, + cached: 0.01, + }, + output: { + normal: 0.18, + }, + }, + image: 0, + }, + reasoning: EFFORT_LOW_HIGH_MAX, +} as const +const Z_AI_GLM_5_3_FLASHX = { + id: 'z-ai/glm-5.3-flashx', + name: 'Z.ai: GLM 5.3 FlashX', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'maxCompletionTokens', 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -15172,20 +14704,20 @@ const Z_AI_GLM_5_3_FLASH_BATCH = { pricing: { text: { input: { - normal: 0.05, - cached: 0.01, + normal: 0.37, + cached: 0.075, }, output: { - normal: 0.18, + normal: 1.25, }, }, image: 0, }, reasoning: EFFORT_LOW_HIGH_MAX, } as const -const Z_AI_GLM_5_3_FLASHX = { - id: 'z-ai/glm-5.3-flashx', - name: 'Z.ai: GLM 5.3 FlashX', +const Z_AI_GLM_5_3_FLASHX_LEGAL = { + id: 'z-ai/glm-5.3-flashx-legal', + name: 'Z.ai: GLM 5.3 FlashX Legal', supports: { input: ['text', 'image', 'video'], output: ['text'], @@ -15204,7 +14736,7 @@ const Z_AI_GLM_5_3_FLASHX = { text: { input: { normal: 0.37, - cached: 0.09, + cached: 0.075, }, output: { normal: 1.25, @@ -15212,7 +14744,6 @@ const Z_AI_GLM_5_3_FLASHX = { }, image: 0, }, - reasoning: EFFORT_LOW_HIGH_MAX, } as const const Z_AI_GLM_5_3_PRIME = { id: 'z-ai/glm-5.3-prime', @@ -15436,6 +14967,8 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -15502,6 +15035,7 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' @@ -15871,11 +15405,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'stop' | 'toolChoice' > - [ARCEE_AI_TRINITY_LARGE_THINKING.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'temperature' | 'toolChoice' | 'topP' - > [BYTEDANCE_SEED_SEED_1_6.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -16106,7 +15635,6 @@ export type OpenRouterModelOptionsByName = { | 'frequencyPenalty' | 'maxCompletionTokens' | 'responseFormat' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -16227,6 +15755,7 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -16666,6 +16195,7 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -16692,6 +16222,7 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -16736,21 +16267,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [IBM_GRANITE_GRANITE_4_0_H_MICRO.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'topLogprobs' - | 'topP' - > [IBM_GRANITE_GRANITE_4_2_8B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -16866,7 +16382,7 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [LIQUID_LFM_2_5_2_6B_FREE.id]: OpenRouterCommonOptions & + [LIQUID_LFM_2_5_2_6B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16880,8 +16396,9 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'toolChoice' | 'topLogprobs' + | 'topP' > - [LIQUID_LFM_2_5_24B_A2B.id]: OpenRouterCommonOptions & + [LIQUID_LFM_2_5_2_6B_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -16895,49 +16412,57 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'toolChoice' | 'topLogprobs' + | 'topP' > - [MANCER_WEAVER.id]: OpenRouterCommonOptions & + [LIQUID_LFM_2_5_24B_A2B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topLogprobs' | 'topP' > - [MEITUAN_LONGCAT_2_0.id]: OpenRouterCommonOptions & + [MANCER_WEAVER.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' + | 'topLogprobs' | 'topP' > - [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: OpenRouterCommonOptions & + [MEITUAN_LONGCAT_2_0.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' - | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > + [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + > [META_LLAMA_LLAMA_3_1_8B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17152,17 +16677,7 @@ export type OpenRouterModelOptionsByName = { [MINIMAX_MINIMAX_M2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' + 'maxCompletionTokens' | 'temperature' | 'toolChoice' | 'topP' > [MINIMAX_MINIMAX_M2_HER.id]: OpenRouterCommonOptions & Pick @@ -17221,19 +16736,12 @@ 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 & + [MINIMAX_MINIMAX_M3_1_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -17241,9 +16749,10 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MISTRALAI_CODESTRAL_2508_BATCH.id]: OpenRouterCommonOptions & + [MISTRALAI_CODESTRAL_2508.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -17308,19 +16817,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MISTRALAI_MINISTRAL_8B_2512_BATCH.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [MISTRALAI_MISTRAL_LARGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17360,19 +16856,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MISTRALAI_MISTRAL_LARGE_2512_BATCH.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [MISTRALAI_MISTRAL_LARGE_4_0.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17440,19 +16923,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [MISTRALAI_MISTRAL_NEMO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17508,19 +16978,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MISTRALAI_MISTRAL_SMALL_2603_BATCH.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -17617,7 +17074,6 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -17625,7 +17081,6 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [MOONSHOTAI_KIMI_K2_5.id]: OpenRouterCommonOptions & @@ -17685,6 +17140,8 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -17708,17 +17165,21 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MORPH_MORPH_V3_FAST.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K3_1_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'responseFormat' | 'stop' | 'temperature' + | 'toolChoice' | 'topLogprobs' + | 'topP' > - [MORPH_MORPH_V3_LARGE.id]: OpenRouterCommonOptions & + [MORPH_MORPH_V3_FAST.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'logprobs' @@ -17728,84 +17189,36 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topLogprobs' > - [NEX_AGI_NEX_N2_5_MINI.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'logprobs' - | 'maxCompletionTokens' - | 'temperature' - | 'topLogprobs' - | 'topP' - > - [NEX_AGI_NEX_N2_5_PRO.id]: OpenRouterCommonOptions & + [MORPH_MORPH_V3_LARGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'logprobs' | 'maxCompletionTokens' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'seed' | 'stop' | 'temperature' - | 'topP' + | 'topLogprobs' > - [NOUSRESEARCH_HERMES_4_405B.id]: OpenRouterCommonOptions & + [NEX_AGI_NEX_N2_5_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' | 'temperature' | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: OpenRouterCommonOptions & + [NEX_AGI_NEX_N2_5_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' - > - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: OpenRouterCommonOptions & + [NOUSRESEARCH_HERMES_4_405B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -17817,62 +17230,14 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'maxCompletionTokens' - | 'responseFormat' - | 'seed' - | 'temperature' - | 'toolChoice' - | 'topP' - > - [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > - [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' - > - [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > - [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'seed' | 'temperature' | 'topP' - > - [NVIDIA_NEMOTRON_3_5_LIGHTNING.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -17880,15 +17245,14 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > - [NVIDIA_NEMOTRON_3_5_SUPER_VL.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -17904,33 +17268,43 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' + | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [OPENAI_GPT_3_5_TURBO.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' + > + [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' - | 'topLogprobs' | 'topP' > - [OPENAI_GPT_3_5_TURBO_0613.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'seed' | 'temperature' | 'topP' + > + [NVIDIA_NEMOTRON_3_5_LIGHTNING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -17946,14 +17320,18 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_3_5_TURBO_16K.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' + > + [NVIDIA_NEMOTRON_3_5_SUPER_VL.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -17963,22 +17341,17 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_5_SUPER_VL_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' - | 'topLogprobs' + | 'toolChoice' | 'topP' > - [OPENAI_GPT_3_5_TURBO_BATCH.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO_0613.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -17994,14 +17367,13 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO_16K.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -18011,7 +17383,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4_TURBO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -18079,7 +17451,6 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'temperature' @@ -18130,7 +17501,6 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -18669,6 +18039,34 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' > + [OPENAI_GPT_6_1_TERRA.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_6_1_TERRA_PRO.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_6_1_TERRA_PRO_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' + > + [OPENAI_GPT_6_1_TERRA_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' + > [OPENAI_GPT_AUDIO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -18777,31 +18175,11 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [OPENAI_O1.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' - > - [OPENAI_O1_PRO.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' - > [OPENAI_O3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_O3_MINI.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' - > - [OPENAI_O3_MINI_HIGH.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' - > [OPENAI_O3_MINI_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -18817,20 +18195,25 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_O4_MINI.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' - > - [OPENAI_O4_MINI_HIGH.id]: OpenRouterCommonOptions & + [OPENAI_O4_MINI_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_O4_MINI_BATCH.id]: OpenRouterCommonOptions & + [PARTICLE_AI_PARTICLE_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' > [PERCEPTRON_PERCEPTRON_MK1.id]: OpenRouterCommonOptions & Pick< @@ -18896,27 +18279,22 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [POOLSIDE_LAGUNA_S_2_1.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'temperature' | 'toolChoice' - > - [POOLSIDE_LAGUNA_S_2_1_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'temperature' | 'toolChoice' - > - [POOLSIDE_LAGUNA_XS_2_1.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'temperature' | 'toolChoice' - > - [POOLSIDE_LAGUNA_XS_2_1_FREE.id]: OpenRouterCommonOptions & + [PRISM_ML_TERNARY_BONSAI_2_27B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'temperature' | 'toolChoice' + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' > - [PRISM_ML_TERNARY_BONSAI_2_27B.id]: OpenRouterCommonOptions & + [PRISM_ML_TERNARY_BONSAI_2_9B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -19095,7 +18473,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -19103,7 +18480,6 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & @@ -19164,21 +18540,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19308,6 +18669,7 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -19679,6 +19041,15 @@ export type OpenRouterModelOptionsByName = { Pick [SCALEDOWN_SUMMARIZE.id]: OpenRouterCommonOptions & Pick + [STEALTH_CROUTON_ALPHA.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > [STEPFUN_STEP_3_5_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19707,7 +19078,6 @@ export type OpenRouterModelOptionsByName = { Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' @@ -19771,19 +19141,32 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > + [TENCENT_HY4.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > [TENCENT_HY4_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > [THEDRUMMER_CYDONIA_24B_V4_1.id]: OpenRouterCommonOptions & @@ -19837,7 +19220,6 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' @@ -19856,28 +19238,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [THINKINGMACHINES_INKLING_SMALL_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > - [THINKINGMACHINES_INKLING_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > [UNBIASED_PARETO_26_10.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -19919,18 +19279,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [UPSTAGE_SOLAR_PRO_3.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'parallelToolCalls' - | 'presencePenalty' - | 'responseFormat' - | 'temperature' - | 'toolChoice' - | 'topP' - > [UPSTAGE_SOLAR_PRO4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -20020,7 +19368,32 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [X_AI_GROK_4_6_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'logprobs' + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > [X_AI_GROK_4_7.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'logprobs' + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [X_AI_GROK_4_7_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'logprobs' @@ -20051,7 +19424,6 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' @@ -20060,13 +19432,10 @@ export type OpenRouterModelOptionsByName = { [XIAOMI_MIMO_V2_5_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' @@ -20079,6 +19448,7 @@ export type OpenRouterModelOptionsByName = { | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -20334,6 +19704,15 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > + [Z_AI_GLM_5_3_FLASHX_LEGAL.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > [Z_AI_GLM_5_3_PRIME.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -20481,7 +19860,6 @@ export type OpenRouterModelInputModalitiesByName = { [ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'document' > - [ARCEE_AI_TRINITY_LARGE_THINKING.id]: ReadonlyArray<'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'> @@ -20604,7 +19982,6 @@ export type OpenRouterModelInputModalitiesByName = { [GOOGLE_LYRIA_3_CLIP_PREVIEW.id]: ReadonlyArray<'text' | 'image'> [GOOGLE_LYRIA_3_PRO_PREVIEW.id]: ReadonlyArray<'text' | 'image'> [GRYPHE_MYTHOMAX_L2_13B.id]: ReadonlyArray<'text'> - [IBM_GRANITE_GRANITE_4_0_H_MICRO.id]: ReadonlyArray<'text'> [IBM_GRANITE_GRANITE_4_2_8B.id]: ReadonlyArray<'text'> [INCEPTION_MERCURY_2.id]: ReadonlyArray<'text'> [INCEPTION_MERCURY_2_5.id]: ReadonlyArray<'text'> @@ -20614,6 +19991,7 @@ export type OpenRouterModelInputModalitiesByName = { [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.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'> @@ -20657,24 +20035,17 @@ 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' - > + [MINIMAX_MINIMAX_M3_1_FLASH.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'> [MISTRALAI_MINISTRAL_14B_2512.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MINISTRAL_3B_2512.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MINISTRAL_8B_2512.id]: ReadonlyArray<'text' | 'image'> - [MISTRALAI_MINISTRAL_8B_2512_BATCH.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MISTRAL_LARGE.id]: ReadonlyArray<'text' | 'document'> [MISTRALAI_MISTRAL_LARGE_2407.id]: ReadonlyArray<'text' | 'document'> [MISTRALAI_MISTRAL_LARGE_2512.id]: ReadonlyArray< 'text' | 'image' | 'document' > - [MISTRALAI_MISTRAL_LARGE_2512_BATCH.id]: ReadonlyArray< - 'text' | 'image' | 'document' - > [MISTRALAI_MISTRAL_LARGE_4_0.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MISTRAL_MEDIUM_3.id]: ReadonlyArray<'text' | 'image' | 'document'> [MISTRALAI_MISTRAL_MEDIUM_3_5.id]: ReadonlyArray< @@ -20686,14 +20057,10 @@ export type OpenRouterModelInputModalitiesByName = { [MISTRALAI_MISTRAL_MEDIUM_3_1.id]: ReadonlyArray< 'text' | 'image' | 'document' > - [MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH.id]: ReadonlyArray< - 'text' | 'image' | 'document' - > [MISTRALAI_MISTRAL_NEMO.id]: ReadonlyArray<'text'> [MISTRALAI_MISTRAL_SABA.id]: ReadonlyArray<'text' | 'document'> [MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501.id]: ReadonlyArray<'text'> [MISTRALAI_MISTRAL_SMALL_2603.id]: ReadonlyArray<'text' | 'image'> - [MISTRALAI_MISTRAL_SMALL_2603_BATCH.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id]: ReadonlyArray<'image' | 'text'> [MISTRALAI_MIXTRAL_8X22B_INSTRUCT.id]: ReadonlyArray<'text' | 'document'> @@ -20710,19 +20077,17 @@ export type OpenRouterModelInputModalitiesByName = { [MOONSHOTAI_KIMI_K2_7_CODE.id]: ReadonlyArray<'text' | 'image'> [MOONSHOTAI_KIMI_K3.id]: ReadonlyArray<'text' | 'image' | 'video'> [MOONSHOTAI_KIMI_K3_BATCH.id]: ReadonlyArray<'text' | 'image' | 'video'> + [MOONSHOTAI_KIMI_K3_1_PRO.id]: ReadonlyArray<'text' | 'image' | 'video'> [MORPH_MORPH_V3_FAST.id]: ReadonlyArray<'text'> [MORPH_MORPH_V3_LARGE.id]: ReadonlyArray<'text'> [NEX_AGI_NEX_N2_5_MINI.id]: ReadonlyArray<'text' | 'image'> [NEX_AGI_NEX_N2_5_PRO.id]: ReadonlyArray<'text' | 'image'> - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id]: ReadonlyArray<'text'> - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id]: ReadonlyArray<'text'> [NOUSRESEARCH_HERMES_4_405B.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id]: ReadonlyArray< 'text' | 'audio' | 'image' | 'video' > [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: ReadonlyArray<'text'> - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY.id]: ReadonlyArray<'text' | 'image'> @@ -20733,13 +20098,9 @@ export type OpenRouterModelInputModalitiesByName = { [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'> - [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: ReadonlyArray<'text'> - [OPENAI_GPT_3_5_TURBO_BATCH.id]: ReadonlyArray<'text'> [OPENAI_GPT_4.id]: ReadonlyArray<'text'> - [OPENAI_GPT_4_TURBO.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_4_TURBO_BATCH.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_4_1.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_4_1_MINI.id]: ReadonlyArray<'image' | 'text' | 'document'> @@ -20830,6 +20191,12 @@ export type OpenRouterModelInputModalitiesByName = { 'document' | 'image' | 'text' > [OPENAI_GPT_6_1_SOL_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_6_1_TERRA.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_6_1_TERRA_PRO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_6_1_TERRA_PRO_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' + > + [OPENAI_GPT_6_1_TERRA_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'> @@ -20838,17 +20205,12 @@ export type OpenRouterModelInputModalitiesByName = { [OPENAI_GPT_OSS_20B.id]: ReadonlyArray<'text'> [OPENAI_GPT_OSS_20B_BATCH.id]: ReadonlyArray<'text'> [OPENAI_GPT_OSS_SAFEGUARD_20B.id]: ReadonlyArray<'text'> - [OPENAI_O1.id]: ReadonlyArray<'text' | 'image' | 'document'> - [OPENAI_O1_PRO.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_O3.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_O3_MINI.id]: ReadonlyArray<'text' | 'document'> - [OPENAI_O3_MINI_HIGH.id]: ReadonlyArray<'text' | 'document'> [OPENAI_O3_MINI_BATCH.id]: ReadonlyArray<'text' | 'document'> [OPENAI_O3_PRO.id]: ReadonlyArray<'text' | 'document' | 'image'> [OPENAI_O3_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_O4_MINI.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_O4_MINI_HIGH.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_O4_MINI_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> + [PARTICLE_AI_PARTICLE_1.id]: ReadonlyArray<'text' | 'image'> [PERCEPTRON_PERCEPTRON_MK1.id]: ReadonlyArray<'text' | 'image' | 'video'> [PERCEPTRON_PERCEPTRON_MK1_5.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'audio' @@ -20858,11 +20220,8 @@ export type OpenRouterModelInputModalitiesByName = { [PERPLEXITY_SONAR_PRO.id]: ReadonlyArray<'text' | 'image'> [PERPLEXITY_SONAR_PRO_SEARCH.id]: ReadonlyArray<'text' | 'image'> [PERPLEXITY_SONAR_REASONING_PRO.id]: ReadonlyArray<'text' | 'image'> - [POOLSIDE_LAGUNA_S_2_1.id]: ReadonlyArray<'text'> - [POOLSIDE_LAGUNA_S_2_1_FREE.id]: ReadonlyArray<'text'> - [POOLSIDE_LAGUNA_XS_2_1.id]: ReadonlyArray<'text'> - [POOLSIDE_LAGUNA_XS_2_1_FREE.id]: ReadonlyArray<'text'> [PRISM_ML_TERNARY_BONSAI_2_27B.id]: ReadonlyArray<'text' | 'image'> + [PRISM_ML_TERNARY_BONSAI_2_9B.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN_2_5_72B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN_2_5_7B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id]: ReadonlyArray<'text'> @@ -20879,7 +20238,6 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN3_CODER_FLASH.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER_NEXT.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_30B_A3B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: ReadonlyArray<'text' | 'image'> @@ -20922,6 +20280,9 @@ export type OpenRouterModelInputModalitiesByName = { [SAO10K_L3_1_EURYALE_70B.id]: ReadonlyArray<'text'> [SCALEDOWN_EXTRACT.id]: ReadonlyArray<'text' | 'image' | 'document'> [SCALEDOWN_SUMMARIZE.id]: ReadonlyArray<'text' | 'image' | 'document'> + [STEALTH_CROUTON_ALPHA.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > [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'> @@ -20931,21 +20292,17 @@ export type OpenRouterModelInputModalitiesByName = { [TENCENT_HY_MT2_7B.id]: ReadonlyArray<'text'> [TENCENT_HY3.id]: ReadonlyArray<'text'> [TENCENT_HY3_PREVIEW.id]: ReadonlyArray<'text'> + [TENCENT_HY4.id]: ReadonlyArray<'text' | 'image'> [TENCENT_HY4_PREVIEW.id]: ReadonlyArray<'text'> [THEDRUMMER_CYDONIA_24B_V4_1.id]: ReadonlyArray<'text'> [THEDRUMMER_SKYFALL_36B_V2.id]: ReadonlyArray<'text'> [THEDRUMMER_UNSLOPNEMO_12B.id]: ReadonlyArray<'text'> [THINKINGMACHINES_INKLING.id]: ReadonlyArray<'text' | 'image' | 'audio'> [THINKINGMACHINES_INKLING_SMALL.id]: ReadonlyArray<'text' | 'image' | 'audio'> - [THINKINGMACHINES_INKLING_SMALL_FREE.id]: ReadonlyArray< - 'text' | 'image' | 'audio' - > - [THINKINGMACHINES_INKLING_FREE.id]: ReadonlyArray<'text' | 'image' | 'audio'> [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'> [UPSTAGE_SOLAR_PRO4.id]: ReadonlyArray<'text'> [WRITER_PALMYRA_X5.id]: ReadonlyArray<'text'> [X_AI_GROK_4_20.id]: ReadonlyArray<'text' | 'image' | 'document'> @@ -20954,7 +20311,9 @@ export type OpenRouterModelInputModalitiesByName = { [X_AI_GROK_4_3_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_4_5.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_4_6.id]: ReadonlyArray<'text' | 'image' | 'document'> + [X_AI_GROK_4_6_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_4_7.id]: ReadonlyArray<'text' | 'image' | 'document'> + [X_AI_GROK_4_7_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_BUILD_0_1.id]: ReadonlyArray<'text' | 'image' | 'document'> [XIAOMI_MIMO_V2_5.id]: ReadonlyArray<'text' | 'audio' | 'image' | 'video'> [XIAOMI_MIMO_V2_5_PRO.id]: ReadonlyArray<'text'> @@ -20981,6 +20340,7 @@ export type OpenRouterModelInputModalitiesByName = { [Z_AI_GLM_5_3_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> [Z_AI_GLM_5_3_FLASH_BATCH.id]: ReadonlyArray<'text' | 'image' | 'video'> [Z_AI_GLM_5_3_FLASHX.id]: ReadonlyArray<'text' | 'image' | 'video'> + [Z_AI_GLM_5_3_FLASHX_LEGAL.id]: ReadonlyArray<'text' | 'image' | 'video'> [Z_AI_GLM_5_3_PRIME.id]: ReadonlyArray<'text'> [Z_AI_GLM_5_3_BATCH.id]: ReadonlyArray<'text'> [Z_AI_GLM_5V_TURBO.id]: ReadonlyArray<'image' | 'text' | 'video'> @@ -21051,7 +20411,6 @@ export const OPENROUTER_CHAT_MODELS = [ ANTHROPIC_CLAUDE_SONNET_5_BATCH.id, ANTHROPIC_CLAUDE_SONNET_5_5.id, ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id, - ARCEE_AI_TRINITY_LARGE_THINKING.id, BYTEDANCE_SEED_SEED_1_6.id, BYTEDANCE_SEED_SEED_1_6_FLASH.id, BYTEDANCE_SEED_SEED_2_1_TURBO.id, @@ -21124,7 +20483,6 @@ export const OPENROUTER_CHAT_MODELS = [ GOOGLE_GEMMA_4_31B_IT.id, GOOGLE_GEMMA_4_31B_IT_FREE.id, GRYPHE_MYTHOMAX_L2_13B.id, - IBM_GRANITE_GRANITE_4_0_H_MICRO.id, IBM_GRANITE_GRANITE_4_2_8B.id, INCEPTION_MERCURY_2.id, INCEPTION_MERCURY_2_5.id, @@ -21134,6 +20492,7 @@ export const OPENROUTER_CHAT_MODELS = [ INCLUSIONAI_LING_3_1_FLASH.id, INFERENCE_NET_SCHEMATRON_V2_SMALL.id, INFERENCE_NET_SCHEMATRON_V2_TURBO.id, + LIQUID_LFM_2_5_2_6B.id, LIQUID_LFM_2_5_2_6B_FREE.id, LIQUID_LFM_2_5_24B_A2B.id, MANCER_WEAVER.id, @@ -21163,29 +20522,24 @@ 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, + MINIMAX_MINIMAX_M3_1_FLASH.id, MISTRALAI_CODESTRAL_2508.id, - MISTRALAI_CODESTRAL_2508_BATCH.id, MISTRALAI_DEVSTRAL_2512.id, MISTRALAI_MINISTRAL_14B_2512.id, MISTRALAI_MINISTRAL_3B_2512.id, MISTRALAI_MINISTRAL_8B_2512.id, - MISTRALAI_MINISTRAL_8B_2512_BATCH.id, MISTRALAI_MISTRAL_LARGE.id, MISTRALAI_MISTRAL_LARGE_2407.id, MISTRALAI_MISTRAL_LARGE_2512.id, - MISTRALAI_MISTRAL_LARGE_2512_BATCH.id, MISTRALAI_MISTRAL_LARGE_4_0.id, MISTRALAI_MISTRAL_MEDIUM_3.id, MISTRALAI_MISTRAL_MEDIUM_3_5.id, MISTRALAI_MISTRAL_MEDIUM_3_5_BATCH.id, MISTRALAI_MISTRAL_MEDIUM_3_1.id, - MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH.id, MISTRALAI_MISTRAL_NEMO.id, MISTRALAI_MISTRAL_SABA.id, MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501.id, MISTRALAI_MISTRAL_SMALL_2603.id, - MISTRALAI_MISTRAL_SMALL_2603_BATCH.id, MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id, MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id, MISTRALAI_MIXTRAL_8X22B_INSTRUCT.id, @@ -21200,17 +20554,15 @@ export const OPENROUTER_CHAT_MODELS = [ MOONSHOTAI_KIMI_K2_7_CODE.id, MOONSHOTAI_KIMI_K3.id, MOONSHOTAI_KIMI_K3_BATCH.id, + MOONSHOTAI_KIMI_K3_1_PRO.id, MORPH_MORPH_V3_FAST.id, MORPH_MORPH_V3_LARGE.id, NEX_AGI_NEX_N2_5_MINI.id, NEX_AGI_NEX_N2_5_PRO.id, - NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id, - NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id, NOUSRESEARCH_HERMES_4_405B.id, NVIDIA_NEMOTRON_3_NANO_30B_A3B.id, NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id, NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id, - NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id, NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id, NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id, NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY.id, @@ -21219,13 +20571,9 @@ export const OPENROUTER_CHAT_MODELS = [ 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, - OPENAI_GPT_3_5_TURBO_INSTRUCT.id, - OPENAI_GPT_3_5_TURBO_BATCH.id, OPENAI_GPT_4.id, - OPENAI_GPT_4_TURBO.id, OPENAI_GPT_4_TURBO_BATCH.id, OPENAI_GPT_4_1.id, OPENAI_GPT_4_1_MINI.id, @@ -21304,6 +20652,10 @@ export const OPENROUTER_CHAT_MODELS = [ OPENAI_GPT_6_1_SOL_PRO.id, OPENAI_GPT_6_1_SOL_PRO_BATCH.id, OPENAI_GPT_6_1_SOL_BATCH.id, + OPENAI_GPT_6_1_TERRA.id, + OPENAI_GPT_6_1_TERRA_PRO.id, + OPENAI_GPT_6_1_TERRA_PRO_BATCH.id, + OPENAI_GPT_6_1_TERRA_BATCH.id, OPENAI_GPT_AUDIO.id, OPENAI_GPT_AUDIO_MINI.id, OPENAI_GPT_CHAT_LATEST.id, @@ -21312,17 +20664,12 @@ export const OPENROUTER_CHAT_MODELS = [ OPENAI_GPT_OSS_20B.id, OPENAI_GPT_OSS_20B_BATCH.id, OPENAI_GPT_OSS_SAFEGUARD_20B.id, - OPENAI_O1.id, - OPENAI_O1_PRO.id, OPENAI_O3.id, - OPENAI_O3_MINI.id, - OPENAI_O3_MINI_HIGH.id, OPENAI_O3_MINI_BATCH.id, OPENAI_O3_PRO.id, OPENAI_O3_BATCH.id, - OPENAI_O4_MINI.id, - OPENAI_O4_MINI_HIGH.id, OPENAI_O4_MINI_BATCH.id, + PARTICLE_AI_PARTICLE_1.id, PERCEPTRON_PERCEPTRON_MK1.id, PERCEPTRON_PERCEPTRON_MK1_5.id, PERPLEXITY_SONAR.id, @@ -21330,11 +20677,8 @@ export const OPENROUTER_CHAT_MODELS = [ PERPLEXITY_SONAR_PRO.id, PERPLEXITY_SONAR_PRO_SEARCH.id, PERPLEXITY_SONAR_REASONING_PRO.id, - POOLSIDE_LAGUNA_S_2_1.id, - POOLSIDE_LAGUNA_S_2_1_FREE.id, - POOLSIDE_LAGUNA_XS_2_1.id, - POOLSIDE_LAGUNA_XS_2_1_FREE.id, PRISM_ML_TERNARY_BONSAI_2_27B.id, + PRISM_ML_TERNARY_BONSAI_2_9B.id, QWEN_QWEN_2_5_72B_INSTRUCT.id, QWEN_QWEN_2_5_7B_INSTRUCT.id, QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id, @@ -21351,7 +20695,6 @@ export const OPENROUTER_CHAT_MODELS = [ QWEN_QWEN3_CODER_FLASH.id, QWEN_QWEN3_CODER_NEXT.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_30B_A3B_INSTRUCT.id, QWEN_QWEN3_VL_30B_A3B_THINKING.id, @@ -21392,6 +20735,7 @@ export const OPENROUTER_CHAT_MODELS = [ SAO10K_L3_1_EURYALE_70B.id, SCALEDOWN_EXTRACT.id, SCALEDOWN_SUMMARIZE.id, + STEALTH_CROUTON_ALPHA.id, STEPFUN_STEP_3_5_FLASH.id, STEPFUN_STEP_3_7_FLASH.id, STEPFUN_STEP_5_PREVIEW.id, @@ -21401,19 +20745,17 @@ export const OPENROUTER_CHAT_MODELS = [ TENCENT_HY_MT2_7B.id, TENCENT_HY3.id, TENCENT_HY3_PREVIEW.id, + TENCENT_HY4.id, TENCENT_HY4_PREVIEW.id, THEDRUMMER_CYDONIA_24B_V4_1.id, THEDRUMMER_SKYFALL_36B_V2.id, THEDRUMMER_UNSLOPNEMO_12B.id, THINKINGMACHINES_INKLING.id, THINKINGMACHINES_INKLING_SMALL.id, - THINKINGMACHINES_INKLING_SMALL_FREE.id, - THINKINGMACHINES_INKLING_FREE.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, UPSTAGE_SOLAR_PRO4.id, WRITER_PALMYRA_X5.id, X_AI_GROK_4_20.id, @@ -21422,7 +20764,9 @@ export const OPENROUTER_CHAT_MODELS = [ X_AI_GROK_4_3_BATCH.id, X_AI_GROK_4_5.id, X_AI_GROK_4_6.id, + X_AI_GROK_4_6_BATCH.id, X_AI_GROK_4_7.id, + X_AI_GROK_4_7_BATCH.id, X_AI_GROK_BUILD_0_1.id, XIAOMI_MIMO_V2_5.id, XIAOMI_MIMO_V2_5_PRO.id, @@ -21445,6 +20789,7 @@ export const OPENROUTER_CHAT_MODELS = [ Z_AI_GLM_5_3_FLASH.id, Z_AI_GLM_5_3_FLASH_BATCH.id, Z_AI_GLM_5_3_FLASHX.id, + Z_AI_GLM_5_3_FLASHX_LEGAL.id, Z_AI_GLM_5_3_PRIME.id, Z_AI_GLM_5_3_BATCH.id, Z_AI_GLM_5V_TURBO.id, @@ -21544,8 +20889,6 @@ 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, - [ARCEE_AI_TRINITY_LARGE_THINKING.id]: - ARCEE_AI_TRINITY_LARGE_THINKING.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, @@ -21657,8 +21000,6 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [GOOGLE_GEMMA_4_31B_IT.id]: GOOGLE_GEMMA_4_31B_IT.supports.input, [GOOGLE_GEMMA_4_31B_IT_FREE.id]: GOOGLE_GEMMA_4_31B_IT_FREE.supports.input, [GRYPHE_MYTHOMAX_L2_13B.id]: GRYPHE_MYTHOMAX_L2_13B.supports.input, - [IBM_GRANITE_GRANITE_4_0_H_MICRO.id]: - IBM_GRANITE_GRANITE_4_0_H_MICRO.supports.input, [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, @@ -21671,6 +21012,7 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< INFERENCE_NET_SCHEMATRON_V2_SMALL.supports.input, [INFERENCE_NET_SCHEMATRON_V2_TURBO.id]: INFERENCE_NET_SCHEMATRON_V2_TURBO.supports.input, + [LIQUID_LFM_2_5_2_6B.id]: LIQUID_LFM_2_5_2_6B.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, @@ -21708,25 +21050,18 @@ 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, + [MINIMAX_MINIMAX_M3_1_FLASH.id]: MINIMAX_MINIMAX_M3_1_FLASH.supports.input, [MISTRALAI_CODESTRAL_2508.id]: MISTRALAI_CODESTRAL_2508.supports.input, - [MISTRALAI_CODESTRAL_2508_BATCH.id]: - MISTRALAI_CODESTRAL_2508_BATCH.supports.input, [MISTRALAI_DEVSTRAL_2512.id]: MISTRALAI_DEVSTRAL_2512.supports.input, [MISTRALAI_MINISTRAL_14B_2512.id]: MISTRALAI_MINISTRAL_14B_2512.supports.input, [MISTRALAI_MINISTRAL_3B_2512.id]: MISTRALAI_MINISTRAL_3B_2512.supports.input, [MISTRALAI_MINISTRAL_8B_2512.id]: MISTRALAI_MINISTRAL_8B_2512.supports.input, - [MISTRALAI_MINISTRAL_8B_2512_BATCH.id]: - MISTRALAI_MINISTRAL_8B_2512_BATCH.supports.input, [MISTRALAI_MISTRAL_LARGE.id]: MISTRALAI_MISTRAL_LARGE.supports.input, [MISTRALAI_MISTRAL_LARGE_2407.id]: MISTRALAI_MISTRAL_LARGE_2407.supports.input, [MISTRALAI_MISTRAL_LARGE_2512.id]: MISTRALAI_MISTRAL_LARGE_2512.supports.input, - [MISTRALAI_MISTRAL_LARGE_2512_BATCH.id]: - MISTRALAI_MISTRAL_LARGE_2512_BATCH.supports.input, [MISTRALAI_MISTRAL_LARGE_4_0.id]: MISTRALAI_MISTRAL_LARGE_4_0.supports.input, [MISTRALAI_MISTRAL_MEDIUM_3.id]: MISTRALAI_MISTRAL_MEDIUM_3.supports.input, [MISTRALAI_MISTRAL_MEDIUM_3_5.id]: @@ -21735,16 +21070,12 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< MISTRALAI_MISTRAL_MEDIUM_3_5_BATCH.supports.input, [MISTRALAI_MISTRAL_MEDIUM_3_1.id]: MISTRALAI_MISTRAL_MEDIUM_3_1.supports.input, - [MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH.id]: - MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH.supports.input, [MISTRALAI_MISTRAL_NEMO.id]: MISTRALAI_MISTRAL_NEMO.supports.input, [MISTRALAI_MISTRAL_SABA.id]: MISTRALAI_MISTRAL_SABA.supports.input, [MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501.id]: MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501.supports.input, [MISTRALAI_MISTRAL_SMALL_2603.id]: MISTRALAI_MISTRAL_SMALL_2603.supports.input, - [MISTRALAI_MISTRAL_SMALL_2603_BATCH.id]: - MISTRALAI_MISTRAL_SMALL_2603_BATCH.supports.input, [MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id]: MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.supports.input, [MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id]: @@ -21765,14 +21096,11 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [MOONSHOTAI_KIMI_K2_7_CODE.id]: MOONSHOTAI_KIMI_K2_7_CODE.supports.input, [MOONSHOTAI_KIMI_K3.id]: MOONSHOTAI_KIMI_K3.supports.input, [MOONSHOTAI_KIMI_K3_BATCH.id]: MOONSHOTAI_KIMI_K3_BATCH.supports.input, + [MOONSHOTAI_KIMI_K3_1_PRO.id]: MOONSHOTAI_KIMI_K3_1_PRO.supports.input, [MORPH_MORPH_V3_FAST.id]: MORPH_MORPH_V3_FAST.supports.input, [MORPH_MORPH_V3_LARGE.id]: MORPH_MORPH_V3_LARGE.supports.input, [NEX_AGI_NEX_N2_5_MINI.id]: NEX_AGI_NEX_N2_5_MINI.supports.input, [NEX_AGI_NEX_N2_5_PRO.id]: NEX_AGI_NEX_N2_5_PRO.supports.input, - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id]: - NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.supports.input, - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id]: - NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.supports.input, [NOUSRESEARCH_HERMES_4_405B.id]: NOUSRESEARCH_HERMES_4_405B.supports.input, [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: NVIDIA_NEMOTRON_3_NANO_30B_A3B.supports.input, @@ -21780,8 +21108,6 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.supports.input, [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: NVIDIA_NEMOTRON_3_SUPER_120B_A12B.supports.input, - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: - NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.supports.input, [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.supports.input, [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: @@ -21798,14 +21124,9 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< 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, - [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: - OPENAI_GPT_3_5_TURBO_INSTRUCT.supports.input, - [OPENAI_GPT_3_5_TURBO_BATCH.id]: OPENAI_GPT_3_5_TURBO_BATCH.supports.input, [OPENAI_GPT_4.id]: OPENAI_GPT_4.supports.input, - [OPENAI_GPT_4_TURBO.id]: OPENAI_GPT_4_TURBO.supports.input, [OPENAI_GPT_4_TURBO_BATCH.id]: OPENAI_GPT_4_TURBO_BATCH.supports.input, [OPENAI_GPT_4_1.id]: OPENAI_GPT_4_1.supports.input, [OPENAI_GPT_4_1_MINI.id]: OPENAI_GPT_4_1_MINI.supports.input, @@ -21890,6 +21211,11 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [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_6_1_TERRA.id]: OPENAI_GPT_6_1_TERRA.supports.input, + [OPENAI_GPT_6_1_TERRA_PRO.id]: OPENAI_GPT_6_1_TERRA_PRO.supports.input, + [OPENAI_GPT_6_1_TERRA_PRO_BATCH.id]: + OPENAI_GPT_6_1_TERRA_PRO_BATCH.supports.input, + [OPENAI_GPT_6_1_TERRA_BATCH.id]: OPENAI_GPT_6_1_TERRA_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, @@ -21899,17 +21225,12 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [OPENAI_GPT_OSS_20B_BATCH.id]: OPENAI_GPT_OSS_20B_BATCH.supports.input, [OPENAI_GPT_OSS_SAFEGUARD_20B.id]: OPENAI_GPT_OSS_SAFEGUARD_20B.supports.input, - [OPENAI_O1.id]: OPENAI_O1.supports.input, - [OPENAI_O1_PRO.id]: OPENAI_O1_PRO.supports.input, [OPENAI_O3.id]: OPENAI_O3.supports.input, - [OPENAI_O3_MINI.id]: OPENAI_O3_MINI.supports.input, - [OPENAI_O3_MINI_HIGH.id]: OPENAI_O3_MINI_HIGH.supports.input, [OPENAI_O3_MINI_BATCH.id]: OPENAI_O3_MINI_BATCH.supports.input, [OPENAI_O3_PRO.id]: OPENAI_O3_PRO.supports.input, [OPENAI_O3_BATCH.id]: OPENAI_O3_BATCH.supports.input, - [OPENAI_O4_MINI.id]: OPENAI_O4_MINI.supports.input, - [OPENAI_O4_MINI_HIGH.id]: OPENAI_O4_MINI_HIGH.supports.input, [OPENAI_O4_MINI_BATCH.id]: OPENAI_O4_MINI_BATCH.supports.input, + [PARTICLE_AI_PARTICLE_1.id]: PARTICLE_AI_PARTICLE_1.supports.input, [PERCEPTRON_PERCEPTRON_MK1.id]: PERCEPTRON_PERCEPTRON_MK1.supports.input, [PERCEPTRON_PERCEPTRON_MK1_5.id]: PERCEPTRON_PERCEPTRON_MK1_5.supports.input, [PERPLEXITY_SONAR.id]: PERPLEXITY_SONAR.supports.input, @@ -21919,12 +21240,10 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [PERPLEXITY_SONAR_PRO_SEARCH.id]: PERPLEXITY_SONAR_PRO_SEARCH.supports.input, [PERPLEXITY_SONAR_REASONING_PRO.id]: PERPLEXITY_SONAR_REASONING_PRO.supports.input, - [POOLSIDE_LAGUNA_S_2_1.id]: POOLSIDE_LAGUNA_S_2_1.supports.input, - [POOLSIDE_LAGUNA_S_2_1_FREE.id]: POOLSIDE_LAGUNA_S_2_1_FREE.supports.input, - [POOLSIDE_LAGUNA_XS_2_1.id]: POOLSIDE_LAGUNA_XS_2_1.supports.input, - [POOLSIDE_LAGUNA_XS_2_1_FREE.id]: POOLSIDE_LAGUNA_XS_2_1_FREE.supports.input, [PRISM_ML_TERNARY_BONSAI_2_27B.id]: PRISM_ML_TERNARY_BONSAI_2_27B.supports.input, + [PRISM_ML_TERNARY_BONSAI_2_9B.id]: + PRISM_ML_TERNARY_BONSAI_2_9B.supports.input, [QWEN_QWEN_2_5_72B_INSTRUCT.id]: QWEN_QWEN_2_5_72B_INSTRUCT.supports.input, [QWEN_QWEN_2_5_7B_INSTRUCT.id]: QWEN_QWEN_2_5_7B_INSTRUCT.supports.input, [QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id]: @@ -21947,8 +21266,6 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [QWEN_QWEN3_CODER_NEXT.id]: QWEN_QWEN3_CODER_NEXT.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_30B_A3B_INSTRUCT.id]: @@ -21993,6 +21310,7 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [SAO10K_L3_1_EURYALE_70B.id]: SAO10K_L3_1_EURYALE_70B.supports.input, [SCALEDOWN_EXTRACT.id]: SCALEDOWN_EXTRACT.supports.input, [SCALEDOWN_SUMMARIZE.id]: SCALEDOWN_SUMMARIZE.supports.input, + [STEALTH_CROUTON_ALPHA.id]: STEALTH_CROUTON_ALPHA.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, @@ -22003,6 +21321,7 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [TENCENT_HY_MT2_7B.id]: TENCENT_HY_MT2_7B.supports.input, [TENCENT_HY3.id]: TENCENT_HY3.supports.input, [TENCENT_HY3_PREVIEW.id]: TENCENT_HY3_PREVIEW.supports.input, + [TENCENT_HY4.id]: TENCENT_HY4.supports.input, [TENCENT_HY4_PREVIEW.id]: TENCENT_HY4_PREVIEW.supports.input, [THEDRUMMER_CYDONIA_24B_V4_1.id]: THEDRUMMER_CYDONIA_24B_V4_1.supports.input, [THEDRUMMER_SKYFALL_36B_V2.id]: THEDRUMMER_SKYFALL_36B_V2.supports.input, @@ -22010,15 +21329,10 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [THINKINGMACHINES_INKLING.id]: THINKINGMACHINES_INKLING.supports.input, [THINKINGMACHINES_INKLING_SMALL.id]: THINKINGMACHINES_INKLING_SMALL.supports.input, - [THINKINGMACHINES_INKLING_SMALL_FREE.id]: - THINKINGMACHINES_INKLING_SMALL_FREE.supports.input, - [THINKINGMACHINES_INKLING_FREE.id]: - THINKINGMACHINES_INKLING_FREE.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, [UPSTAGE_SOLAR_PRO4.id]: UPSTAGE_SOLAR_PRO4.supports.input, [WRITER_PALMYRA_X5.id]: WRITER_PALMYRA_X5.supports.input, [X_AI_GROK_4_20.id]: X_AI_GROK_4_20.supports.input, @@ -22027,7 +21341,9 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [X_AI_GROK_4_3_BATCH.id]: X_AI_GROK_4_3_BATCH.supports.input, [X_AI_GROK_4_5.id]: X_AI_GROK_4_5.supports.input, [X_AI_GROK_4_6.id]: X_AI_GROK_4_6.supports.input, + [X_AI_GROK_4_6_BATCH.id]: X_AI_GROK_4_6_BATCH.supports.input, [X_AI_GROK_4_7.id]: X_AI_GROK_4_7.supports.input, + [X_AI_GROK_4_7_BATCH.id]: X_AI_GROK_4_7_BATCH.supports.input, [X_AI_GROK_BUILD_0_1.id]: X_AI_GROK_BUILD_0_1.supports.input, [XIAOMI_MIMO_V2_5.id]: XIAOMI_MIMO_V2_5.supports.input, [XIAOMI_MIMO_V2_5_PRO.id]: XIAOMI_MIMO_V2_5_PRO.supports.input, @@ -22052,6 +21368,7 @@ export const OPENROUTER_MODEL_INPUT_MODALITIES: Readonly< [Z_AI_GLM_5_3_FLASH.id]: Z_AI_GLM_5_3_FLASH.supports.input, [Z_AI_GLM_5_3_FLASH_BATCH.id]: Z_AI_GLM_5_3_FLASH_BATCH.supports.input, [Z_AI_GLM_5_3_FLASHX.id]: Z_AI_GLM_5_3_FLASHX.supports.input, + [Z_AI_GLM_5_3_FLASHX_LEGAL.id]: Z_AI_GLM_5_3_FLASHX_LEGAL.supports.input, [Z_AI_GLM_5_3_PRIME.id]: Z_AI_GLM_5_3_PRIME.supports.input, [Z_AI_GLM_5_3_BATCH.id]: Z_AI_GLM_5_3_BATCH.supports.input, [Z_AI_GLM_5V_TURBO.id]: Z_AI_GLM_5V_TURBO.supports.input, @@ -22136,8 +21453,6 @@ const OPENROUTER_REASONING = { [ANTHROPIC_CLAUDE_SONNET_5_5.id]: ANTHROPIC_CLAUDE_SONNET_5_5.reasoning, [ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.id]: ANTHROPIC_CLAUDE_SONNET_5_5_BATCH.reasoning, - [ARCEE_AI_TRINITY_LARGE_THINKING.id]: - ARCEE_AI_TRINITY_LARGE_THINKING.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, @@ -22230,8 +21545,6 @@ const OPENROUTER_REASONING = { [MISTRALAI_MISTRAL_MEDIUM_3_5_BATCH.id]: MISTRALAI_MISTRAL_MEDIUM_3_5_BATCH.reasoning, [MISTRALAI_MISTRAL_SMALL_2603.id]: MISTRALAI_MISTRAL_SMALL_2603.reasoning, - [MISTRALAI_MISTRAL_SMALL_2603_BATCH.id]: - MISTRALAI_MISTRAL_SMALL_2603_BATCH.reasoning, [MOONSHOTAI_KIMI_K2_THINKING.id]: MOONSHOTAI_KIMI_K2_THINKING.reasoning, [MOONSHOTAI_KIMI_K2_5.id]: MOONSHOTAI_KIMI_K2_5.reasoning, [MOONSHOTAI_KIMI_K2_6.id]: MOONSHOTAI_KIMI_K2_6.reasoning, @@ -22246,8 +21559,6 @@ const OPENROUTER_REASONING = { NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.reasoning, [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: NVIDIA_NEMOTRON_3_SUPER_120B_A12B.reasoning, - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: - NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.reasoning, [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.reasoning, [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: @@ -22324,34 +21635,22 @@ const OPENROUTER_REASONING = { [OPENAI_GPT_OSS_20B.id]: OPENAI_GPT_OSS_20B.reasoning, [OPENAI_GPT_OSS_20B_BATCH.id]: OPENAI_GPT_OSS_20B_BATCH.reasoning, [OPENAI_GPT_OSS_SAFEGUARD_20B.id]: OPENAI_GPT_OSS_SAFEGUARD_20B.reasoning, - [OPENAI_O1.id]: OPENAI_O1.reasoning, - [OPENAI_O1_PRO.id]: OPENAI_O1_PRO.reasoning, [OPENAI_O3.id]: OPENAI_O3.reasoning, - [OPENAI_O3_MINI.id]: OPENAI_O3_MINI.reasoning, - [OPENAI_O3_MINI_HIGH.id]: OPENAI_O3_MINI_HIGH.reasoning, [OPENAI_O3_MINI_BATCH.id]: OPENAI_O3_MINI_BATCH.reasoning, [OPENAI_O3_PRO.id]: OPENAI_O3_PRO.reasoning, [OPENAI_O3_BATCH.id]: OPENAI_O3_BATCH.reasoning, - [OPENAI_O4_MINI.id]: OPENAI_O4_MINI.reasoning, - [OPENAI_O4_MINI_HIGH.id]: OPENAI_O4_MINI_HIGH.reasoning, [OPENAI_O4_MINI_BATCH.id]: OPENAI_O4_MINI_BATCH.reasoning, [PERCEPTRON_PERCEPTRON_MK1.id]: PERCEPTRON_PERCEPTRON_MK1.reasoning, [PERCEPTRON_PERCEPTRON_MK1_5.id]: PERCEPTRON_PERCEPTRON_MK1_5.reasoning, [PERPLEXITY_SONAR_DEEP_RESEARCH.id]: PERPLEXITY_SONAR_DEEP_RESEARCH.reasoning, [PERPLEXITY_SONAR_PRO_SEARCH.id]: PERPLEXITY_SONAR_PRO_SEARCH.reasoning, [PERPLEXITY_SONAR_REASONING_PRO.id]: PERPLEXITY_SONAR_REASONING_PRO.reasoning, - [POOLSIDE_LAGUNA_S_2_1.id]: POOLSIDE_LAGUNA_S_2_1.reasoning, - [POOLSIDE_LAGUNA_S_2_1_FREE.id]: POOLSIDE_LAGUNA_S_2_1_FREE.reasoning, - [POOLSIDE_LAGUNA_XS_2_1.id]: POOLSIDE_LAGUNA_XS_2_1.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_THINKING_2507.id]: QWEN_QWEN3_235B_A22B_THINKING_2507.reasoning, [QWEN_QWEN3_30B_A3B.id]: QWEN_QWEN3_30B_A3B.reasoning, [QWEN_QWEN3_32B.id]: QWEN_QWEN3_32B.reasoning, - [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: - QWEN_QWEN3_NEXT_80B_A3B_THINKING.reasoning, [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: QWEN_QWEN3_VL_30B_A3B_THINKING.reasoning, [QWEN_QWEN3_5_122B_A10B.id]: QWEN_QWEN3_5_122B_A10B.reasoning, [QWEN_QWEN3_5_27B.id]: QWEN_QWEN3_5_27B.reasoning, @@ -22387,11 +21686,7 @@ const OPENROUTER_REASONING = { [TENCENT_HY4_PREVIEW.id]: TENCENT_HY4_PREVIEW.reasoning, [THINKINGMACHINES_INKLING.id]: THINKINGMACHINES_INKLING.reasoning, [THINKINGMACHINES_INKLING_SMALL.id]: THINKINGMACHINES_INKLING_SMALL.reasoning, - [THINKINGMACHINES_INKLING_SMALL_FREE.id]: - THINKINGMACHINES_INKLING_SMALL_FREE.reasoning, - [THINKINGMACHINES_INKLING_FREE.id]: THINKINGMACHINES_INKLING_FREE.reasoning, [UPSTAGE_SOLAR_MINI4.id]: UPSTAGE_SOLAR_MINI4.reasoning, - [UPSTAGE_SOLAR_PRO_3.id]: UPSTAGE_SOLAR_PRO_3.reasoning, [UPSTAGE_SOLAR_PRO4.id]: UPSTAGE_SOLAR_PRO4.reasoning, [X_AI_GROK_4_20.id]: X_AI_GROK_4_20.reasoning, [X_AI_GROK_4_20_MULTI_AGENT.id]: X_AI_GROK_4_20_MULTI_AGENT.reasoning, @@ -22480,6 +21775,7 @@ export const OPENROUTER_VIDEO_MODELS = [ 'minimax/hailuo-3-max', 'runway/aleph-2', 'runway/gen-4.5', + 'tbc/mischief-1', 'x-ai/grok-imagine-video', 'x-ai/grok-imagine-video-1.5', 'x-ai/grok-imagine-video-1.5-lite', @@ -22820,8 +22116,11 @@ export const OPENROUTER_VIDEO_MODEL_META = { }, 'heygen/heygen-video-1': { name: 'HeyGen: HeyGen Video', - durations: [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], - resolutions: ['480p', '768p', '2K'], + durations: [ + 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, + ], + resolutions: ['480p', '768p', '1080p', '2K'], aspectRatios: ['21:9', '16:9', '4:3', '1:1', '3:4', '9:16'], frameImages: ['first_frame'], sizes: null, @@ -22908,6 +22207,16 @@ export const OPENROUTER_VIDEO_MODEL_META = { generateAudio: false, seed: true, }, + 'tbc/mischief-1': { + name: 'TBC: mischief 1', + durations: [3, 5], + resolutions: ['480p', '720p'], + aspectRatios: ['16:9'], + frameImages: ['first_frame'], + sizes: ['854x480', '1280x720'], + generateAudio: false, + seed: true, + }, 'x-ai/grok-imagine-video': { name: 'SpaceXAI: Grok Imagine Video', durations: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], @@ -23082,9 +22391,9 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = INCEPTION_MERCURY_3.id, INCLUSIONAI_LING_3_0_FLASH_VL.id, INCLUSIONAI_LING_3_1_FLASH.id, + LIQUID_LFM_2_5_2_6B.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, META_LLAMA_LLAMA_4_MAVERICK.id, @@ -23097,30 +22406,25 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = 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, + MINIMAX_MINIMAX_M3_1_FLASH.id, MISTRALAI_CODESTRAL_2508.id, - MISTRALAI_CODESTRAL_2508_BATCH.id, MISTRALAI_DEVSTRAL_2512.id, MISTRALAI_MINISTRAL_14B_2512.id, MISTRALAI_MINISTRAL_3B_2512.id, MISTRALAI_MINISTRAL_8B_2512.id, - MISTRALAI_MINISTRAL_8B_2512_BATCH.id, MISTRALAI_MISTRAL_LARGE.id, MISTRALAI_MISTRAL_LARGE_2407.id, MISTRALAI_MISTRAL_LARGE_2512.id, - MISTRALAI_MISTRAL_LARGE_2512_BATCH.id, MISTRALAI_MISTRAL_LARGE_4_0.id, MISTRALAI_MISTRAL_MEDIUM_3.id, MISTRALAI_MISTRAL_MEDIUM_3_5.id, MISTRALAI_MISTRAL_MEDIUM_3_5_BATCH.id, MISTRALAI_MISTRAL_MEDIUM_3_1.id, - MISTRALAI_MISTRAL_MEDIUM_3_1_BATCH.id, MISTRALAI_MISTRAL_NEMO.id, MISTRALAI_MISTRAL_SABA.id, MISTRALAI_MISTRAL_SMALL_2603.id, - MISTRALAI_MISTRAL_SMALL_2603_BATCH.id, MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id, MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id, MISTRALAI_MIXTRAL_8X22B_INSTRUCT.id, @@ -23132,20 +22436,16 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = MOONSHOTAI_KIMI_K2_7_CODE.id, MOONSHOTAI_KIMI_K3.id, MOONSHOTAI_KIMI_K3_BATCH.id, + MOONSHOTAI_KIMI_K3_1_PRO.id, NEX_AGI_NEX_N2_5_PRO.id, NVIDIA_NEMOTRON_3_NANO_30B_A3B.id, NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id, - 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, - OPENAI_GPT_3_5_TURBO_BATCH.id, - OPENAI_GPT_4.id, - OPENAI_GPT_4_TURBO.id, OPENAI_GPT_4_TURBO_BATCH.id, OPENAI_GPT_4_1.id, OPENAI_GPT_4_1_MINI.id, @@ -23221,6 +22521,10 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = OPENAI_GPT_6_1_SOL_PRO.id, OPENAI_GPT_6_1_SOL_PRO_BATCH.id, OPENAI_GPT_6_1_SOL_BATCH.id, + OPENAI_GPT_6_1_TERRA.id, + OPENAI_GPT_6_1_TERRA_PRO.id, + OPENAI_GPT_6_1_TERRA_PRO_BATCH.id, + OPENAI_GPT_6_1_TERRA_BATCH.id, OPENAI_GPT_AUDIO.id, OPENAI_GPT_AUDIO_MINI.id, OPENAI_GPT_CHAT_LATEST.id, @@ -23229,18 +22533,15 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = OPENAI_GPT_OSS_20B.id, OPENAI_GPT_OSS_20B_BATCH.id, OPENAI_GPT_OSS_SAFEGUARD_20B.id, - OPENAI_O1.id, OPENAI_O3.id, - OPENAI_O3_MINI.id, - OPENAI_O3_MINI_HIGH.id, OPENAI_O3_MINI_BATCH.id, OPENAI_O3_PRO.id, OPENAI_O3_BATCH.id, - OPENAI_O4_MINI.id, - OPENAI_O4_MINI_HIGH.id, OPENAI_O4_MINI_BATCH.id, + PARTICLE_AI_PARTICLE_1.id, PERCEPTRON_PERCEPTRON_MK1_5.id, PRISM_ML_TERNARY_BONSAI_2_27B.id, + PRISM_ML_TERNARY_BONSAI_2_9B.id, QWEN_QWEN_2_5_72B_INSTRUCT.id, QWEN_QWEN_2_5_7B_INSTRUCT.id, QWEN_QWEN_PLUS.id, @@ -23253,7 +22554,6 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = QWEN_QWEN3_CODER_30B_A3B_INSTRUCT.id, QWEN_QWEN3_CODER_NEXT.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_30B_A3B_INSTRUCT.id, QWEN_QWEN3_VL_30B_A3B_THINKING.id, @@ -23285,19 +22585,22 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = SAKANA_FUGU_ULTRA.id, SAKANA_FUGU_ULTRA_V2.id, SAKANA_SAKANA_NAMAZU.id, + STEALTH_CROUTON_ALPHA.id, STEPFUN_STEP_3_7_FLASH.id, STEPFUN_STEP_5_PREVIEW.id, TENCENT_HY3.id, + TENCENT_HY4.id, TENCENT_HY4_PREVIEW.id, UPSTAGE_SOLAR_MINI4.id, - UPSTAGE_SOLAR_PRO_3.id, UPSTAGE_SOLAR_PRO4.id, X_AI_GROK_4_20.id, X_AI_GROK_4_3.id, X_AI_GROK_4_3_BATCH.id, X_AI_GROK_4_5.id, X_AI_GROK_4_6.id, + X_AI_GROK_4_6_BATCH.id, X_AI_GROK_4_7.id, + X_AI_GROK_4_7_BATCH.id, X_AI_GROK_BUILD_0_1.id, XIAOMI_MIMO_V2_5.id, XIAOMI_MIMO_V2_5_PRO.id, @@ -23314,6 +22617,7 @@ export const OPENROUTER_COMBINED_TOOLS_AND_SCHEMA_MODELS: ReadonlySet = Z_AI_GLM_5_3.id, Z_AI_GLM_5_3_FLASH.id, Z_AI_GLM_5_3_FLASH_BATCH.id, + Z_AI_GLM_5_3_FLASHX_LEGAL.id, Z_AI_GLM_5_3_BATCH.id, ]) @@ -23333,12 +22637,11 @@ export const OPENROUTER_JSON_OBJECT_ONLY_MODELS: ReadonlySet = 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, MINIMAX_MINIMAX_M2_1.id, MINIMAX_MINIMAX_M2_7.id, - MINIMAX_MINIMAX_M3_1_FLASH_FREE.id, + OPENAI_GPT_4.id, QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id, QWEN_QWEN3_CODER_FLASH.id, QWEN_QWEN3_7_FLASH.id, diff --git a/packages/ai-vercel-gateway/src/model-meta.ts b/packages/ai-vercel-gateway/src/model-meta.ts index 9882909b1c..041c534bb1 100644 --- a/packages/ai-vercel-gateway/src/model-meta.ts +++ b/packages/ai-vercel-gateway/src/model-meta.ts @@ -76,8 +76,8 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ '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/joey-1', 'baseten/mammoth-1', 'bytedance/seed-1.6', 'bytedance/seed-1.8', @@ -85,7 +85,6 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'callstack/apex', 'cohere/command-a', 'convaiinnovations/laya', - 'convaiinnovations/laya-free', 'deepseek/deepseek-r1', 'deepseek/deepseek-v3.1', 'deepseek/deepseek-v3.2', @@ -99,6 +98,20 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'deepseek/deepseek-v4.1-flash-1017', 'deepseek/deepseek-v4.1-flash-1017-fast', 'deepseek/deepseek-v4.1-flash-fast', + 'elevenlabs/eleven-flash-v2', + 'elevenlabs/eleven-flash-v2.5', + 'elevenlabs/eleven-multilingual-v2', + 'elevenlabs/eleven-realtime-v1-max', + 'elevenlabs/eleven-realtime-v1-mini', + 'elevenlabs/eleven-v3', + 'elevenlabs/eleven-v3-conversational', + 'elevenlabs/eleven-v4', + 'elevenlabs/eleven-v4-turbo', + 'elevenlabs/music-v2', + 'elevenlabs/music-v2.5', + 'elevenlabs/scribe-v2', + 'elevenlabs/scribe-v2-realtime', + 'elevenlabs/sound-effects-v2', 'elorian/glimpse', 'fireworks/ember-1', 'fish-audio/drama-3', @@ -152,13 +165,14 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'inclusionai/ling-3.0-flash-sante', 'inclusionai/ling-3.0-flash-vl', 'inclusionai/ling-3.1-flash', + 'inclusionai/ling-3.1-flash-1019', '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', + 'meituan/longcat-2.5', 'meta/llama-3.1-70b', 'meta/llama-3.1-8b', 'meta/llama-3.3-70b', @@ -208,6 +222,8 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'moonshotai/kimi-k2.7-code-highspeed', 'moonshotai/kimi-k3', 'moonshotai/kimi-k3-fast', + 'moonshotai/kimi-k3.1-pro', + 'moonshotai/kimi-k3.1-pro-highspeed', 'morph/morph-v3-fast', 'morph/morph-v3-large', 'nvidia/nemotron-3-nano-30b-a3b', @@ -218,8 +234,6 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ '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', @@ -227,8 +241,6 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ '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', @@ -296,7 +308,10 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'openai/gpt-6.1-sol', 'openai/gpt-6.1-sol-batch', 'openai/gpt-6.1-sol-fast', + 'openai/gpt-6.1-terra', + 'openai/gpt-6.1-terra-fast', 'openai/gpt-live-1', + 'openai/gpt-live-transcribe', 'openai/gpt-oss-120b', 'openai/gpt-oss-20b', 'openai/gpt-oss-safeguard-120b', @@ -306,21 +321,21 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'openai/gpt-realtime-2.1', 'openai/gpt-realtime-mini', 'openai/gpt-realtime-whisper', + 'openai/gpt-transcribe', 'openai/o1', 'openai/o3', 'openai/o3-fast', 'openai/o3-mini', 'openai/o3-pro', 'openai/o4-mini', - 'openai/o4-mini-fast', 'openai/tts-1', 'openai/tts-1-hd', 'openai/whisper-1', + 'particle/particle-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', @@ -332,8 +347,6 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ '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', @@ -360,14 +373,13 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'tencent/hy-mt2-plus', 'tencent/hy-mt2-pro', 'tencent/hy3', + 'tencent/hy4', 'tencent/hy4-preview', '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', 'xiaomi/mimo-v2.6-pro', 'xiaomi/mimo-v2.6-pro-ultraspeed', @@ -387,6 +399,7 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'zai/glm-5.3-fast', 'zai/glm-5.3-flash', 'zai/glm-5.3-flashx', + 'zai/glm-5.3-flashx-legal', 'zai/glm-5v-turbo', ] as const @@ -396,7 +409,6 @@ export const VERCEL_GATEWAY_PROVIDERS = [ 'alibaba', 'amazon', 'anthropic', - 'arcee-ai', 'baseten', 'bfl', 'bytedance', @@ -404,6 +416,7 @@ export const VERCEL_GATEWAY_PROVIDERS = [ 'cohere', 'convaiinnovations', 'deepseek', + 'elevenlabs', 'elorian', 'fireworks', 'fish-audio', @@ -425,6 +438,7 @@ export const VERCEL_GATEWAY_PROVIDERS = [ 'morph', 'nvidia', 'openai', + 'particle', 'perplexity', 'poolside', 'prodia', @@ -455,8 +469,10 @@ export const VERCEL_GATEWAY_MODEL_TAGS = [ 'free', 'image-generation', 'implicit-caching', + 'music', 'open-weights', 'reasoning', + 'sound-effects', 'structured-output', 'tool-use', 'video-generation', @@ -464,6 +480,7 @@ export const VERCEL_GATEWAY_MODEL_TAGS = [ 'vision', 'web-search', 'websocket-realtime', + 'websocket-speech', 'websocket-transcription', ] as const @@ -523,7 +540,6 @@ export const VERCEL_GATEWAY_IMAGE_MODELS = [ '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', 'openai/gpt-image-2', @@ -1104,17 +1120,8 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'arcee-ai/trinity-large-thinking': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > 'baseten/elephant-1': VercelGatewayCommonOptions + 'baseten/joey-1': VercelGatewayCommonOptions 'baseten/mammoth-1': VercelGatewayCommonOptions 'bytedance/seed-1.6': VercelGatewayCommonOptions & Pick< @@ -1147,7 +1154,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'structured_outputs' > 'convaiinnovations/laya': VercelGatewayCommonOptions - 'convaiinnovations/laya-free': VercelGatewayCommonOptions 'deepseek/deepseek-r1': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1263,6 +1269,28 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'elevenlabs/eleven-flash-v2': VercelGatewayCommonOptions + 'elevenlabs/eleven-flash-v2.5': VercelGatewayCommonOptions + 'elevenlabs/eleven-multilingual-v2': VercelGatewayCommonOptions + 'elevenlabs/eleven-realtime-v1-max': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'elevenlabs/eleven-realtime-v1-mini': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > + 'elevenlabs/eleven-v3': VercelGatewayCommonOptions + 'elevenlabs/eleven-v3-conversational': VercelGatewayCommonOptions + 'elevenlabs/eleven-v4': VercelGatewayCommonOptions + 'elevenlabs/eleven-v4-turbo': VercelGatewayCommonOptions + 'elevenlabs/music-v2': VercelGatewayCommonOptions + 'elevenlabs/music-v2.5': VercelGatewayCommonOptions + 'elevenlabs/scribe-v2': VercelGatewayCommonOptions + 'elevenlabs/scribe-v2-realtime': VercelGatewayCommonOptions + 'elevenlabs/sound-effects-v2': VercelGatewayCommonOptions 'elorian/glimpse': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1662,6 +1690,11 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > + 'inclusionai/ling-3.1-flash-1019': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > 'inference-net/schematron-v2-small': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1704,7 +1737,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'meituan/longcat-2.5-preview': VercelGatewayCommonOptions & + 'meituan/longcat-2.5': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -2087,6 +2120,26 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'moonshotai/kimi-k3.1-pro': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'moonshotai/kimi-k3.1-pro-highspeed': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'morph/morph-v3-fast': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2170,16 +2223,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { 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, @@ -2250,26 +2293,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { | '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, @@ -2887,11 +2910,32 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'openai/gpt-6.1-terra': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > + 'openai/gpt-6.1-terra-fast': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'openai/gpt-live-1': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > + 'openai/gpt-live-transcribe': VercelGatewayCommonOptions 'openai/gpt-oss-120b': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2953,6 +2997,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > 'openai/gpt-realtime-whisper': VercelGatewayCommonOptions + 'openai/gpt-transcribe': VercelGatewayCommonOptions 'openai/o1': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -3008,18 +3053,14 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'openai/o4-mini-fast': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'stop' - | 'response_format' - | 'structured_outputs' - > 'openai/tts-1': VercelGatewayCommonOptions 'openai/tts-1-hd': VercelGatewayCommonOptions 'openai/whisper-1': VercelGatewayCommonOptions + 'particle/particle-1': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' + > 'perplexity/pplx-decider-flash-v1.2': VercelGatewayCommonOptions 'perplexity/pplx-decider-v1.2': VercelGatewayCommonOptions 'perplexity/sonar': VercelGatewayCommonOptions & @@ -3037,11 +3078,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'poolside/laguna-s-2.1-free': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > 'quiverai/arrow-2': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -3128,26 +3164,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'spacexai/grok-4.1-fast-non-reasoning': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > - 'spacexai/grok-4.1-fast-reasoning': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' - > 'spacexai/grok-4.20-multi-agent': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -3370,12 +3386,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'tencent/hy4-preview': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' - > - 'thinkingmachines/inkling': VercelGatewayCommonOptions & + 'tencent/hy4': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -3385,20 +3396,12 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'thinkingmachines/inkling-small': VercelGatewayCommonOptions & + 'tencent/hy4-preview': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'response_format' - | 'structured_outputs' + 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' > - 'typesafe-ai/jev': VercelGatewayCommonOptions - 'typesafe-ai/jev-1.13.0': VercelGatewayCommonOptions - 'typesafe-ai/jev-1.14.0': VercelGatewayCommonOptions - 'xiaomi/mimo-v2.5': VercelGatewayCommonOptions & + 'thinkingmachines/inkling': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -3408,7 +3411,7 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > - 'xiaomi/mimo-v2.5-pro': VercelGatewayCommonOptions & + 'thinkingmachines/inkling-small': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, | 'max_tokens' @@ -3418,6 +3421,9 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'typesafe-ai/jev': VercelGatewayCommonOptions + 'typesafe-ai/jev-1.13.0': VercelGatewayCommonOptions + 'typesafe-ai/jev-1.14.0': VercelGatewayCommonOptions 'xiaomi/mimo-v2.6-flash': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -3598,6 +3604,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'response_format' | 'structured_outputs' > + 'zai/glm-5.3-flashx-legal': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'response_format' + | 'structured_outputs' + > 'zai/glm-5v-turbo': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -3671,8 +3687,8 @@ export type VercelGatewayModelInputModalitiesByName = { '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/joey-1': readonly ['text'] 'baseten/mammoth-1': readonly ['text'] 'bytedance/seed-1.6': readonly ['text', 'image'] 'bytedance/seed-1.8': readonly ['text', 'image'] @@ -3680,7 +3696,6 @@ export type VercelGatewayModelInputModalitiesByName = { '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-v3.2': readonly ['text'] @@ -3694,6 +3709,20 @@ export type VercelGatewayModelInputModalitiesByName = { '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'] + 'elevenlabs/eleven-flash-v2': readonly ['text'] + 'elevenlabs/eleven-flash-v2.5': readonly ['text'] + 'elevenlabs/eleven-multilingual-v2': readonly ['text'] + 'elevenlabs/eleven-realtime-v1-max': readonly ['text', 'audio'] + 'elevenlabs/eleven-realtime-v1-mini': readonly ['text', 'audio'] + 'elevenlabs/eleven-v3': readonly ['text'] + 'elevenlabs/eleven-v3-conversational': readonly ['text'] + 'elevenlabs/eleven-v4': readonly ['text'] + 'elevenlabs/eleven-v4-turbo': readonly ['text'] + 'elevenlabs/music-v2': readonly ['text'] + 'elevenlabs/music-v2.5': readonly ['text'] + 'elevenlabs/scribe-v2': readonly ['text', 'audio'] + 'elevenlabs/scribe-v2-realtime': readonly ['text', 'audio'] + 'elevenlabs/sound-effects-v2': readonly ['text'] 'elorian/glimpse': readonly ['text', 'image', 'video'] 'fireworks/ember-1': readonly ['text', 'image'] 'fish-audio/drama-3': readonly ['text'] @@ -3777,13 +3806,14 @@ export type VercelGatewayModelInputModalitiesByName = { '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-1019': 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', 'image'] 'liquid/d1-ultra': readonly ['text', 'image'] 'liquid/lfm2.5-24b-a2b': readonly ['text'] - 'meituan/longcat-2.5-preview': readonly ['text', 'image'] + 'meituan/longcat-2.5': readonly ['text', 'image'] 'meta/llama-3.1-70b': readonly ['text'] 'meta/llama-3.1-8b': readonly ['text'] 'meta/llama-3.3-70b': readonly ['text'] @@ -3838,6 +3868,8 @@ export type VercelGatewayModelInputModalitiesByName = { ] 'moonshotai/kimi-k3': readonly ['text', 'image', 'document', 'video'] 'moonshotai/kimi-k3-fast': readonly ['text', 'image', 'document'] + 'moonshotai/kimi-k3.1-pro': readonly ['text', 'image'] + 'moonshotai/kimi-k3.1-pro-highspeed': readonly ['text', 'image'] 'morph/morph-v3-fast': readonly ['text'] 'morph/morph-v3-large': readonly ['text'] 'nvidia/nemotron-3-nano-30b-a3b': readonly ['text'] @@ -3848,8 +3880,6 @@ export type VercelGatewayModelInputModalitiesByName = { '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'] @@ -3857,8 +3887,6 @@ export type VercelGatewayModelInputModalitiesByName = { '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'] @@ -3926,7 +3954,10 @@ export type VercelGatewayModelInputModalitiesByName = { '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-6.1-terra': readonly ['text', 'image', 'document'] + 'openai/gpt-6.1-terra-fast': readonly ['text', 'image', 'document'] 'openai/gpt-live-1': readonly ['text', 'audio'] + 'openai/gpt-live-transcribe': readonly ['text', 'audio'] 'openai/gpt-oss-120b': readonly ['text'] 'openai/gpt-oss-20b': readonly ['text'] 'openai/gpt-oss-safeguard-120b': readonly ['text'] @@ -3936,21 +3967,21 @@ export type VercelGatewayModelInputModalitiesByName = { 'openai/gpt-realtime-2.1': readonly ['text', 'audio'] 'openai/gpt-realtime-mini': readonly ['text', 'audio'] 'openai/gpt-realtime-whisper': readonly ['text', 'audio'] + 'openai/gpt-transcribe': readonly ['text', 'audio'] 'openai/o1': readonly ['text', 'image', 'document'] 'openai/o3': readonly ['text', 'image', 'document'] 'openai/o3-fast': readonly ['text', 'image', 'document'] 'openai/o3-mini': readonly ['text'] 'openai/o3-pro': readonly ['text', 'image', 'document'] 'openai/o4-mini': readonly ['text', 'image', 'document'] - 'openai/o4-mini-fast': readonly ['text', 'image', 'document'] 'openai/tts-1': readonly ['text'] 'openai/tts-1-hd': readonly ['text'] 'openai/whisper-1': readonly ['text', 'audio'] + 'particle/particle-1': readonly ['text', 'image'] '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'] @@ -3962,8 +3993,6 @@ export type VercelGatewayModelInputModalitiesByName = { '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'] @@ -3998,14 +4027,13 @@ export type VercelGatewayModelInputModalitiesByName = { 'tencent/hy-mt2-plus': readonly ['text'] 'tencent/hy-mt2-pro': readonly ['text'] 'tencent/hy3': readonly ['text'] + 'tencent/hy4': readonly ['text', 'image'] 'tencent/hy4-preview': readonly ['text'] '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'] 'xiaomi/mimo-v2.6-pro': readonly ['text', 'image', 'audio', 'video'] 'xiaomi/mimo-v2.6-pro-ultraspeed': readonly [ @@ -4030,6 +4058,7 @@ export type VercelGatewayModelInputModalitiesByName = { 'zai/glm-5.3-fast': readonly ['text'] 'zai/glm-5.3-flash': readonly ['text', 'image', 'video'] 'zai/glm-5.3-flashx': readonly ['text', 'image'] + 'zai/glm-5.3-flashx-legal': readonly ['text', 'image'] 'zai/glm-5v-turbo': readonly ['text', 'image', 'document'] } @@ -4319,7 +4348,6 @@ const VERCEL_GATEWAY_REASONING = { 'anthropic/claude-sonnet-4.6': BUDGET_NONE_LOW_TO_HIGH_MAX, 'anthropic/claude-sonnet-5': BUDGET_NONE_LOW_TO_MAX, 'anthropic/claude-sonnet-5.5': EFFORT_LOW_TO_MAX, - 'arcee-ai/trinity-large-thinking': EFFORT_NONE_LOW_TO_HIGH, 'bytedance/seed-1.6': EFFORT_OFF_HIGH, 'bytedance/seed-1.8': EFFORT_NONE_MINIMAL_TO_HIGH, 'bytedance/seed-2.1-turbo': EFFORT_NONE_LOW_TO_HIGH, @@ -4358,7 +4386,6 @@ const VERCEL_GATEWAY_REASONING = { 'inclusionai/ling-3.0-flash-vl': EFFORT_OFF_HIGH, 'inclusionai/ling-3.1-flash': 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, 'meta/muse-spark-1.1': EFFORT_MINIMAL_TO_XHIGH, 'meta/muse-spark-1.2': EFFORT_MINIMAL_TO_XHIGH, @@ -4438,16 +4465,13 @@ const VERCEL_GATEWAY_REASONING = { 'openai/o3-mini': EFFORT_LOW_TO_HIGH, 'openai/o3-pro': EFFORT_LOW_TO_HIGH, 'openai/o4-mini': EFFORT_LOW_TO_HIGH, - 'openai/o4-mini-fast': EFFORT_LOW_TO_HIGH, 'poolside/laguna-s-2.1': EFFORT_OFF_HIGH, - 'poolside/laguna-s-2.1-free': EFFORT_OFF_HIGH, 'quiverai/arrow-2': EFFORT_LOW_TO_XHIGH, 'quiverai/arrow-2-telos': EFFORT_LOW_TO_XHIGH, 'sakana/fugu-max': EFFORT_HIGH_XHIGH, 'sakana/fugu-ultra': EFFORT_HIGH_XHIGH, 'sakana/fugu-ultra-v2': EFFORT_HIGH_XHIGH, 'sakana/namazu': EFFORT_NONE_LOW_TO_HIGH, - 'spacexai/grok-4.1-fast-reasoning': EFFORT_NONE_LOW_TO_HIGH, 'spacexai/grok-4.20-multi-agent': EFFORT_NONE_LOW_TO_HIGH, 'spacexai/grok-4.20-multi-agent-beta': EFFORT_NONE_LOW_TO_HIGH, 'spacexai/grok-4.20-reasoning': EFFORT_NONE_LOW_TO_HIGH, @@ -4462,8 +4486,6 @@ const VERCEL_GATEWAY_REASONING = { 'tencent/hy4-preview': EFFORT_NONE_HIGH, 'thinkingmachines/inkling': EFFORT_NONE_MINIMAL_TO_MAX, 'thinkingmachines/inkling-small': EFFORT_NONE_MINIMAL_TO_MAX, - 'xiaomi/mimo-v2.5': EFFORT_OFF_HIGH, - 'xiaomi/mimo-v2.5-pro': EFFORT_OFF_HIGH, 'xiaomi/mimo-v2.6-flash': EFFORT_NONE_MINIMAL_TO_HIGH, 'xiaomi/mimo-v2.6-pro': EFFORT_NONE_MINIMAL_TO_HIGH, 'xiaomi/mimo-v2.6-pro-ultraspeed': EFFORT_NONE_MINIMAL_TO_HIGH, diff --git a/scripts/.sync-models-last-run b/scripts/.sync-models-last-run index 0e8cd66fa9..4233b4cea9 100644 --- a/scripts/.sync-models-last-run +++ b/scripts/.sync-models-last-run @@ -1 +1 @@ -1792665861 +1793798506 diff --git a/scripts/llmgateway.models.json b/scripts/llmgateway.models.json index f02f0e0a0c..b44beb8402 100644 --- a/scripts/llmgateway.models.json +++ b/scripts/llmgateway.models.json @@ -4,7 +4,7 @@ "name": "Auto Route", "display_name": "Auto Route", "created": 1704067200, - "description": "auto provided by llmgateway", + "description": "Automatic model routing based on request characteristics.", "family": "llmgateway", "architecture": { "input_modalities": ["text", "image"], @@ -23,7 +23,15 @@ "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty" + ] } ], "pricing": { @@ -54,7 +62,7 @@ "name": "BGE-M3", "display_name": "BGE-M3", "created": 1706486400, - "description": "bge-m3 provided by deepinfra", + "description": "BAAI's multilingual embedding model supporting dense, sparse, and multi-vector retrieval across 100+ languages. 8K context, 1024-dim output.", "family": "baai", "architecture": { "input_modalities": ["text"], @@ -77,12 +85,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8192, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "quantization": "fp32" } ], "pricing": { @@ -116,7 +127,7 @@ "name": "Claude Fable 5", "display_name": "Claude Fable 5", "created": 1780963200, - "description": "claude-fable-5 provided by anthropic, azure-anthropic, aws-bedrock", + "description": "Next generation intelligence for knowledge work and coding.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -139,15 +150,18 @@ "input_cache_write": "12.5e-6", "input_cache_write_1h": "20.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 1024, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "azure-anthropic", @@ -161,15 +175,18 @@ "input_cache_write": "12.5e-6", "input_cache_write_1h": "20.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 1024, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "aws-bedrock", @@ -183,6 +200,39 @@ "input_cache_write": "12.5e-6", "input_cache_write_1h": "20.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "10.0e-6", + "completion": "50.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6", + "input_cache_write_1h": "20.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "11e-6", + "completion": "55e-6", + "image": "0", + "request": "0", + "input_cache_read": "1.1e-6", + "input_cache_write": "13.75e-6", + "input_cache_write_1h": "22e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -191,7 +241,8 @@ "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 1024, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -217,7 +268,7 @@ "name": "Claude Fable 5.1", "display_name": "Claude Fable 5.1", "created": 1788220800, - "description": "claude-fable-5-1 provided by anthropic, azure-anthropic, aws-bedrock", + "description": "Anthropic's most capable model for demanding reasoning and long-horizon agentic work, extending Claude Fable 5 with stronger agentic coding, multistep research, and document work.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -240,15 +291,18 @@ "input_cache_write": "12.5e-6", "input_cache_write_1h": "20.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "azure-anthropic", @@ -262,15 +316,18 @@ "input_cache_write": "12.5e-6", "input_cache_write_1h": "20.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "aws-bedrock", @@ -284,6 +341,39 @@ "input_cache_write": "12.5e-6", "input_cache_write_1h": "20.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "10.0e-6", + "completion": "50.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_write": "12.5e-6", + "input_cache_write_1h": "20.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "11e-6", + "completion": "55e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.275e-6", + "input_cache_write": "13.75e-6", + "input_cache_write_1h": "22e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -292,7 +382,8 @@ "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -318,7 +409,7 @@ "name": "Claude Haiku 4.5", "display_name": "Claude Haiku 4.5", "created": 1760486400, - "description": "claude-haiku-4-5 provided by anthropic, aws-bedrock, vertex-anthropic", + "description": "Fast, efficient model for high-volume, low-latency applications.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -339,15 +430,21 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "1.25e-6", - "input_cache_write_1h": "2.0e-6" + "input_cache_write_1h": "2.0e-6", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, "max_output": 64000 }, @@ -363,13 +460,94 @@ "input_cache_write": "1.25e-6", "input_cache_write_1h": "2.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "1.0e-6", + "completion": "5.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.1e-6", + "input_cache_write": "1.25e-6", + "input_cache_write_1h": "2.0e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + } + ], + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, "max_output": 64000 }, @@ -385,13 +563,17 @@ "input_cache_write": "1.25e-6", "input_cache_write_1h": "2.0e-6" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, "max_output": 64000 } @@ -404,7 +586,7 @@ "input_cache_read": "0.1e-6", "input_cache_write": "1.25e-6", "input_cache_write_1h": "2.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 200000, @@ -427,7 +609,7 @@ "name": "Claude Haiku 4.5 (2025-10-01)", "display_name": "Claude Haiku 4.5 (2025-10-01)", "created": 1760486400, - "description": "claude-haiku-4-5-20251001 provided by anthropic, aws-bedrock", + "description": "Fast, efficient model for high-volume, low-latency applications.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -448,15 +630,21 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "1.25e-6", - "input_cache_write_1h": "2.0e-6" + "input_cache_write_1h": "2.0e-6", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, "max_output": 64000 }, @@ -472,13 +660,94 @@ "input_cache_write": "1.25e-6", "input_cache_write_1h": "2.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "1.0e-6", + "completion": "5.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.1e-6", + "input_cache_write": "1.25e-6", + "input_cache_write_1h": "2.0e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "1.1e-6", + "completion": "5.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "1.375e-6", + "input_cache_write_1h": "2.2e-6" + }, + "context_length": 200000, + "max_output": 64000, + "streaming": true + } + ], + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, "max_output": 64000 } @@ -491,7 +760,7 @@ "input_cache_read": "0.1e-6", "input_cache_write": "1.25e-6", "input_cache_write_1h": "2.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 200000, @@ -514,7 +783,7 @@ "name": "Claude Haiku 5.5", "display_name": "Claude Haiku 5.5", "created": 1791331200, - "description": "claude-haiku-5-5 provided by anthropic, aws-bedrock", + "description": "Claude Haiku 5.5 is Anthropic's fastest model for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks, with adaptive thinking and vision capabilities.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -535,17 +804,43 @@ "request": "0", "input_cache_read": "0.01e-6", "input_cache_write": "0.125e-6", - "input_cache_write_1h": "0.2e-6" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, + "input_cache_write_1h": "0.2e-6", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 100K", + "up_to_tokens": 100000, + "prompt": "0.1e-6", + "completion": "0.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0.2e-6" + }, + { + "name": "Over 100K", + "up_to_tokens": null, + "prompt": "0.5e-6", + "completion": "2.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6", + "input_cache_write_1h": "1.0e-6" + } + ] + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] }, { "providerId": "aws-bedrock", @@ -557,17 +852,147 @@ "request": "0", "input_cache_read": "0.01e-6", "input_cache_write": "0.125e-6", - "input_cache_write_1h": "0.2e-6" - }, + "input_cache_write_1h": "0.2e-6", + "tiers": [ + { + "name": "Up to 100K", + "up_to_tokens": 100000, + "prompt": "0.1e-6", + "completion": "0.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0.2e-6" + }, + { + "name": "Over 100K", + "up_to_tokens": null, + "prompt": "0.5e-6", + "completion": "2.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6", + "input_cache_write_1h": "1.0e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "0.1e-6", + "completion": "0.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0.2e-6", + "tiers": [ + { + "name": "Up to 100K", + "up_to_tokens": 100000, + "prompt": "0.1e-6", + "completion": "0.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0.2e-6" + }, + { + "name": "Over 100K", + "up_to_tokens": null, + "prompt": "0.5e-6", + "completion": "2.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6", + "input_cache_write_1h": "1.0e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "0.11e-6", + "completion": "0.55e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.011e-6", + "input_cache_write": "0.1375e-6", + "input_cache_write_1h": "0.22e-6", + "tiers": [ + { + "name": "Up to 100K", + "up_to_tokens": 100000, + "prompt": "0.11e-6", + "completion": "0.55e-6", + "input_cache_read": "0.011e-6", + "input_cache_write": "0.1375e-6", + "input_cache_write_1h": "0.22e-6" + }, + { + "name": "Over 100K", + "up_to_tokens": null, + "prompt": "0.55e-6", + "completion": "2.75e-6", + "input_cache_read": "0.055e-6", + "input_cache_write": "0.6875e-6", + "input_cache_write_1h": "1.1e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "0.11e-6", + "completion": "0.55e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.011e-6", + "input_cache_write": "0.1375e-6", + "input_cache_write_1h": "0.22e-6", + "tiers": [ + { + "name": "Up to 100K", + "up_to_tokens": 100000, + "prompt": "0.11e-6", + "completion": "0.55e-6", + "input_cache_read": "0.011e-6", + "input_cache_write": "0.1375e-6", + "input_cache_write_1h": "0.22e-6" + }, + { + "name": "Over 100K", + "up_to_tokens": null, + "prompt": "0.55e-6", + "completion": "2.75e-6", + "input_cache_read": "0.055e-6", + "input_cache_write": "0.6875e-6", + "input_cache_write_1h": "1.1e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "required", "function"], "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] } ], "pricing": { @@ -578,7 +1003,27 @@ "input_cache_read": "0.01e-6", "input_cache_write": "0.125e-6", "input_cache_write_1h": "0.2e-6", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 100K", + "up_to_tokens": 100000, + "prompt": "0.1e-6", + "completion": "0.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0.2e-6" + }, + { + "name": "Over 100K", + "up_to_tokens": null, + "prompt": "0.5e-6", + "completion": "2.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6", + "input_cache_write_1h": "1.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1000000, @@ -598,7 +1043,7 @@ "name": "Claude Opus 4.5", "display_name": "Claude Opus 4.5", "created": 1763942400, - "description": "claude-opus-4-5-20251101 provided by anthropic, aws-bedrock, vertex-anthropic", + "description": "Claude Opus 4.5 is Anthropic's advanced reasoning model built for complex coding, agentic workflows, and long-running tasks with improved multimodal performance, efficiency, and reliability.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -619,17 +1064,23 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", - "input_cache_write_1h": "10.0e-6" + "input_cache_write_1h": "10.0e-6", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, - "max_output": 32000 + "max_output": 32000, + "supported_parameters": ["temperature", "max_tokens", "top_p", "effort"] }, { "providerId": "aws-bedrock", @@ -643,13 +1094,63 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "5.0e-6", + "completion": "25.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "6.25e-6", + "input_cache_write_1h": "10.0e-6" + }, + "context_length": 200000, + "max_output": 32000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 200000, + "max_output": 32000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 200000, + "max_output": 32000, + "streaming": true + } + ], + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, "max_output": 32000 }, @@ -665,15 +1166,19 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, - "max_output": 32000 + "max_output": 32000, + "supported_parameters": ["temperature", "max_tokens", "top_p", "effort"] } ], "pricing": { @@ -684,7 +1189,7 @@ "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 200000, @@ -705,7 +1210,7 @@ "name": "Claude Opus 4.6", "display_name": "Claude Opus 4.6", "created": 1770249600, - "description": "claude-opus-4-6 provided by anthropic, aws-bedrock, azure-anthropic, vertex-anthropic", + "description": "Claude Opus 4.6 is Anthropic's latest flagship model with advanced reasoning capabilities for complex coding, agentic workflows, and long-running tasks.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -726,17 +1231,22 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", - "input_cache_write_1h": "10.0e-6" + "input_cache_write_1h": "10.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["temperature", "max_tokens", "top_p", "effort"] }, { "providerId": "aws-bedrock", @@ -750,11 +1260,90 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "5.0e-6", + "completion": "25.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "6.25e-6", + "input_cache_write_1h": "10.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu-west-2", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, @@ -772,15 +1361,18 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["temperature", "max_tokens", "top_p", "effort"] }, { "providerId": "vertex-anthropic", @@ -794,15 +1386,18 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["temperature", "max_tokens", "top_p", "effort"] } ], "pricing": { @@ -813,7 +1408,7 @@ "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -834,7 +1429,7 @@ "name": "Claude Opus 4.7", "display_name": "Claude Opus 4.7", "created": 1776297600, - "description": "claude-opus-4-7 provided by anthropic, aws-bedrock, azure-anthropic, vertex-anthropic", + "description": "Claude Opus 4.7 is Anthropic's latest flagship model with enhanced coding and vision capabilities, adaptive reasoning, and improved performance on complex agentic workflows.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -855,17 +1450,22 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", - "input_cache_write_1h": "10.0e-6" + "input_cache_write_1h": "10.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "aws-bedrock", @@ -879,6 +1479,84 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "5.0e-6", + "completion": "25.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "6.25e-6", + "input_cache_write_1h": "10.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -887,7 +1565,8 @@ "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "azure-anthropic", @@ -901,15 +1580,18 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "vertex-anthropic", @@ -923,15 +1605,18 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -942,7 +1627,7 @@ "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -957,7 +1642,7 @@ "name": "Claude Opus 4.8", "display_name": "Claude Opus 4.8", "created": 1779926400, - "description": "claude-opus-4-8 provided by anthropic, aws-bedrock, azure-anthropic", + "description": "Claude Opus 4.8 is Anthropic's most capable model with state-of-the-art coding, reasoning, and agentic capabilities.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -978,17 +1663,22 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", - "input_cache_write_1h": "10.0e-6" + "input_cache_write_1h": "10.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "aws-bedrock", @@ -1002,6 +1692,84 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "5.0e-6", + "completion": "25.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "6.25e-6", + "input_cache_write_1h": "10.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -1010,7 +1778,8 @@ "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "azure-anthropic", @@ -1024,15 +1793,18 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -1043,7 +1815,7 @@ "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -1058,7 +1830,7 @@ "name": "Claude Opus 5", "display_name": "Claude Opus 5", "created": 1784851200, - "description": "claude-opus-5 provided by anthropic, aws-bedrock, azure-anthropic", + "description": "Claude Opus 5 is Anthropic's model for complex agentic coding and enterprise work, with state-of-the-art reasoning and agentic capabilities.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1079,17 +1851,22 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", - "input_cache_write_1h": "10.0e-6" + "input_cache_write_1h": "10.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "aws-bedrock", @@ -1103,6 +1880,54 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "5.0e-6", + "completion": "25.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "6.25e-6", + "input_cache_write_1h": "10.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "5.5e-6", + "completion": "27.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "6.875e-6", + "input_cache_write_1h": "11e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -1111,7 +1936,8 @@ "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "azure-anthropic", @@ -1125,15 +1951,18 @@ "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -1144,7 +1973,7 @@ "input_cache_read": "0.5e-6", "input_cache_write": "6.25e-6", "input_cache_write_1h": "10.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -1159,7 +1988,7 @@ "name": "Claude Opus 5.5", "display_name": "Claude Opus 5.5", "created": 1790035200, - "description": "claude-opus-5-5 provided by anthropic, azure-anthropic, aws-bedrock", + "description": "Claude Opus 5.5 is Anthropic's model for long-running agentic coding and knowledge work, with always-on adaptive thinking at a lower price than Claude Opus 5.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1180,17 +2009,22 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "5.0e-6", - "input_cache_write_1h": "8.0e-6" + "input_cache_write_1h": "8.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "azure-anthropic", @@ -1204,15 +2038,18 @@ "input_cache_write": "5.0e-6", "input_cache_write_1h": "8.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] }, { "providerId": "aws-bedrock", @@ -1226,6 +2063,84 @@ "input_cache_write": "5.0e-6", "input_cache_write_1h": "8.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "4.0e-6", + "completion": "20.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "5.0e-6", + "input_cache_write_1h": "8.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "4.4e-6", + "completion": "22e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "8.8e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "4.4e-6", + "completion": "22e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "8.8e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "4.4e-6", + "completion": "22e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "8.8e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "4.4e-6", + "completion": "22e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "8.8e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -1234,7 +2149,8 @@ "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -1245,7 +2161,7 @@ "input_cache_read": "0.2e-6", "input_cache_write": "5.0e-6", "input_cache_write_1h": "8.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -1260,7 +2176,7 @@ "name": "Claude Sonnet 4.5", "display_name": "Claude Sonnet 4.5", "created": 1759104000, - "description": "claude-sonnet-4-5 provided by anthropic, aws-bedrock, vertex-anthropic", + "description": "Latest Claude Sonnet with improved reasoning and extended thinking.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1281,17 +2197,24 @@ "request": "0", "input_cache_read": "0.3e-6", "input_cache_write": "3.75e-6", - "input_cache_write_1h": "6.0e-6" + "input_cache_write_1h": "6.0e-6", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 1024, - "max_output": 64000 + "max_output": 64000, + "deprecated_at": "2026-10-30T00:00:00.000Z", + "deactivated_at": "2026-11-24T17:00:00.000Z" }, { "providerId": "aws-bedrock", @@ -1305,13 +2228,93 @@ "input_cache_write": "3.75e-6", "input_cache_write_1h": "6.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "3.0e-6", + "completion": "15.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.3e-6", + "input_cache_write": "3.75e-6", + "input_cache_write_1h": "6.0e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + } + ], + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 1024, "max_output": 8192 }, @@ -1327,15 +2330,19 @@ "input_cache_write": "3.75e-6", "input_cache_write_1h": "6.0e-6" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 1024, - "max_output": 64000 + "max_output": 64000, + "deactivated_at": "2026-11-30T00:00:00.000Z" } ], "pricing": { @@ -1369,7 +2376,7 @@ "name": "Claude Sonnet 4.5 (2025-09-29)", "display_name": "Claude Sonnet 4.5 (2025-09-29)", "created": 1759104000, - "description": "claude-sonnet-4-5-20250929 provided by anthropic, aws-bedrock", + "description": "Latest Claude Sonnet with improved reasoning and extended thinking.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1390,17 +2397,24 @@ "request": "0", "input_cache_read": "0.3e-6", "input_cache_write": "3.75e-6", - "input_cache_write_1h": "6.0e-6" + "input_cache_write_1h": "6.0e-6", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 1024, - "max_output": 64000 + "max_output": 64000, + "deprecated_at": "2026-10-30T00:00:00.000Z", + "deactivated_at": "2026-11-24T17:00:00.000Z" }, { "providerId": "aws-bedrock", @@ -1414,13 +2428,93 @@ "input_cache_write": "3.75e-6", "input_cache_write_1h": "6.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "3.0e-6", + "completion": "15.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.3e-6", + "input_cache_write": "3.75e-6", + "input_cache_write_1h": "6.0e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 200000, + "max_output": 8192, + "streaming": true + } + ], + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 1024, "max_output": 8192 } @@ -1456,7 +2550,7 @@ "name": "Claude Sonnet 4.6", "display_name": "Claude Sonnet 4.6", "created": 1771286400, - "description": "claude-sonnet-4-6 provided by anthropic, aws-bedrock, vertex-anthropic", + "description": "Claude Sonnet 4.6 with advanced reasoning, extended thinking, and vision capabilities.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1477,15 +2571,20 @@ "request": "0", "input_cache_read": "0.3e-6", "input_cache_write": "3.75e-6", - "input_cache_write_1h": "6.0e-6" + "input_cache_write_1h": "6.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 2048, "max_output": 64000 }, @@ -1501,13 +2600,108 @@ "input_cache_write": "3.75e-6", "input_cache_write_1h": "6.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "3.0e-6", + "completion": "15.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.3e-6", + "input_cache_write": "3.75e-6", + "input_cache_write_1h": "6.0e-6" + }, + "context_length": 1000000, + "max_output": 64000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 1000000, + "max_output": 64000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 1000000, + "max_output": 64000, + "streaming": true + }, + { + "id": "au", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 1000000, + "max_output": 64000, + "streaming": true + }, + { + "id": "jp", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 1000000, + "max_output": 64000, + "streaming": true + }, + { + "id": "eu-west-2", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "6.6e-6" + }, + "context_length": 1000000, + "max_output": 64000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 2048, "max_output": 64000 }, @@ -1523,13 +2717,16 @@ "input_cache_write": "3.75e-6", "input_cache_write_1h": "6.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 2048, "max_output": 64000 } @@ -1542,7 +2739,7 @@ "input_cache_read": "0.3e-6", "input_cache_write": "3.75e-6", "input_cache_write_1h": "6.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -1565,7 +2762,7 @@ "name": "Claude Sonnet 5", "display_name": "Claude Sonnet 5", "created": 1782777600, - "description": "claude-sonnet-5 provided by anthropic, aws-bedrock, azure-anthropic, vertex-anthropic", + "description": "Claude Sonnet 5 with advanced reasoning, adaptive thinking, and vision capabilities.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1586,17 +2783,23 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "4.0e-6" + "input_cache_write_1h": "4.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] }, { "providerId": "aws-bedrock", @@ -1610,15 +2813,51 @@ "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "10.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "4.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "2.2e-6", + "completion": "11e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "4.4e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "required", "function"], + "structured_outputs": false, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] }, { "providerId": "azure-anthropic", @@ -1632,15 +2871,19 @@ "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] }, { "providerId": "vertex-anthropic", @@ -1654,15 +2897,19 @@ "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 4096, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] } ], "pricing": { @@ -1673,7 +2920,7 @@ "input_cache_read": "0.2e-6", "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -1693,7 +2940,7 @@ "name": "Claude Sonnet 5.5", "display_name": "Claude Sonnet 5.5", "created": 1790553600, - "description": "claude-sonnet-5-5 provided by anthropic, azure-anthropic, aws-bedrock", + "description": "Claude Sonnet 5.5 is Anthropic's best combination of speed and intelligence, with adaptive thinking and vision capabilities.", "family": "anthropic", "architecture": { "input_modalities": ["text", "image"], @@ -1714,17 +2961,23 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "4.0e-6" + "input_cache_write_1h": "4.0e-6", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] }, { "providerId": "azure-anthropic", @@ -1738,15 +2991,19 @@ "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort", "tool_choice"] }, { "providerId": "aws-bedrock", @@ -1760,6 +3017,54 @@ "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "10.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "4.0e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "2.2e-6", + "completion": "11e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "4.4e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + }, + { + "id": "eu", + "pricing": { + "prompt": "2.2e-6", + "completion": "11e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.11e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "4.4e-6" + }, + "context_length": 1000000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, @@ -1768,7 +3073,8 @@ "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "min_cacheable_tokens": 512, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": ["max_tokens", "effort"] } ], "pricing": { @@ -1779,7 +3085,7 @@ "input_cache_read": "0.1e-6", "input_cache_write": "2.5e-6", "input_cache_write_1h": "4.0e-6", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -1799,7 +3105,7 @@ "name": "Codestral", "display_name": "Codestral", "created": 1753833600, - "description": "codestral-2508 provided by mistral", + "description": "Code specialist model for low-latency code generation and FIM.", "family": "mistral", "architecture": { "input_modalities": ["text"], @@ -1822,11 +3128,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false } ], @@ -1861,7 +3169,7 @@ "name": "CogView-4", "display_name": "CogView-4", "created": 1741046400, - "description": "cogview-4 provided by zai", + "description": "Z.AI's CogView-4 text-to-image generation model with bilingual support and excellent text rendering.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -1884,11 +3192,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -1925,7 +3235,7 @@ "name": "Custom Model", "display_name": "Custom Model", "created": 1704067200, - "description": "custom provided by llmgateway", + "description": "Custom model endpoint with user-provided base URL.", "family": "llmgateway", "architecture": { "input_modalities": ["text", "image"], @@ -1944,7 +3254,15 @@ "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty" + ] } ], "pricing": { @@ -1975,7 +3293,7 @@ "name": "DeepSeek V3.2", "display_name": "DeepSeek V3.2", "created": 1759104000, - "description": "deepseek-v3.2 provided by deepseek, novita, alibaba, bytedance, nebius, deepinfra, vertex-openai", + "description": "Latest DeepSeek V3 with tools and improved performance.", "family": "deepseek", "architecture": { "input_modalities": ["text"], @@ -1998,12 +3316,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 163840, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "deactivated_at": "2026-05-01T00:00:00.000Z" }, { "providerId": "novita", @@ -2017,13 +3338,28 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 163840, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 65536 + "max_output": 65536, + "quantization": "fp8", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools" + ], + "deactivated_at": "2026-10-28T00:00:00.000Z" }, { "providerId": "alibaba", @@ -2037,13 +3373,48 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.57e-6", + "completion": "1.71e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.114e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 131072, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.287e-6", + "completion": "0.431e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0574e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 131072, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 65536 + "max_output": 65536, + "deactivated_at": "2026-07-08T00:00:00.000Z" }, { "providerId": "bytedance", @@ -2055,13 +3426,31 @@ "request": "0", "input_cache_read": "0.056e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32768, + "prompt": "0.28e-6", + "completion": "0.42e-6", + "input_cache_read": "0.056e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.56e-6", + "completion": "0.84e-6", + "input_cache_read": "0.056e-6" + } + ] }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "max_output": 32768 }, @@ -2077,13 +3466,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 163840, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2026-06-22T00:00:00.000Z" }, { "providerId": "deepinfra", @@ -2097,13 +3489,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 160000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 65536 + "max_output": 65536, + "quantization": "fp4" }, { "providerId": "vertex-openai", @@ -2117,14 +3512,34 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "0.56e-6", + "completion": "1.68e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.056e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 163840, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 163840, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 65536, - "stability": "unstable" + "stability": "unstable", + "deactivated_at": "2026-10-21T00:00:00.000Z" } ], "pricing": { @@ -2161,7 +3576,7 @@ "name": "DeepSeek V4 Flash", "display_name": "DeepSeek V4 Flash", "created": 1776988800, - "description": "deepseek-v4-flash provided by deepseek, novita, alibaba, deepinfra, bytedance, fireworks, together-ai, ranoai, canopywave, baidu, tencent, runware, consensusprotocol", + "description": "DeepSeek's fast and cost-efficient V4 model with extended context and reasoning.", "family": "deepseek", "architecture": { "input_modalities": ["text"], @@ -2182,16 +3597,48 @@ "request": "0", "input_cache_read": "0.0028e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.44e-6", + "completion": "1.32e-6", + "input_cache_read": "0.014e-6" + }, + "off_peak": { + "prompt": "0.22e-6", + "completion": "0.66e-6", + "input_cache_read": "0.007e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } }, + "context_length": 1050000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "max"], - "max_output": 393216 + "max_output": 393216, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ], + "deactivated_at": "2026-09-10T00:00:00.000Z" }, { "providerId": "novita", @@ -2205,13 +3652,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1050000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, - "max_output": 393216 + "max_output": 393216, + "quantization": "fp8" }, { "providerId": "alibaba", @@ -2225,11 +3676,75 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.2e-6", + "completion": "0.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.04e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.2e-6", + "completion": "0.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.04e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.2e-6", + "completion": "0.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.04e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.138e-6", + "completion": "0.275e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.028e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2240,6 +3755,7 @@ "xhigh", "max" ], + "reasoning_max_tokens": true, "max_output": 393216 }, { @@ -2254,14 +3770,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "max"], - "max_output": 393216 + "max_output": 393216, + "quantization": "fp8" }, { "providerId": "bytedance", @@ -2275,11 +3794,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -2304,14 +3825,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.25, + "description": "Queue precedence over standard traffic and protection from load shedding during congestion, at a 25% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 393216 + "max_output": 393216, + "deactivated_at": "2026-10-19T00:00:00.000Z" }, { "providerId": "together-ai", @@ -2325,14 +3858,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 163840, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "xhigh", "max"], - "max_output": 163840 + "max_output": 163840, + "deactivated_at": "2026-10-22T00:00:00.000Z" }, { "providerId": "ranoai", @@ -2346,11 +3883,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2361,7 +3901,8 @@ "xhigh", "max" ], - "max_output": 393216 + "max_output": 393216, + "quantization": "fp4" }, { "providerId": "canopywave", @@ -2375,11 +3916,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2390,7 +3934,8 @@ "xhigh", "max" ], - "max_output": 393216 + "max_output": 393216, + "quantization": "fp8" }, { "providerId": "baidu", @@ -2404,11 +3949,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2425,19 +3972,40 @@ "providerId": "tencent", "externalId": "deepseek-v4-flash-202605", "pricing": { - "prompt": "0.14e-6", - "completion": "0.28e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.0028e-6", + "input_cache_read": "0.003e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.006e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.003e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -2451,26 +4019,37 @@ "max_output": 393216 }, { - "providerId": "runware", - "externalId": "deepseek-v4-flash", + "providerId": "cloudflare", + "externalId": "@cf/deepseek-ai/deepseek-v4-flash-0731", "pricing": { - "prompt": "0.000000076", - "completion": "0.000000153", + "prompt": "0.44e-6", + "completion": "1.32e-6", "image": "0", "request": "0", - "input_cache_read": "0.000000014", + "input_cache_read": "0.014e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, - "cancellation": false, + "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["none", "high", "xhigh", "max"], - "max_output": 384000, - "stability": "stable" + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 393216 }, { "providerId": "consensusprotocol", @@ -2484,15 +4063,79 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, + "reasoning_max_tokens": false, + "quantization": "fp8", "stability": "stable" - } - ], + }, + { + "providerId": "flexai", + "externalId": "DeepSeek-V4-Flash-0731", + "pricing": { + "prompt": "0.000000119", + "completion": "0.000000238", + "image": "0", + "request": "0", + "input_cache_read": "0.0000000178", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.05" + }, + "context_length": 1048576, + "streaming": true, + "vision": false, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["low", "high", "medium", "max"], + "reasoning_max_tokens": false, + "stability": "stable" + }, + { + "providerId": "runware", + "externalId": "deepseek-v4-flash", + "pricing": { + "prompt": "0.000000076", + "completion": "0.000000153", + "image": "0", + "request": "0", + "input_cache_read": "0.000000014", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": false, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": false, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["none", "high", "xhigh", "max"], + "reasoning_max_tokens": false, + "max_output": 384000, + "quantization": "fp8", + "stability": "stable" + } + ], "pricing": { "prompt": "0.000000076", "completion": "0.000000153", @@ -2528,7 +4171,7 @@ "name": "DeepSeek V4 Pro", "display_name": "DeepSeek V4 Pro", "created": 1776988800, - "description": "deepseek-v4-pro provided by deepseek, together-ai, alibaba, deepinfra, bytedance, nebius, canopywave, fireworks, baidu, tencent, reka-ai, runware", + "description": "DeepSeek's most capable V4 model with extended context and reasoning.", "family": "deepseek", "architecture": { "input_modalities": ["text"], @@ -2543,22 +4186,57 @@ "providerId": "deepseek", "externalId": "deepseek-v4-pro", "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", + "prompt": "0.66e-6", + "completion": "1.98e-6", "image": "0", "request": "0", - "input_cache_read": "0.003625e-6", + "input_cache_read": "0.022e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.00075", + "peak": { + "peak": { + "prompt": "1.32e-6", + "completion": "3.96e-6", + "input_cache_read": "0.044e-6" + }, + "off_peak": { + "prompt": "0.66e-6", + "completion": "1.98e-6", + "input_cache_read": "0.022e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } }, + "context_length": 1050000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "high", "max"], - "max_output": 393216 + "max_output": 393216, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "together-ai", @@ -2572,11 +4250,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "high", "max"], "max_output": 163840 @@ -2593,11 +4274,75 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "2.4e-6", + "completion": "4.8e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "2.4e-6", + "completion": "4.8e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "2.4e-6", + "completion": "4.8e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "1.65e-6", + "completion": "3.301e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.138e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2608,6 +4353,7 @@ "xhigh", "max" ], + "reasoning_max_tokens": true, "max_output": 393216 }, { @@ -2622,14 +4368,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "high", "max"], - "max_output": 64000 + "max_output": 64000, + "quantization": "fp8" }, { "providerId": "bytedance", @@ -2643,11 +4392,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -2672,12 +4423,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": true, + "reasoning": true, + "quantization": "fp8", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "canopywave", @@ -2691,11 +4446,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2706,7 +4464,8 @@ "xhigh", "max" ], - "max_output": 393216 + "max_output": 393216, + "quantization": "fp8" }, { "providerId": "fireworks", @@ -2720,14 +4479,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.5, + "description": "Queue precedence over standard traffic and protection from load shedding during congestion, at a 25% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 393216 + "max_output": 393216, + "deactivated_at": "2026-10-13T00:00:00.000Z" }, { "providerId": "baidu", @@ -2741,11 +4512,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2762,19 +4535,40 @@ "providerId": "tencent", "externalId": "deepseek-v4-pro-202606", "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", + "prompt": "0.66e-6", + "completion": "1.98e-6", "image": "0", "request": "0", - "input_cache_read": "0.00363e-6", + "input_cache_read": "0.022e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "1.32e-6", + "completion": "3.96e-6", + "input_cache_read": "0.044e-6" + }, + "off_peak": { + "prompt": "0.66e-6", + "completion": "1.98e-6", + "input_cache_read": "0.022e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -2788,22 +4582,26 @@ "max_output": 393216 }, { - "providerId": "reka-ai", - "externalId": "deepseek-v4-pro", + "providerId": "cloudflare", + "externalId": "@cf/deepseek-ai/deepseek-v4-pro-0813", "pricing": { - "prompt": "0.0000012", - "completion": "0.0000033", + "prompt": "1.32e-6", + "completion": "3.96e-6", "image": "0", "request": "0", - "input_cache_read": "0.00000013", + "input_cache_read": "0.044e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, - "cancellation": false, + "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2814,8 +4612,7 @@ "xhigh", "max" ], - "max_output": 393216, - "stability": "stable" + "max_output": 393216 }, { "providerId": "runware", @@ -2829,26 +4626,50 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": ["none", "high", "xhigh", "max"], + "reasoning_max_tokens": false, "max_output": 384000, + "quantization": "fp8", "stability": "stable" } ], "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", + "prompt": "0.66e-6", + "completion": "1.98e-6", "image": "0", "request": "0", - "input_cache_read": "0.003625e-6", + "input_cache_read": "0.022e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.00075", + "peak": { + "peak": { + "prompt": "1.32e-6", + "completion": "3.96e-6", + "input_cache_read": "0.044e-6" + }, + "off_peak": { + "prompt": "0.66e-6", + "completion": "1.98e-6", + "input_cache_read": "0.022e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + }, "internal_reasoning": "0" }, "context_length": 1050000, @@ -2863,6 +4684,7 @@ "stream", "response_format", "tools", + "tool_choice", "reasoning_effort", "reasoning" ], @@ -2875,7 +4697,7 @@ "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, reka-ai, luminal, sciforium, scx-ai-gp, runware, consensusprotocol", + "description": "DeepSeek's V4.1 Flash model with native vision, extended context, and reasoning; succeeds V4 Flash and V4 Pro.", "family": "deepseek", "architecture": { "input_modalities": ["text", "image"], @@ -2886,6 +4708,56 @@ "is_moderated": true }, "providers": [ + { + "providerId": "tencent", + "externalId": "deepseek-v4.1-flash", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.003e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.006e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.003e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "function"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 393216 + }, { "providerId": "deepseek", "externalId": "deepseek-flash", @@ -2896,16 +4768,48 @@ "request": "0", "input_cache_read": "0.003e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.006e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.003e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } }, + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "max"], - "max_output": 393216 + "max_output": 393216, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ], + "deactivated_at": "2026-10-24T00:00:00.000Z" }, { "providerId": "alibaba", @@ -2917,13 +4821,142 @@ "request": "0", "input_cache_read": "0.03e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.03e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.015e-6" + }, + "hours_utc": [[0, 14]] + } + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.03e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.03e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.015e-6" + }, + "hours_utc": [[0, 14]] + } + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.283e-6", + "completion": "1.131e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0283e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.283e-6", + "completion": "1.131e-6", + "input_cache_read": "0.0283e-6" + }, + "off_peak": { + "prompt": "0.141e-6", + "completion": "0.565e-6", + "input_cache_read": "0.0141e-6" + }, + "hours_utc": [[0, 14]] + } + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.283e-6", + "completion": "1.131e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0283e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.283e-6", + "completion": "1.131e-6", + "input_cache_read": "0.0283e-6" + }, + "off_peak": { + "prompt": "0.141e-6", + "completion": "0.565e-6", + "input_cache_read": "0.0141e-6" + }, + "hours_utc": [[0, 14]] + } + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.283e-6", + "completion": "1.131e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0283e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.283e-6", + "completion": "1.131e-6", + "input_cache_read": "0.0283e-6" + }, + "off_peak": { + "prompt": "0.141e-6", + "completion": "0.565e-6", + "input_cache_read": "0.0141e-6" + }, + "hours_utc": [[0, 14]] + } + }, + "context_length": 1000000, + "max_output": 393216, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2934,6 +4967,7 @@ "xhigh", "max" ], + "reasoning_max_tokens": true, "max_output": 393216 }, { @@ -2948,11 +4982,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -2963,7 +5000,8 @@ "xhigh", "max" ], - "max_output": 393216 + "max_output": 393216, + "quantization": "fp8" }, { "providerId": "fireworks", @@ -2977,11 +5015,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.25, + "description": "Queue precedence over standard traffic and protection from load shedding during congestion, at a 25% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "max_output": 393216 @@ -2998,11 +5047,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], "max_output": 393216 @@ -3019,11 +5071,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -3048,11 +5104,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -3065,44 +5124,28 @@ ], "max_output": 393216 }, - { - "providerId": "entrim", - "externalId": "deepseek-ai/DeepSeek-V4.1-Flash", - "pricing": { - "prompt": "0.0000002", - "completion": "0.0000006", - "image": "0", - "request": "0", - "input_cache_read": "0.000000005", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": false, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["max", "xhigh", "high", "medium", "low"], - "stability": "stable" - }, { "providerId": "reka-ai", "externalId": "deepseek41-flash", "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012", + "prompt": "0.0000001275", + "completion": "0.00000051", "image": "0", "request": "0", - "input_cache_read": "0.000000006", + "input_cache_read": "0.0000000095", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -3113,7 +5156,9 @@ "xhigh", "max" ], + "reasoning_max_tokens": false, "max_output": 393216, + "quantization": "fp4", "stability": "stable" }, { @@ -3128,33 +5173,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, - "stability": "stable" - }, - { - "providerId": "sciforium", - "externalId": "/deployments/ebd34f25/deepseek-ai/DeepSeek-V4.1-Flash", - "pricing": { - "prompt": "0.000000246", - "completion": "0.000000944", - "image": "0", - "request": "0", - "input_cache_read": "0.000000012", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": false, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], + "reasoning_max_tokens": false, "stability": "stable" }, { @@ -3169,12 +5199,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": false, + "reasoning_max_tokens": false, "stability": "stable" }, { @@ -3189,13 +5225,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "high", "xhigh", "max", "none"], + "reasoning_max_tokens": false, "stability": "stable" }, { @@ -3210,22 +5253,29 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "high", "max", "xhigh"], + "reasoning_max_tokens": false, + "quantization": "fp8", "stability": "stable" } ], "pricing": { - "prompt": "0.000000135", - "completion": "0.00000054", + "prompt": "0.0000001275", + "completion": "0.00000051", "image": "0", "request": "0", - "input_cache_read": "0.0000000027", + "input_cache_read": "0.0000000095", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -3254,8 +5304,9 @@ "id": "deepseek-v4.1-flash-1017", "name": "DeepSeek V4.1 Flash 1017", "display_name": "DeepSeek V4.1 Flash 1017", + "aliases": ["deepseek-v4.1-flash-latest"], "created": 1792195200, - "description": "deepseek-v4.1-flash-1017 provided by deepseek, alibaba, together-ai, novita, inference.net, deepinfra, reka-ai", + "description": "DeepSeek's October 2026 update of V4.1 Flash, with native vision, 1M context, and reasoning.", "family": "deepseek", "architecture": { "input_modalities": ["text", "image"], @@ -3266,6 +5317,56 @@ "is_moderated": true }, "providers": [ + { + "providerId": "tencent", + "externalId": "deepseek/deepseek-flash", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.003e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.006e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.003e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": false, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 393216 + }, { "providerId": "deepseek", "externalId": "deepseek-flash", @@ -3276,16 +5377,51 @@ "request": "0", "input_cache_read": "0.003e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.00075", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.006e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.003e-6" + }, + "hours_utc": [ + [1, 4], + [6, 10] + ], + "off_peak_days_utc": [0, 6] + } }, + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "max"], - "max_output": 393216 + "max_output": 393216, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "alibaba", @@ -3297,13 +5433,28 @@ "request": "0", "input_cache_read": "0.03e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "peak": { + "peak": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.03e-6" + }, + "off_peak": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "input_cache_read": "0.015e-6" + }, + "hours_utc": [[0, 14]] + } }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -3314,6 +5465,7 @@ "xhigh", "max" ], + "reasoning_max_tokens": true, "max_output": 393216 }, { @@ -3328,14 +5480,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], - "max_output": 393216 + "max_output": 393216, + "max_temperature": 1.5 }, { "providerId": "novita", @@ -3349,11 +5505,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -3378,14 +5537,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1.5 }, { "providerId": "deepinfra", @@ -3399,11 +5563,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -3414,25 +5581,29 @@ "xhigh", "max" ], - "max_output": 393216 + "max_output": 393216, + "quantization": "fp8" }, { - "providerId": "reka-ai", - "externalId": "deepseek41-flash-20261017", + "providerId": "baidu", + "externalId": "deepseek-v4.1-flash-1017", "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", + "prompt": "0.28e-6", + "completion": "1.13e-6", "image": "0", "request": "0", - "input_cache_read": "0.000000003", + "input_cache_read": "0.006e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, - "cancellation": false, + "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -3444,45 +5615,303 @@ "max" ], "max_output": 393216, - "stability": "stable" - } - ], - "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.003e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1050000, - "max_output": 131072, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "stop", - "stream", - "response_format", - "tools", - "reasoning_effort", - "reasoning" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, + "quantization": "fp8" + }, + { + "providerId": "cloudflare", + "externalId": "@cf/deepseek-ai/deepseek-v4.1-flash-1017", + "pricing": { + "prompt": "0.3e-6", + "completion": "1.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.006e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "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" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "reasoning_max_tokens": false, + "max_output": 393216, + "quantization": "fp4", + "stability": "stable" + }, + { + "providerId": "runware", + "externalId": "deepseek-v4.1-flash-1017", + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "image": "0", + "request": "0", + "input_cache_read": "0.00000001", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "required"], + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], + "reasoning_max_tokens": false, + "max_output": 1048576, + "stability": "stable" + }, + { + "providerId": "flexai", + "externalId": "DeepSeek-V4.1-Flash-1017", + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "image": "0", + "request": "0", + "input_cache_read": "0.0000000225", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.05" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["medium", "high", "max", "low"], + "reasoning_max_tokens": false, + "quantization": "fp8", + "stability": "stable" + }, + { + "providerId": "sciforium", + "externalId": "/deployments/serverless/deepseek-ai/DeepSeek-V4.1-Flash-1017", + "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" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], + "reasoning_max_tokens": false, + "quantization": "fp8", + "stability": "stable" + }, + { + "providerId": "entrim", + "externalId": "deepseek-v4.1-flash-1017", + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000008", + "image": "0", + "request": "0", + "input_cache_read": "0.000000005", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.31" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["low", "high", "medium", "xhigh", "max"], + "reasoning_max_tokens": false, + "quantization": "fp8", + "stability": "stable" + } + ], + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000008", + "image": "0", + "request": "0", + "input_cache_read": "0.000000005", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "discount": "0.31", + "internal_reasoning": "0" + }, + "context_length": 1050000, + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "tool_choice", + "reasoning_effort", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, + { + "id": "deepseek-v4.1-flash-cyber", + "name": "DeepSeek V4.1 Flash Cyber", + "display_name": "DeepSeek V4.1 Flash Cyber", + "created": 1793232000, + "description": "Abliterated DeepSeek V4.1 Flash 1017 for security tooling and agents, with fewer refusals, vision, tool calling, and a 1M-token context window. Enterprise plan only.", + "family": "deepseek", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "inference.net", + "externalId": "deepseek-v4.1-flash-1017-cyber", + "pricing": { + "prompt": "0.3e-6", + "completion": "1e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.007e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1040000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["none", "low", "high", "xhigh", "max"], + "max_output": 393216, + "max_temperature": 1.5 + } + ], + "pricing": { + "prompt": "0.3e-6", + "completion": "1e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.007e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 1040000, + "max_output": 393216, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, { "id": "devstral-2512", "name": "Devstral 2", "display_name": "Devstral 2", "created": 1765238400, - "description": "devstral-2512 provided by mistral", + "description": "Frontier code agents model for software engineering tasks.", "family": "mistral", "architecture": { "input_modalities": ["text"], @@ -3505,11 +5934,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false } ], @@ -3544,7 +5975,7 @@ "name": "Eleven Flash v2.5", "display_name": "Eleven Flash v2.5", "created": 1733184000, - "description": "eleven-flash-v2-5 provided by elevenlabs", + "description": "Ultra-fast, low-latency ElevenLabs text-to-speech model optimized for real-time use across 32 languages. Generates speech via the /v1/audio/speech endpoint.", "family": "elevenlabs", "architecture": { "input_modalities": ["text"], @@ -3562,23 +5993,49 @@ "prompt": "0", "completion": "0", "image": "0", + "input_character": "55e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 40000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "supported_voices": [ + "Sarah", + "Aria", + "Roger", + "Laura", + "Charlie", + "George", + "Callum", + "River", + "Liam", + "Charlotte", + "Alice", + "Matilda", + "Will", + "Jessica", + "Eric", + "Chris", + "Brian", + "Daniel", + "Lily", + "Bill" + ] } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", + "input_character": "55e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -3606,7 +6063,7 @@ "name": "Eleven Multilingual v2", "display_name": "Eleven Multilingual v2", "created": 1692662400, - "description": "eleven-multilingual-v2 provided by elevenlabs", + "description": "ElevenLabs' most lifelike text-to-speech model with rich emotional expression across 29 languages. Generates speech via the /v1/audio/speech endpoint.", "family": "elevenlabs", "architecture": { "input_modalities": ["text"], @@ -3624,23 +6081,49 @@ "prompt": "0", "completion": "0", "image": "0", + "input_character": "110e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 10000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "supported_voices": [ + "Sarah", + "Aria", + "Roger", + "Laura", + "Charlie", + "George", + "Callum", + "River", + "Liam", + "Charlotte", + "Alice", + "Matilda", + "Will", + "Jessica", + "Eric", + "Chris", + "Brian", + "Daniel", + "Lily", + "Bill" + ] } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", + "input_character": "110e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -3668,7 +6151,7 @@ "name": "Eleven Turbo v2.5", "display_name": "Eleven Turbo v2.5", "created": 1721260800, - "description": "eleven-turbo-v2-5 provided by elevenlabs", + "description": "Fast, balanced ElevenLabs text-to-speech model with low latency across 32 languages. Generates speech via the /v1/audio/speech endpoint.", "family": "elevenlabs", "architecture": { "input_modalities": ["text"], @@ -3686,23 +6169,49 @@ "prompt": "0", "completion": "0", "image": "0", + "input_character": "55e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 40000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "supported_voices": [ + "Sarah", + "Aria", + "Roger", + "Laura", + "Charlie", + "George", + "Callum", + "River", + "Liam", + "Charlotte", + "Alice", + "Matilda", + "Will", + "Jessica", + "Eric", + "Chris", + "Brian", + "Daniel", + "Lily", + "Bill" + ] } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", + "input_character": "55e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -3730,7 +6239,7 @@ "name": "Eleven v3", "display_name": "Eleven v3", "created": 1749081600, - "description": "eleven-v3 provided by elevenlabs", + "description": "ElevenLabs' most expressive, human-like text-to-speech model supporting 70+ languages. Generates speech via the /v1/audio/speech endpoint.", "family": "elevenlabs", "architecture": { "input_modalities": ["text"], @@ -3748,23 +6257,49 @@ "prompt": "0", "completion": "0", "image": "0", + "input_character": "110e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 5000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "supported_voices": [ + "Sarah", + "Aria", + "Roger", + "Laura", + "Charlie", + "George", + "Callum", + "River", + "Liam", + "Charlotte", + "Alice", + "Matilda", + "Will", + "Jessica", + "Eric", + "Chris", + "Brian", + "Daniel", + "Lily", + "Bill" + ] } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", + "input_character": "110e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -3788,15 +6323,15 @@ "free": false }, { - "id": "ernie-4.5-vl-424b-a47b", - "name": "ERNIE 4.5 VL 424B A47B", - "display_name": "ERNIE 4.5 VL 424B A47B", - "created": 1751241600, - "description": "ernie-4.5-vl-424b-a47b provided by novita", - "family": "baidu", + "id": "flux-3-max", + "name": "FLUX 3 Max", + "display_name": "FLUX 3 Max", + "created": 1792022400, + "description": "FLUX 3 Max text-to-video and image-to-video generation with optional audio.", + "family": "black-forest-labs", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["text"], + "output_modalities": ["video"], "tokenizer": "GPT" }, "top_provider": { @@ -3804,30 +6339,60 @@ }, "providers": [ { - "providerId": "novita", - "externalId": "baidu/ernie-4.5-vl-424b-a47b", + "providerId": "fal-ai", + "externalId": "blackforestlabs/flux-3-max", + "supportedVideoSizes": [ + "1280x720", + "720x1280", + "1920x1080", + "1080x1920" + ], + "supportsVideoAudio": true, + "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [ + 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20 + ], + "supported_video_durations_seconds_image_to_video": [ + 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20 + ], "pricing": { - "prompt": "0.42e-6", - "completion": "1.25e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_second": { + "default_audio": "0.17", + "default_video": "0.17", + "720p_audio": "0.17", + "720p_video": "0.17", + "1080p_audio": "0.29", + "1080p_video": "0.29" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "streaming": false, "vision": true, - "cancellation": true, + "cancellation": false, "tools": false, "parallelToolCalls": false, - "reasoning": true, - "max_output": 16000 + "json_output": false, + "reasoning": false } ], "pricing": { - "prompt": "0.42e-6", - "completion": "1.25e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_second": { + "default_audio": "0.17", + "default_video": "0.17", + "720p_audio": "0.17", + "720p_video": "0.17", + "1080p_audio": "0.29", + "1080p_video": "0.29" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -3835,17 +6400,19 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 123000, - "max_output": 16000, + "context_length": 0, + "per_request_limits": { + "max_video_duration_seconds": "20" + }, "supported_parameters": [ "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty", - "stop", - "stream", - "reasoning" + "response_format", + "tools", + "tool_choice" ], "json_output": false, "structured_outputs": false, @@ -3856,7 +6423,7 @@ "name": "Fugu Max", "display_name": "Fugu Max", "created": 1789084800, - "description": "fugu-max provided by sakana", + "description": "Sakana AI's multi-agent orchestration model optimized for cost and performance, coordinating a diverse pool of open and specialized models.", "family": "sakana", "architecture": { "input_modalities": ["text", "image"], @@ -3879,11 +6446,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["high", "xhigh", "max"] } @@ -3920,7 +6491,7 @@ "name": "Fugu Ultra", "display_name": "Fugu Ultra", "created": 1782086400, - "description": "fugu-ultra provided by sakana", + "description": "Sakana AI's quality-optimized multi-agent orchestration model. Delivered as a single OpenAI-compatible model, Fugu Ultra coordinates a pool of frontier models — selecting, delegating, verifying, and synthesizing internally — for hard, multi-step reasoning.", "family": "sakana", "architecture": { "input_modalities": ["text", "image"], @@ -3941,13 +6512,31 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5e-6", + "completion": "30e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10e-6", + "completion": "45e-6", + "input_cache_read": "1e-6" + } + ] }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["high", "xhigh", "max"] } @@ -3961,6 +6550,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5e-6", + "completion": "30e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10e-6", + "completion": "45e-6", + "input_cache_read": "1e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1000000, @@ -3984,7 +6589,7 @@ "name": "Fugu Ultra v2.0", "display_name": "Fugu Ultra v2.0", "created": 1789084800, - "description": "fugu-ultra-v2.0 provided by sakana", + "description": "Sakana AI's flagship multi-agent orchestration model, coordinating frontier and specialized models for complex reasoning, research, and software development.", "family": "sakana", "architecture": { "input_modalities": ["text", "image"], @@ -4005,13 +6610,33 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5e-6", + "completion": "30e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10e-6", + "completion": "45e-6", + "input_cache_read": "1e-6" + } + ] }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["high", "xhigh", "max"] } @@ -4025,6 +6650,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5e-6", + "completion": "30e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10e-6", + "completion": "45e-6", + "input_cache_read": "1e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1000000, @@ -4049,7 +6690,7 @@ "display_name": "Gemini 2.5 Flash Image", "aliases": ["nano banana"], "created": 1759363200, - "description": "gemini-2.5-flash-image provided by google-ai-studio, google-vertex, glacier", + "description": "Production Gemini Flash model for text and image generation.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -4065,68 +6706,82 @@ "externalId": "gemini-2.5-flash-image", "pricing": { "prompt": "0.3e-6", - "completion": "30e-6", + "completion": "2.5e-6", "image": "0", + "image_output": "30e-6", + "image_output_tokens_by_resolution": { + "default": 1290 + }, "request": "0", - "input_cache_read": "0.03e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 32768, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2027-03-15T00:00:00.000Z" }, { "providerId": "google-vertex", "externalId": "gemini-2.5-flash-image", "pricing": { "prompt": "0.3e-6", - "completion": "30e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.03e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - }, - { - "providerId": "glacier", - "externalId": "gemini-2.5-flash-image", - "pricing": { - "prompt": "0.3e-6", - "completion": "30e-6", + "completion": "2.5e-6", "image": "0", + "image_output": "30e-6", + "image_output_tokens_by_resolution": { + "default": 1290 + }, "request": "0", - "input_cache_read": "0.03e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2027-03-15T00:00:00.000Z" } ], "pricing": { "prompt": "0.3e-6", - "completion": "30e-6", + "completion": "2.5e-6", "image": "0", + "image_output": "30e-6", + "image_output_tokens_by_resolution": { + "default": 1290 + }, "request": "0", - "input_cache_read": "0.03e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -4144,16 +6799,17 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, - "free": false + "json_output": false, + "structured_outputs": false, + "free": false, + "deactivated_at": "2027-03-15T00:00:00.000Z" }, { "id": "gemini-2.5-flash-native-audio-preview-12-2025", "name": "Gemini 2.5 Flash Native Audio Preview (12-2025)", "display_name": "Gemini 2.5 Flash Native Audio Preview (12-2025)", "created": 1765497600, - "description": "gemini-2.5-flash-native-audio-preview-12-2025 provided by google-ai-studio", + "description": "Google's native-audio Gemini Live model. Served via the gateway's /v1/realtime WebSocket endpoint using Gemini's own BidiGenerateContent protocol, with text and audio input/output and function calling.", "family": "google", "architecture": { "input_modalities": ["text", "audio"], @@ -4179,14 +6835,49 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 8192, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ], "stability": "beta" } ], @@ -4226,7 +6917,7 @@ "name": "Gemini 2.5 Flash Preview TTS", "display_name": "Gemini 2.5 Flash Preview TTS", "created": 1747699200, - "description": "gemini-2.5-flash-preview-tts provided by google-ai-studio", + "description": "Gemini 2.5 Flash text-to-speech model. Generates natural, controllable single-speaker audio from text via the /v1/audio/speech endpoint.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -4250,13 +6941,47 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 16000 + "max_output": 16000, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ] } ], "pricing": { @@ -4292,7 +7017,7 @@ "name": "Gemini 2.5 Pro Preview TTS", "display_name": "Gemini 2.5 Pro Preview TTS", "created": 1747699200, - "description": "gemini-2.5-pro-preview-tts provided by google-ai-studio, google-vertex", + "description": "Gemini 2.5 Pro text-to-speech model. Generates high-quality, controllable single-speaker audio from text via the /v1/audio/speech endpoint.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -4316,13 +7041,47 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 16000 + "max_output": 16000, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ] }, { "providerId": "google-vertex", @@ -4337,13 +7096,47 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 16000 + "max_output": 16000, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ] } ], "pricing": { @@ -4379,7 +7172,7 @@ "name": "Gemini 3 Flash (Preview)", "display_name": "Gemini 3 Flash (Preview)", "created": 1765929600, - "description": "gemini-3-flash-preview provided by google-ai-studio, google-vertex", + "description": "Preview of next-generation Gemini 3 Flash built for speed, combining frontier intelligence with superior search and grounding.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -4402,15 +7195,37 @@ "request": "0", "input_cache_read": "0.05e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65535 }, { @@ -4425,15 +7240,38 @@ "request": "0", "input_cache_read": "0.05e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65535 } ], @@ -4447,7 +7285,7 @@ "input_cache_read": "0.05e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -4473,7 +7311,7 @@ "display_name": "Gemini 3 Pro Image", "aliases": ["nano banana pro"], "created": 1779926400, - "description": "gemini-3-pro-image provided by google-ai-studio, glacier, google-vertex, quartz", + "description": "Native image generation model for professional-grade image editing and generation.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -4491,36 +7329,43 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - }, - { - "providerId": "glacier", - "externalId": "gemini-3-pro-image-preview", - "pricing": { - "prompt": "2e-6", - "completion": "12e-6", - "image": "2e-6", - "request": "0", - "input_cache_read": "0.2e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, "max_output": 32768 }, @@ -4531,16 +7376,38 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, "max_output": 32768 }, @@ -4551,16 +7418,29 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, "max_output": 32768 } @@ -4569,6 +7449,16 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -4598,7 +7488,7 @@ "display_name": "Gemini 3 Pro Image (Preview)", "aliases": ["nano banana", "nano banana 2"], "created": 1763596800, - "description": "gemini-3-pro-image-preview provided by google-ai-studio, glacier, google-vertex, quartz", + "description": "Native image generation model optimized for speed, flexibility, and contextual understanding. Text priced same as Gemini 3 Pro, image output at $0.134/image (1K-2K) or $0.24/image (4K).", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -4616,36 +7506,43 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - }, - { - "providerId": "glacier", - "externalId": "gemini-3-pro-image-preview", - "pricing": { - "prompt": "2e-6", - "completion": "12e-6", - "image": "2e-6", - "request": "0", - "input_cache_read": "0.2e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, "max_output": 32768 }, @@ -4656,16 +7553,38 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, "max_output": 32768 }, @@ -4676,16 +7595,29 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, "max_output": 32768 } @@ -4694,6 +7626,16 @@ "prompt": "2e-6", "completion": "12e-6", "image": "2e-6", + "image_output": "120e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1120, + "4K": 2000, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -4723,7 +7665,7 @@ "display_name": "Gemini 3.1 Flash Image", "aliases": ["nano banana 2"], "created": 1779926400, - "description": "gemini-3.1-flash-image provided by google-ai-studio, glacier, google-vertex, quartz", + "description": "Native image generation model optimized for fast, high-volume image creation and editing.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -4741,39 +7683,33 @@ "prompt": "0.5e-6", "completion": "3e-6", "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 32768 }, - { - "providerId": "glacier", - "externalId": "gemini-3.1-flash-image-preview", - "pricing": { - "prompt": "0.25e-6", - "completion": "1.5e-6", - "image": "0.25e-6", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 65536 - }, { "providerId": "google-vertex", "externalId": "gemini-3.1-flash-image", @@ -4781,16 +7717,39 @@ "prompt": "0.5e-6", "completion": "3e-6", "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 32768 }, @@ -4801,24 +7760,49 @@ "prompt": "0.5e-6", "completion": "3e-6", "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 32768 } ], "pricing": { - "prompt": "0.25e-6", - "completion": "1.5e-6", - "image": "0.25e-6", + "prompt": "0.5e-6", + "completion": "3e-6", + "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -4838,8 +7822,8 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, + "json_output": false, + "structured_outputs": false, "free": false }, { @@ -4847,7 +7831,7 @@ "name": "Gemini 3.1 Flash Image (Preview)", "display_name": "Gemini 3.1 Flash Image (Preview)", "created": 1772064000, - "description": "gemini-3.1-flash-image-preview provided by google-ai-studio, glacier, google-vertex, quartz", + "description": "Preview of Gemini 3.1 Flash with native image generation capabilities.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -4865,39 +7849,33 @@ "prompt": "0.5e-6", "completion": "3e-6", "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 32768 }, - { - "providerId": "glacier", - "externalId": "gemini-3.1-flash-image-preview", - "pricing": { - "prompt": "0.25e-6", - "completion": "1.5e-6", - "image": "0.25e-6", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 65536 - }, { "providerId": "google-vertex", "externalId": "gemini-3.1-flash-image", @@ -4905,16 +7883,39 @@ "prompt": "0.5e-6", "completion": "3e-6", "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 32768 }, @@ -4925,24 +7926,49 @@ "prompt": "0.5e-6", "completion": "3e-6", "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 32768 } ], "pricing": { - "prompt": "0.25e-6", - "completion": "1.5e-6", - "image": "0.25e-6", + "prompt": "0.5e-6", + "completion": "3e-6", + "image": "0.5e-6", + "image_output": "60e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "0.5K": 747, + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -4962,8 +7988,8 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, + "json_output": false, + "structured_outputs": false, "free": false }, { @@ -4971,7 +7997,7 @@ "name": "Gemini 3.1 Flash Lite", "display_name": "Gemini 3.1 Flash Lite", "created": 1778198400, - "description": "gemini-3.1-flash-lite provided by google-ai-studio, google-vertex", + "description": "Ultra-lightweight Gemini 3.1 Flash Lite for high-volume, cost-sensitive tasks.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -4994,15 +8020,37 @@ "request": "0", "input_cache_read": "0.025e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 }, { @@ -5017,15 +8065,38 @@ "request": "0", "input_cache_read": "0.025e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 } ], @@ -5039,7 +8110,7 @@ "input_cache_read": "0.025e-6", "input_cache_write": "0.08333e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5064,7 +8135,7 @@ "name": "Gemini 3.1 Flash Lite Image", "display_name": "Gemini 3.1 Flash Lite Image", "created": 1782172800, - "description": "gemini-3.1-flash-lite-image provided by google-ai-studio, google-vertex", + "description": "Our smallest and most cost effective image generation and editing model, built for at scale usage.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -5082,18 +8153,30 @@ "prompt": "0.25e-6", "completion": "1.5e-6", "image": "0.25e-6", + "image_output": "30e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": ["minimal", "high"], + "reasoning_max_tokens": true, "max_output": 4096 }, { @@ -5103,18 +8186,39 @@ "prompt": "0.25e-6", "completion": "1.5e-6", "image": "0.25e-6", + "image_output": "30e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": ["none", "high"], + "reasoning_max_tokens": true, "max_output": 4096 } ], @@ -5122,6 +8226,14 @@ "prompt": "0.25e-6", "completion": "1.5e-6", "image": "0.25e-6", + "image_output": "30e-6", + "image_input_tokens_by_resolution": { + "default": 560 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -5151,7 +8263,7 @@ "name": "Gemini 3.1 Flash Live Preview", "display_name": "Gemini 3.1 Flash Live Preview", "created": 1774483200, - "description": "gemini-3.1-flash-live-preview provided by google-ai-studio", + "description": "Google's low-latency Gemini Live model. Served via the gateway's /v1/realtime WebSocket endpoint using Gemini's own BidiGenerateContent protocol, with text and audio input/output and function calling.", "family": "google", "architecture": { "input_modalities": ["text", "audio"], @@ -5177,14 +8289,49 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 65536, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ], "stability": "beta" } ], @@ -5224,7 +8371,7 @@ "name": "Gemini 3.1 Flash TTS Preview", "display_name": "Gemini 3.1 Flash TTS Preview", "created": 1776211200, - "description": "gemini-3.1-flash-tts-preview provided by google-ai-studio, google-vertex", + "description": "Gemini 3.1 Flash text-to-speech model. Generates low-latency, prompt-steerable audio from text via the /v1/audio/speech endpoint.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -5248,13 +8395,47 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 16000 + "max_output": 16000, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ] }, { "providerId": "google-vertex", @@ -5269,13 +8450,47 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 16000 + "max_output": 16000, + "supported_voices": [ + "Kore", + "Puck", + "Zephyr", + "Charon", + "Fenrir", + "Leda", + "Orus", + "Aoede", + "Callirrhoe", + "Autonoe", + "Enceladus", + "Iapetus", + "Umbriel", + "Algieba", + "Despina", + "Erinome", + "Algenib", + "Rasalgethi", + "Laomedeia", + "Achernar", + "Alnilam", + "Schedar", + "Gacrux", + "Pulcherrima", + "Achird", + "Zubenelgenubi", + "Vindemiatrix", + "Sadachbia", + "Sadaltager", + "Sulafat" + ] } ], "pricing": { @@ -5311,7 +8526,7 @@ "name": "Gemini 3.1 Pro (Preview)", "display_name": "Gemini 3.1 Pro (Preview)", "created": 1771459200, - "description": "gemini-3.1-pro-preview provided by google-ai-studio, google-vertex, quartz", + "description": "Preview of Gemini 3.1 Pro with enhanced capabilities and reasoning.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5332,15 +8547,53 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2e-6", + "completion": "12e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4e-6", + "completion": "18e-6", + "input_cache_read": "0.4e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 }, { @@ -5353,15 +8606,54 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2e-6", + "completion": "12e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4e-6", + "completion": "18e-6", + "input_cache_read": "0.4e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 }, { @@ -5374,15 +8666,38 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.014", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2e-6", + "completion": "12e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4e-6", + "completion": "18e-6", + "input_cache_read": "0.4e-6" + } + ] }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 } ], @@ -5394,7 +8709,23 @@ "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2e-6", + "completion": "12e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4e-6", + "completion": "18e-6", + "input_cache_read": "0.4e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1048576, @@ -5419,7 +8750,7 @@ "name": "Gemini 3.5 Flash", "display_name": "Gemini 3.5 Flash", "created": 1779148800, - "description": "gemini-3.5-flash provided by google-ai-studio, google-vertex", + "description": "Gemini 3.5 Flash combines frontier intelligence with superior speed, search, and grounding.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5442,16 +8773,39 @@ "request": "0", "input_cache_read": "0.15e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "deactivated_at": "2026-10-17T00:00:00.000Z" }, { "providerId": "google-vertex", @@ -5465,15 +8819,38 @@ "request": "0", "input_cache_read": "0.15e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 } ], @@ -5487,7 +8864,7 @@ "input_cache_read": "0.15e-6", "input_cache_write": "0.08333e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5512,7 +8889,7 @@ "name": "Gemini 3.5 Flash Lite", "display_name": "Gemini 3.5 Flash Lite", "created": 1784592000, - "description": "gemini-3.5-flash-lite provided by google-ai-studio, google-vertex", + "description": "Gemini 3.5 Flash Lite is the fastest, most cost-effective 3.5 model for high-throughput, low-latency tasks like agentic search and document processing.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5533,15 +8910,37 @@ "request": "0", "input_cache_read": "0.03e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 }, { @@ -5554,15 +8953,38 @@ "request": "0", "input_cache_read": "0.03e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 } ], @@ -5574,7 +8996,7 @@ "input_cache_read": "0.03e-6", "input_cache_write": "0.08333e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5599,7 +9021,7 @@ "name": "Gemini 3.6 Flash", "display_name": "Gemini 3.6 Flash", "created": 1784592000, - "description": "gemini-3.6-flash provided by google-ai-studio, google-vertex", + "description": "Gemini 3.6 Flash delivers better coding, knowledge work, and multimodal performance than 3.5 Flash while using fewer output tokens at a lower price.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5620,16 +9042,45 @@ "request": "0", "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "google-vertex", @@ -5641,16 +9092,47 @@ "request": "0", "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ], + "deactivated_at": "2026-11-19T00:00:00.000Z" } ], "pricing": { @@ -5661,7 +9143,7 @@ "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5683,7 +9165,7 @@ "name": "Gemini 3.7 Flash", "display_name": "Gemini 3.7 Flash", "created": 1786579200, - "description": "gemini-3.7-flash provided by google-ai-studio, google-vertex", + "description": "Gemini 3.7 Flash succeeds 3.6 Flash with stronger coding, document processing, and agentic workflow performance at the same 1M-token context window, with multimodal input and thinking support.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5704,16 +9186,46 @@ "request": "0", "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ], + "deactivated_at": "2026-10-17T00:00:00.000Z" }, { "providerId": "google-vertex", @@ -5725,16 +9237,47 @@ "request": "0", "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ], + "deactivated_at": "2027-01-28T00:00:00.000Z" } ], "pricing": { @@ -5745,7 +9288,7 @@ "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5768,7 +9311,7 @@ "name": "Gemini 3.8 Flash", "display_name": "Gemini 3.8 Flash", "created": 1788307200, - "description": "gemini-3.8-flash provided by google-ai-studio, google-vertex", + "description": "Gemini 3.8 Flash provides fast, multimodal reasoning for coding and agentic workloads.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5789,17 +9332,46 @@ "request": "0", "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, - "max_output": 65536 + "max_output": 65536, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "google-vertex", @@ -5811,17 +9383,47 @@ "request": "0", "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability. Served on the global endpoint." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": true, "min_cacheable_tokens": 4096, - "max_output": 65536 + "max_output": 65536, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { @@ -5832,7 +9434,7 @@ "input_cache_read": "0.075e-6", "input_cache_write": "0.08333e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5854,7 +9456,7 @@ "name": "Gemini 4 Argon", "display_name": "Gemini 4 Argon", "created": 1790726400, - "description": "gemini-4-argon provided by google-ai-studio, google-vertex", + "description": "Gemini 4 Argon is Google's frontier model for long-horizon coding, enterprise knowledge work, and cybersecurity defense, with up to 1M output tokens.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -5875,17 +9477,46 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0.375e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014", + "discount": "0.5000" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for variable latency and best-effort availability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["high"], "min_cacheable_tokens": 4096, - "max_output": 1048576 + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "google-vertex", @@ -5897,17 +9528,41 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0.375e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.014", + "discount": "0.5000" + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.8, + "description": "Premium low-latency tier prioritized above standard and flex traffic, at an 80% premium. Served on the global endpoint." + } + ], + "service_tier_regions": ["global"], + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["high"], "min_cacheable_tokens": 4096, - "max_output": 1048576 + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { @@ -5918,7 +9573,8 @@ "input_cache_read": "0.2e-6", "input_cache_write": "0.375e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", + "discount": "0.5000", "internal_reasoning": "0" }, "context_length": 1048576, @@ -5940,7 +9596,7 @@ "name": "Gemini Embedding 001", "display_name": "Gemini Embedding 001", "created": 1752451200, - "description": "gemini-embedding-001 provided by google-ai-studio, google-vertex", + "description": "Google's state-of-the-art text embedding model. Default output dimension 3072; supports the `dimensions` parameter to shorten output (recommended: 768, 1536, 3072).", "family": "google", "architecture": { "input_modalities": ["text"], @@ -5963,11 +9619,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2048, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false }, { @@ -5982,11 +9640,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2048, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -6021,7 +9681,7 @@ "name": "Gemini Embedding 2", "display_name": "Gemini Embedding 2", "created": 1776816000, - "description": "gemini-embedding-2 provided by google-ai-studio", + "description": "Google's recommended embedding model — first multimodal embedding model in the Gemini API (text-only via this endpoint today). Default output dimension 3072; supports the `dimensions` parameter (recommended: 768, 1536, 3072). Embedding space is incompatible with gemini-embedding-001.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -6044,11 +9704,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8192, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -6084,7 +9746,7 @@ "display_name": "Gemini Nano Banana 2.1", "aliases": ["nano banana 2.1"], "created": 1791244800, - "description": "gemini-nano-banana-2.1 provided by google-ai-studio", + "description": "Flash-tier image generation and conversational editing model succeeding Nano Banana 2, with sharper 1K–4K output, better text rendering, multi-turn character consistency and search grounding.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -6102,16 +9764,31 @@ "prompt": "1.5e-6", "completion": "7.5e-6", "image": "1.5e-6", + "image_output": "30e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.014" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": true, "reasoning": false, "max_output": 32768 } @@ -6120,11 +9797,21 @@ "prompt": "1.5e-6", "completion": "7.5e-6", "image": "1.5e-6", + "image_output": "30e-6", + "image_input_tokens_by_resolution": { + "default": 1120 + }, + "image_output_tokens_by_resolution": { + "1K": 1120, + "2K": 1680, + "4K": 2520, + "default": 1120 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", "internal_reasoning": "0" }, "context_length": 131072, @@ -6143,12 +9830,109 @@ "structured_outputs": false, "free": false }, + { + "id": "gemini-omni-1.1-flash", + "name": "Gemini Omni 1.1 Flash", + "display_name": "Gemini Omni 1.1 Flash", + "created": 1787788800, + "description": "Google Gemini Omni 1.1 Flash video generation with native audio.", + "family": "google", + "architecture": { + "input_modalities": ["text"], + "output_modalities": ["video"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "google-ai-studio", + "externalId": "gemini-omni-1.1-flash", + "supportedVideoSizes": [ + "640x360", + "360x640", + "1280x720", + "720x1280", + "1920x1080", + "1080x1920", + "3840x2160", + "2160x3840" + ], + "supportsVideoAudio": true, + "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [3, 4, 5, 6, 7, 8, 9, 10], + "pricing": { + "prompt": "1.5e-6", + "completion": "9e-6", + "image": "0", + "video_output": "17.5e-6", + "per_second": { + "360p": "0.0337925", + "720p": "0.10136", + "1080p": "0.15204", + "4k": "0.30408" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 131072, + "streaming": false, + "vision": false, + "cancellation": true, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "reasoning": false, + "max_output": 1 + } + ], + "pricing": { + "prompt": "1.5e-6", + "completion": "9e-6", + "image": "0", + "video_output": "17.5e-6", + "per_second": { + "360p": "0.0337925", + "720p": "0.10136", + "1080p": "0.15204", + "4k": "0.30408" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 131072, + "max_output": 1, + "per_request_limits": { + "max_video_duration_seconds": "10" + }, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false + }, { "id": "gemini-pro-latest", "name": "Gemini Pro Latest", "display_name": "Gemini Pro Latest", "created": 1772150400, - "description": "gemini-pro-latest provided by google-ai-studio", + "description": "Always points to the latest Gemini Pro model.", "family": "google", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -6169,15 +9953,39 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.014", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2e-6", + "completion": "12e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4e-6", + "completion": "18e-6", + "input_cache_read": "0.4e-6" + } + ] }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, + "document": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": true, "max_output": 65536 } ], @@ -6189,7 +9997,23 @@ "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.014", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2e-6", + "completion": "12e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4e-6", + "completion": "18e-6", + "input_cache_read": "0.4e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1048576, @@ -6214,7 +10038,7 @@ "name": "Gemma 4 26B A4B IT", "display_name": "Gemma 4 26B A4B IT", "created": 1775088000, - "description": "gemma-4-26b-a4b-it provided by deepinfra, novita", + "description": "Gemma 4 26B mixture-of-experts instruction-tuned model (4B active) with reasoning.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -6237,13 +10061,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 + "max_output": 32768, + "quantization": "fp8" }, { "providerId": "novita", @@ -6257,13 +10084,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 32768, + "quantization": "bf16", "stability": "unstable" } ], @@ -6300,7 +10130,7 @@ "name": "Gemma 4 31B IT", "display_name": "Gemma 4 31B IT", "created": 1775088000, - "description": "gemma-4-31b-it provided by deepinfra, novita, together-ai, cerebras, ranoai, consensusprotocol, runware", + "description": "Large 31B Gemma 4 instruction-tuned model with reasoning.", "family": "google", "architecture": { "input_modalities": ["text", "image"], @@ -6323,13 +10153,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 + "max_output": 32768, + "quantization": "fp8" }, { "providerId": "novita", @@ -6343,13 +10176,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "quantization": "bf16" }, { "providerId": "together-ai", @@ -6363,14 +10199,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2026-09-15T00:00:00.000Z" }, { "providerId": "cerebras", @@ -6384,13 +10223,25 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 + "max_output": 32768, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ], + "deactivated_at": "2026-10-28T00:00:00.000Z" }, { "providerId": "ranoai", @@ -6404,11 +10255,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 20480, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -6419,7 +10272,9 @@ "xhigh", "max" ], - "max_output": 20480 + "max_output": 20480, + "supports_n": true, + "deactivated_at": "2026-08-09T00:00:00.000Z" }, { "providerId": "consensusprotocol", @@ -6433,13 +10288,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["none", "high", "xhigh", "max"], + "reasoning_max_tokens": false, "stability": "stable" }, { @@ -6454,14 +10315,21 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["none", "high", "xhigh", "max"], + "reasoning_max_tokens": false, "max_output": 65536, + "quantization": "bf16", "stability": "stable" } ], @@ -6497,7 +10365,7 @@ "name": "GLM-4 32B (0414-128k)", "display_name": "GLM-4 32B (0414-128k)", "created": 1744588800, - "description": "glm-4-32b-0414-128k provided by zai", + "description": "GLM-4 32B instruction-tuned model.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -6520,11 +10388,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false } ], @@ -6559,7 +10429,7 @@ "name": "GLM-4.5", "display_name": "GLM-4.5", "created": 1753660800, - "description": "glm-4.5 provided by zai, embercloud", + "description": "Zhipu GLM-4.5 with reasoning capabilities.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -6580,36 +10450,19 @@ "request": "0", "input_cache_read": "0.11e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "stability": "unstable" - }, - { - "providerId": "embercloud", - "externalId": "glm-4.5", - "pricing": { - "prompt": "0.6e-6", - "completion": "2.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.11e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 96000, - "stability": "unstable" } ], "pricing": { @@ -6620,27 +10473,19 @@ "input_cache_read": "0.11e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, - "context_length": 131000, - "max_output": 96000, + "context_length": 128000, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", - "logprobs", - "top_logprobs", "tools", - "parallel_tool_calls", + "tool_choice", "reasoning" ], "json_output": true, @@ -6652,7 +10497,7 @@ "name": "GLM-4.5 Air", "display_name": "GLM-4.5 Air", "created": 1753401600, - "description": "glm-4.5-air provided by zai, embercloud", + "description": "Lightweight GLM-4.5 variant.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -6675,34 +10520,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "stability": "unstable" - }, - { - "providerId": "embercloud", - "externalId": "glm-4.5-air", - "pricing": { - "prompt": "0.13e-6", - "completion": "0.85e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.025e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 96000, - "stability": "unstable" } ], "pricing": { @@ -6716,25 +10542,16 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 131000, - "max_output": 96000, + "context_length": 128000, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", - "logprobs", - "top_logprobs", "tools", - "tool_choice", - "parallel_tool_calls" + "tool_choice" ], "json_output": true, "structured_outputs": false, @@ -6745,7 +10562,7 @@ "name": "GLM-4.5 AirX", "display_name": "GLM-4.5 AirX", "created": 1753660800, - "description": "glm-4.5-airx provided by zai", + "description": "Enhanced GLM-4.5 Air variant.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -6768,11 +10585,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "stability": "unstable" } @@ -6808,7 +10627,7 @@ "name": "GLM-4.5 X", "display_name": "GLM-4.5 X", "created": 1753660800, - "description": "glm-4.5-x provided by zai", + "description": "Extended GLM-4.5 with advanced reasoning.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -6831,11 +10650,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "stability": "unstable" } @@ -6872,7 +10693,7 @@ "name": "GLM-4.5V", "display_name": "GLM-4.5V", "created": 1754870400, - "description": "glm-4.5v provided by zai, novita", + "description": "GLM-4.5 with vision support.", "family": "zai", "architecture": { "input_modalities": ["text", "image"], @@ -6895,11 +10716,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 16000 }, @@ -6915,13 +10738,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 65536, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 16000 + "max_output": 16000, + "quantization": "fp8" } ], "pricing": { @@ -6957,7 +10783,7 @@ "name": "GLM-4.6", "display_name": "GLM-4.6", "created": 1759190400, - "description": "glm-4.6 provided by zai, cerebras, alibaba, novita", + "description": "Updated GLM with reasoning capabilities.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -6978,13 +10804,18 @@ "request": "0", "input_cache_read": "0.11e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "web_search": true, "reasoning": true }, { @@ -6999,12 +10830,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": true, + "reasoning": true, + "deactivated_at": "2026-01-20T00:00:00.000Z" }, { "providerId": "alibaba", @@ -7016,15 +10850,63 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.431e-6", + "completion": "2.007e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.574e-6", + "completion": "2.294e-6" + } + ] + }, + "regions": [ + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.431e-6", + "completion": "2.007e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.431e-6", + "completion": "2.007e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.574e-6", + "completion": "2.294e-6" + } + ] + }, + "context_length": 202752, + "max_output": 16384, + "streaming": true + } + ], + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 16384 + "max_output": 16384, + "deactivated_at": "2026-07-08T00:00:00.000Z" }, { "providerId": "novita", @@ -7038,12 +10920,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": true, + "reasoning": true, + "quantization": "bf16" } ], "pricing": { @@ -7078,7 +10963,7 @@ "name": "GLM-4.6V", "display_name": "GLM-4.6V", "created": 1765152000, - "description": "glm-4.6v provided by zai, novita", + "description": "Flagship vision-language model (106B) with native function calling support.", "family": "zai", "architecture": { "input_modalities": ["text", "image"], @@ -7101,11 +10986,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 16000 }, @@ -7121,13 +11008,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 16000 + "max_output": 16000, + "quantization": "bf16" } ], "pricing": { @@ -7163,7 +11053,7 @@ "name": "GLM-4.6V FlashX", "display_name": "GLM-4.6V FlashX", "created": 1765152000, - "description": "glm-4.6v-flashx provided by zai", + "description": "Fast vision-language model with extended capabilities.", "family": "zai", "architecture": { "input_modalities": ["text", "image"], @@ -7186,11 +11076,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 16000 } @@ -7228,7 +11120,7 @@ "name": "GLM-4.7", "display_name": "GLM-4.7", "created": 1766361600, - "description": "glm-4.7 provided by zai, novita, cerebras, bytedance, together-ai, alibaba, embercloud, vertex-openai", + "description": "Latest GLM with enhanced reasoning capabilities.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -7249,13 +11141,17 @@ "request": "0", "input_cache_read": "0.11e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "max_output": 128000 }, @@ -7271,13 +11167,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 128000 + "max_output": 128000, + "quantization": "fp8" }, { "providerId": "cerebras", @@ -7291,13 +11190,24 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ], + "deactivated_at": "2026-10-28T00:00:00.000Z" }, { "providerId": "bytedance", @@ -7311,11 +11221,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "max_output": 128000 }, @@ -7331,11 +11243,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "max_output": 128000 }, @@ -7349,36 +11263,63 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 16384 - }, - { - "providerId": "embercloud", - "externalId": "glm-4.7", - "pricing": { - "prompt": "0.38e-6", - "completion": "1.98e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.19e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.431e-6", + "completion": "2.007e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.574e-6", + "completion": "2.294e-6" + } + ] + }, + "regions": [ + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.431e-6", + "completion": "2.007e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.431e-6", + "completion": "2.007e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.574e-6", + "completion": "2.294e-6" + } + ] + }, + "context_length": 202752, + "max_output": 16384, + "streaming": true + } + ], + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131000, - "stability": "unstable" + "max_output": 16384, + "deactivated_at": "2026-07-08T00:00:00.000Z" }, { "providerId": "vertex-openai", @@ -7392,13 +11333,33 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "0.6e-6", + "completion": "2.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 202752, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 128000 + "max_output": 128000, + "deactivated_at": "2026-10-21T00:00:00.000Z" } ], "pricing": { @@ -7427,88 +11388,12 @@ "structured_outputs": false, "free": false }, - { - "id": "glm-4.7-flash", - "name": "GLM-4.7 Flash", - "display_name": "GLM-4.7 Flash", - "created": 1766361600, - "description": "glm-4.7-flash provided by embercloud", - "family": "zai", - "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "embercloud", - "externalId": "glm-4.7-flash", - "pricing": { - "prompt": "0.06e-6", - "completion": "0.4e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.01e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 131000, - "stability": "unstable" - } - ], - "pricing": { - "prompt": "0.06e-6", - "completion": "0.4e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.01e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 200000, - "max_output": 131000, - "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", - "temperature", - "top_p", - "max_tokens", - "max_completion_tokens", - "seed", - "stop", - "response_format", - "logprobs", - "top_logprobs", - "tools", - "tool_choice", - "parallel_tool_calls" - ], - "json_output": true, - "structured_outputs": false, - "free": false, - "deprecated_at": "2026-10-21T00:00:00.000Z", - "deactivated_at": "2026-10-28T00:00:00.000Z", - "stability": "unstable" - }, { "id": "glm-4.7-flashx", "name": "GLM-4.7 FlashX", "display_name": "GLM-4.7 FlashX", "created": 1766361600, - "description": "glm-4.7-flashx provided by zai", + "description": "Lightweight, high-speed GLM-4.7 variant.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -7531,11 +11416,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 128000, "stability": "unstable" @@ -7574,7 +11461,7 @@ "name": "GLM-5", "display_name": "GLM-5", "created": 1771113600, - "description": "glm-5 provided by zai, together-ai, novita, alibaba, embercloud, nebius, vertex-openai, baidu, tencent", + "description": "Zhipu GLM-5 with advanced reasoning capabilities.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -7595,13 +11482,17 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 202800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "max_output": 131100 }, @@ -7617,13 +11508,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 202752 + "max_output": 202752, + "deactivated_at": "2026-04-22T00:00:00.000Z" }, { "providerId": "novita", @@ -7637,13 +11531,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "quantization": "fp8" }, { "providerId": "alibaba", @@ -7655,13 +11552,60 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.573e-6", + "completion": "2.58e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.86e-6", + "completion": "3.154e-6" + } + ] + }, + "regions": [ + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.573e-6", + "completion": "2.58e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.573e-6", + "completion": "2.58e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.86e-6", + "completion": "3.154e-6" + } + ] + }, + "context_length": 202752, + "max_output": 16384, + "streaming": true + } + ], + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -7671,29 +11615,9 @@ "high", "xhigh" ], + "reasoning_max_tokens": true, "max_output": 16384 }, - { - "providerId": "embercloud", - "externalId": "glm-5", - "pricing": { - "prompt": "0.72e-6", - "completion": "2.3e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.144e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 131000, - "stability": "unstable" - }, { "providerId": "nebius", "externalId": "zai-org/GLM-5", @@ -7706,13 +11630,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2026-06-22T00:00:00.000Z" }, { "providerId": "vertex-openai", @@ -7726,13 +11653,33 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "1e-6", + "completion": "3.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.1e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 202752, + "max_output": 32768, + "streaming": true + } + ], + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2026-10-21T00:00:00.000Z" }, { "providerId": "baidu", @@ -7746,6 +11693,7 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, @@ -7761,7 +11709,8 @@ "xhigh", "max" ], - "max_output": 131072 + "max_output": 131072, + "deactivated_at": "2026-10-19T00:00:00.000Z" }, { "providerId": "tencent", @@ -7775,11 +11724,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -7802,27 +11754,34 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.573e-6", + "completion": "2.58e-6" + }, + { + "name": "Over 32K", + "up_to_tokens": null, + "prompt": "0.86e-6", + "completion": "3.154e-6" + } + ], "internal_reasoning": "0" }, - "context_length": 203000, + "context_length": 202800, "max_output": 16384, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", "tool_choice", - "parallel_tool_calls", - "reasoning", - "reasoning_effort" + "reasoning" ], "json_output": true, "structured_outputs": false, @@ -7833,7 +11792,7 @@ "name": "GLM-5 Turbo", "display_name": "GLM-5 Turbo", "created": 1773532800, - "description": "glm-5-turbo provided by tencent", + "description": "Zhipu's speed-optimised GLM-5 variant with a 200K context window and deep reasoning.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -7856,11 +11815,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 128000 @@ -7899,7 +11861,7 @@ "name": "GLM-5.1", "display_name": "GLM-5.1", "created": 1775520000, - "description": "glm-5.1 provided by zai, novita, together-ai, deepinfra, embercloud, nebius, baidu, tencent", + "description": "Zhipu GLM-5.1 flagship model engineered for long-horizon autonomous tasks with enhanced coding and agentic capabilities.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -7920,13 +11882,17 @@ "request": "0", "input_cache_read": "0.26e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "max_output": 128000 }, @@ -7942,11 +11908,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -7957,7 +11925,8 @@ "xhigh", "max" ], - "max_output": 131072 + "max_output": 131072, + "quantization": "fp8" }, { "providerId": "together-ai", @@ -7971,13 +11940,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 202752 + "max_output": 202752, + "deactivated_at": "2026-07-10T00:00:00.000Z" }, { "providerId": "deepinfra", @@ -7991,34 +11963,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 198000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 65536 - }, - { - "providerId": "embercloud", - "externalId": "glm-5.1", - "pricing": { - "prompt": "0.931e-6", - "completion": "2.93e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.173e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 131000, - "stability": "unstable" + "max_output": 65536, + "quantization": "fp4", + "deactivated_at": "2026-10-01T00:00:00.000Z" }, { "providerId": "nebius", @@ -8032,12 +11987,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": true, + "reasoning": true, + "quantization": "fp8", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "baidu", @@ -8051,11 +12010,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 202752, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -8080,11 +12041,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 128000 @@ -8104,22 +12068,15 @@ "context_length": 204800, "max_output": 128000, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", "tool_choice", - "parallel_tool_calls", - "reasoning", - "reasoning_effort" + "reasoning" ], "json_output": true, "structured_outputs": false, @@ -8130,7 +12087,7 @@ "name": "GLM-5.2", "display_name": "GLM-5.2", "created": 1781308800, - "description": "glm-5.2 provided by zai, novita, canopywave, embercloud, bytedance, alibaba, nebius, baidu, tencent, scx-ai-gp, runware", + "description": "Zhipu GLM-5.2 flagship model for long-horizon coding and agentic engineering tasks with a 1M context window.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -8151,13 +12108,17 @@ "request": "0", "input_cache_read": "0.26e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "high", "max"], "max_output": 128000 @@ -8174,11 +12135,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -8203,34 +12166,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 - }, - { - "providerId": "embercloud", - "externalId": "glm-5.2", - "pricing": { - "prompt": "1.26e-6", - "completion": "3.96e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.234e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 131000, - "stability": "unstable" + "max_output": 32768, + "quantization": "fp8" }, { "providerId": "bytedance", @@ -8244,11 +12189,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1024000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -8273,11 +12220,75 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.28e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.28e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.28e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.28e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -8288,6 +12299,7 @@ "xhigh", "max" ], + "reasoning_max_tokens": true, "max_output": 131072 }, { @@ -8302,12 +12314,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": true, + "reasoning": true, + "quantization": "fp4", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "baidu", @@ -8321,11 +12337,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -8350,11 +12368,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -8367,6 +12388,35 @@ ], "max_output": 128000 }, + { + "providerId": "flexai", + "externalId": "GLM-5.2", + "pricing": { + "prompt": "0.0000007", + "completion": "0.0000022", + "image": "0", + "request": "0", + "input_cache_read": "0.000000105", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.05" + }, + "context_length": 1048576, + "streaming": true, + "vision": false, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["medium", "high", "max"], + "reasoning_max_tokens": false, + "quantization": "fp8", + "stability": "stable" + }, { "providerId": "scx-ai-gp", "externalId": "GLM-5.2", @@ -8379,13 +12429,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, + "reasoning_max_tokens": false, "max_output": 131072, + "quantization": "fp8", "stability": "stable" }, { @@ -8400,11 +12457,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1024000, "streaming": true, "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -8415,7 +12477,9 @@ "xhigh", "max" ], + "reasoning_max_tokens": false, "max_output": 128000, + "quantization": "fp4", "stability": "stable" } ], @@ -8433,25 +12497,18 @@ "context_length": 1048576, "max_output": 32768, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", "tool_choice", - "parallel_tool_calls", - "reasoning", - "reasoning_effort" + "reasoning" ], "json_output": true, - "structured_outputs": false, + "structured_outputs": true, "free": false }, { @@ -8460,7 +12517,7 @@ "display_name": "GLM-5.2 Turbo", "aliases": [], "created": 1786924800, - "description": "glm-5.2-fast provided by scx-ai-gp", + "description": "Zhipu GLM-5.2 Turbo variant for long-horizon coding and agentic engineering tasks with a 1M context window.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -8483,12 +12540,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, + "reasoning_max_tokens": false, "max_output": 131072, "stability": "stable" } @@ -8520,6 +12583,7 @@ "json_output": true, "structured_outputs": false, "free": false, + "image_input_required": false, "stability": "stable" }, { @@ -8527,7 +12591,7 @@ "name": "GLM-5.3", "display_name": "GLM-5.3", "created": 1786665600, - "description": "glm-5.3 provided by zai, novita, baidu, alibaba, fireworks, inference.net, mistral, deepinfra, together-ai, entrim, runware, reka-ai, scx-ai-gp", + "description": "Zhipu GLM-5.3 flagship coding model, post-trained on the GLM-5.2 base with stronger agentic coding and emergent cybersecurity capabilities and a 1M context window.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -8539,10 +12603,35 @@ }, "providers": [ { - "providerId": "zai", + "providerId": "runpod", "externalId": "glm-5.3", "pricing": { - "prompt": "1.4e-6", + "prompt": "0.77e-6", + "completion": "2.42e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.143e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "streaming": true, + "vision": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 131072 + }, + { + "providerId": "tencent", + "externalId": "glm-5.3", + "pricing": { + "prompt": "1.4e-6", "completion": "4.4e-6", "image": "0", "request": "0", @@ -8550,11 +12639,40 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, + "streaming": true, + "vision": false, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 128000 + }, + { + "providerId": "zai", + "externalId": "glm-5.3", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.26e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], "max_output": 128000 @@ -8569,15 +12687,30 @@ "request": "0", "input_cache_read": "0.26e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "discount": "0.2000" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice", + "response_format" + ] }, { "providerId": "baidu", @@ -8591,11 +12724,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], "max_output": 131072 @@ -8612,14 +12747,65 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.28e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 131072, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "1.131e-6", + "completion": "3.957e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2262e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 131072, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "1.131e-6", + "completion": "3.957e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2262e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 131072, + "streaming": true + } + ], + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1 }, { "providerId": "fireworks", @@ -8633,14 +12819,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.25, + "description": "Queue precedence over standard traffic and protection from load shedding during congestion, at a 25% premium." + } + ], + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["xhigh", "max"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1 }, { "providerId": "inference.net", @@ -8654,14 +12852,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1, + "quantization": "fp4" }, { "providerId": "mistral", @@ -8675,14 +12879,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1 }, { "providerId": "deepinfra", @@ -8696,14 +12905,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "high", "max"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1, + "quantization": "fp4", + "deactivated_at": "2026-09-23T00:00:00.000Z" }, { "providerId": "together-ai", @@ -8717,14 +12932,44 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, + "streaming": true, + "vision": false, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["low", "high", "max"], + "max_output": 943717, + "max_temperature": 1 + }, + { + "providerId": "cloudflare", + "externalId": "@cf/zai-org/glm-5.3", + "pricing": { + "prompt": "1.4e-6", + "completion": "4.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.26e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 943717 + "max_output": 131072, + "max_temperature": 1 }, { "providerId": "entrim", @@ -8736,15 +12981,23 @@ "request": "0", "input_cache_read": "0.00000015", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "discount": "0.1" }, + "context_length": 1048576, "streaming": true, "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": false, + "quantization": "fp4", "stability": "stable" }, { @@ -8759,13 +13012,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], + "reasoning_max_tokens": false, "max_output": 131072, "stability": "stable" }, @@ -8773,19 +13032,24 @@ "providerId": "reka-ai", "externalId": "glm5.3", "pricing": { - "prompt": "0.00000117", - "completion": "0.00000396", + "prompt": "0.00000045", + "completion": "0.0000018", "image": "0", "request": "0", - "input_cache_read": "0.000000234", + "input_cache_read": "0.000000135", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -8796,7 +13060,9 @@ "xhigh", "max" ], + "reasoning_max_tokens": false, "max_output": 262144, + "quantization": "fp8", "stability": "stable" }, { @@ -8811,13 +13077,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], + "reasoning_max_tokens": false, "max_output": 128000, "stability": "stable" } @@ -8831,6 +13103,7 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "discount": "0.1", "internal_reasoning": "0" }, "context_length": 1048576, @@ -8858,7 +13131,7 @@ "display_name": "GLM 5.3 Fast", "aliases": [], "created": 1791353600, - "description": "glm-5.3-fast provided by scx-ai-gp", + "description": "GLM-5.3-Prime is a faster version of GLM-5.3. It keeps all of the original model's capabilities while generating output 1.5 to 2 times faster, thanks to inference acceleration.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -8881,12 +13154,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": false, + "reasoning_max_tokens": false, "max_output": 128000, "stability": "stable" } @@ -8917,6 +13196,7 @@ "json_output": false, "structured_outputs": false, "free": false, + "image_input_required": false, "stability": "stable" }, { @@ -8924,7 +13204,7 @@ "name": "GLM-5.3 Flash", "display_name": "GLM-5.3 Flash", "created": 1787702400, - "description": "glm-5.3-flash provided by zai, novita, fireworks, inference.net, together-ai, entrim, greenference, reka-ai, consensusprotocol, runware, scx-ai-gp", + "description": "Lightweight GLM-5.3 variant for efficient coding and long-horizon agent tasks with a 1M context window.", "family": "zai", "architecture": { "input_modalities": ["text", "image"], @@ -8935,6 +13215,32 @@ "is_moderated": true }, "providers": [ + { + "providerId": "tencent", + "externalId": "glm-5.3-flash", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.50e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.03e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["xhigh", "max"], + "max_output": 131072, + "max_temperature": 1 + }, { "providerId": "zai", "externalId": "glm-5.3-flash", @@ -8947,14 +13253,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "required", "function"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 131072 + "max_output": 131072, + "quantization": "fp8" }, { "providerId": "novita", @@ -8966,16 +13276,21 @@ "request": "0", "input_cache_read": "0.03e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "discount": "0.1000" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 131072 + "max_output": 131072, + "quantization": "fp8" }, { "providerId": "fireworks", @@ -8989,15 +13304,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["xhigh", "max"], "min_cacheable_tokens": 2048, - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1 }, { "providerId": "inference.net", @@ -9011,14 +13330,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 128000 + "max_output": 128000, + "max_temperature": 1, + "quantization": "fp4" }, { "providerId": "together-ai", @@ -9032,14 +13357,70 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["low", "high", "max"], + "max_output": 943717, + "max_temperature": 1 + }, + { + "providerId": "baidu", + "externalId": "glm-5.3-flash-intl", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.03e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["xhigh", "max"], + "max_output": 131072, + "max_temperature": 1, + "quantization": "fp8" + }, + { + "providerId": "cloudflare", + "externalId": "@cf/zai-org/glm-5.3-flash", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.03e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 943717 + "max_output": 131072, + "max_temperature": 1 }, { "providerId": "entrim", @@ -9051,15 +13432,52 @@ "request": "0", "input_cache_read": "0.0000000175", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "discount": "0.1" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "reasoning_max_tokens": false, + "quantization": "fp4", + "stability": "stable" + }, + { + "providerId": "flexai", + "externalId": "GLM-5.3-Flash", + "pricing": { + "prompt": "0.00000008", + "completion": "0.0000005", + "image": "0", + "request": "0", + "input_cache_read": "0.000000012", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.05" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_efforts": ["medium", "high", "max", "minimal", "low"], + "reasoning_max_tokens": false, + "quantization": "fp8", "stability": "stable" }, { @@ -9072,35 +13490,48 @@ "request": "0", "input_cache_read": "0.000000028", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "discount": "0.3" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": false, "max_output": 131072, + "quantization": "fp8", "stability": "stable" }, { "providerId": "reka-ai", "externalId": "glm5.3-flash", "pricing": { - "prompt": "0.00000015", - "completion": "0.0000005", + "prompt": "0.00000011", + "completion": "0.00000033", "image": "0", "request": "0", - "input_cache_read": "0.00000002", + "input_cache_read": "0.000000027", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -9111,7 +13542,9 @@ "xhigh", "max" ], + "reasoning_max_tokens": false, "max_output": 262144, + "quantization": "fp8", "stability": "stable" }, { @@ -9126,13 +13559,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], + "reasoning_max_tokens": false, "stability": "stable" }, { @@ -9147,11 +13586,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -9162,6 +13606,7 @@ "xhigh", "max" ], + "reasoning_max_tokens": false, "max_output": 131072, "stability": "stable" }, @@ -9177,14 +13622,21 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], + "reasoning_max_tokens": false, "max_output": 131072, + "quantization": "fp8", "stability": "stable" } ], @@ -9216,12 +13668,83 @@ "structured_outputs": true, "free": false }, + { + "id": "glm-5.3-flashx", + "name": "GLM-5.3 FlashX", + "display_name": "GLM-5.3 FlashX", + "created": 1789689600, + "description": "Multimodal GLM-5.3 FlashX model with reasoning, tool calling, and a 1M-token context window.", + "family": "zai", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "tencent", + "externalId": "glm-5.3-flashx", + "pricing": { + "prompt": "0.37e-6", + "completion": "1.25e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.075e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["xhigh", "max"], + "max_output": 131072, + "max_temperature": 1 + } + ], + "pricing": { + "prompt": "0.37e-6", + "completion": "1.25e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.075e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, { "id": "glm-5v-turbo", "name": "GLM-5V Turbo", "display_name": "GLM-5V Turbo", "created": 1775001600, - "description": "glm-5v-turbo provided by tencent", + "description": "Zhipu's speed-optimised multimodal GLM-5 variant that accepts image input alongside text, with a 200K context window.", "family": "zai", "architecture": { "input_modalities": ["text", "image"], @@ -9244,11 +13767,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 128000 @@ -9287,7 +13813,7 @@ "name": "GLM-Image", "display_name": "GLM-Image", "created": 1736812800, - "description": "glm-image provided by zai", + "description": "Z.AI's GLM-Image text-to-image generation model with hybrid auto-regressive architecture, excellent for text-rendering and knowledge-intensive generation.", "family": "zai", "architecture": { "input_modalities": ["text"], @@ -9310,11 +13836,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -9347,14 +13875,14 @@ "free": false }, { - "id": "gpt-3.5-turbo", - "name": "GPT-3.5 Turbo", - "display_name": "GPT-3.5 Turbo", - "created": 1669766400, - "description": "gpt-3.5-turbo provided by openai, azure", + "id": "gpt-4.1", + "name": "GPT-4.1", + "display_name": "GPT-4.1", + "created": 1744588800, + "description": "Updated GPT-4 with vision support and parallel tool calls.", "family": "openai", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -9364,56 +13892,71 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-3.5-turbo", + "externalId": "gpt-4.1", "pricing": { - "prompt": "0.5e-6", - "completion": "1.5e-6", + "prompt": "2.0e-6", + "completion": "8.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.5e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, - "parallelToolCalls": false, - "reasoning": false + "parallelToolCalls": true, + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "supports_n": true }, { "providerId": "azure", - "externalId": "gpt-35-turbo", + "externalId": "gpt-4.1", "pricing": { - "prompt": "0.5e-6", - "completion": "1.5e-6", + "prompt": "2.0e-6", + "completion": "8.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.5e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.75, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 1000000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, - "parallelToolCalls": false, + "parallelToolCalls": true, + "json_output": true, + "structured_outputs": true, "reasoning": false, - "max_output": 4096 + "deactivated_at": "2027-04-14T00:00:00.000Z" } ], "pricing": { - "prompt": "0.5e-6", - "completion": "1.5e-6", + "prompt": "2.0e-6", + "completion": "8.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.5e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 16385, + "context_length": 1000000, "supported_parameters": [ "temperature", "max_tokens", @@ -9425,19 +13968,18 @@ "tool_choice" ], "json_output": true, - "structured_outputs": false, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "structured_outputs": true, + "free": false }, { - "id": "gpt-4", - "name": "GPT-4", - "display_name": "GPT-4", - "created": 1678752000, - "description": "gpt-4 provided by openai, azure", + "id": "gpt-4.1-mini", + "name": "GPT-4.1 Mini", + "display_name": "GPT-4.1 Mini", + "created": 1744588800, + "description": "Compact version of GPT-4.1 with vision and tool support.", "family": "openai", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -9447,58 +13989,63 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4", + "externalId": "gpt-4.1-mini", "pricing": { - "prompt": "30.0e-6", - "completion": "60.0e-6", + "prompt": "0.4e-6", + "completion": "1.6e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.1e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, - "parallelToolCalls": false, + "parallelToolCalls": true, + "json_output": true, + "structured_outputs": true, "reasoning": false, - "max_output": 8192 + "supports_n": true }, { "providerId": "azure", - "externalId": "gpt-4", + "externalId": "gpt-4.1-mini", "pricing": { - "prompt": "30.0e-6", - "completion": "60.0e-6", + "prompt": "0.4e-6", + "completion": "1.6e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.1e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, - "parallelToolCalls": false, + "parallelToolCalls": true, + "json_output": true, + "structured_outputs": true, "reasoning": false, - "max_output": 8192 + "deactivated_at": "2027-04-14T00:00:00.000Z" } ], "pricing": { - "prompt": "30.0e-6", - "completion": "60.0e-6", + "prompt": "0.4e-6", + "completion": "1.6e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.1e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 8192, - "max_output": 8192, + "context_length": 1000000, "supported_parameters": [ "temperature", "max_tokens", @@ -9509,17 +14056,16 @@ "tools", "tool_choice" ], - "json_output": false, - "structured_outputs": false, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "json_output": true, + "structured_outputs": true, + "free": false }, { - "id": "gpt-4-turbo", - "name": "GPT-4 Turbo", - "display_name": "GPT-4 Turbo", - "created": 1699228800, - "description": "gpt-4-turbo provided by openai, azure", + "id": "gpt-4o", + "name": "GPT-4o", + "display_name": "GPT-4o", + "created": 1715558400, + "description": "Multimodal flagship model with vision, fast responses, and tool support.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -9532,56 +14078,66 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4-turbo", + "externalId": "gpt-4o", "pricing": { - "prompt": "10.0e-6", - "completion": "30.0e-6", - "image": "0", + "prompt": "2.5e-6", + "completion": "10.0e-6", + "image": "0.00553", "request": "0", - "input_cache_read": "0", + "input_cache_read": "1.25e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "structured_outputs": true, + "web_search": true, + "reasoning": false, + "max_output": 16384, + "supports_n": true }, { "providerId": "azure", - "externalId": "gpt-4-turbo", + "externalId": "gpt-4o", "pricing": { - "prompt": "10.0e-6", - "completion": "30.0e-6", - "image": "0", + "prompt": "2.5e-6", + "completion": "10.0e-6", + "image": "0.00553", "request": "0", - "input_cache_read": "0", + "input_cache_read": "1.25e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 4096 + "max_output": 16384, + "deactivated_at": "2027-04-14T00:00:00.000Z" } ], "pricing": { - "prompt": "10.0e-6", - "completion": "30.0e-6", - "image": "0", + "prompt": "2.5e-6", + "completion": "10.0e-6", + "image": "0.00553", "request": "0", - "input_cache_read": "0", + "input_cache_read": "1.25e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, "context_length": 128000, + "max_output": 16384, "supported_parameters": [ "temperature", "max_tokens", @@ -9594,15 +14150,14 @@ ], "json_output": true, "structured_outputs": true, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "free": false }, { - "id": "gpt-4.1", - "name": "GPT-4.1", - "display_name": "GPT-4.1", - "created": 1744588800, - "description": "gpt-4.1 provided by openai, azure", + "id": "gpt-4o-mini", + "name": "GPT-4o Mini", + "display_name": "GPT-4o Mini", + "created": 1721260800, + "description": "Affordable small model for fast, lightweight tasks with text and vision capabilities.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -9615,55 +14170,67 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4.1", + "externalId": "gpt-4o-mini", "pricing": { - "prompt": "2.0e-6", - "completion": "8.0e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", + "input_cache_read": "0.075e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, - "parallelToolCalls": true, - "reasoning": false + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "max_output": 16384, + "supports_n": true }, { "providerId": "azure", - "externalId": "gpt-4.1", + "externalId": "gpt-4o-mini", "pricing": { - "prompt": "2.0e-6", - "completion": "8.0e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", + "input_cache_read": "0.075e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, - "parallelToolCalls": true, - "reasoning": false + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "max_output": 16384, + "deprecated_at": "2026-01-09T00:00:00.000Z", + "deactivated_at": "2026-03-31T00:00:00.000Z" } ], "pricing": { - "prompt": "2.0e-6", - "completion": "8.0e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", + "input_cache_read": "0.075e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1000000, + "context_length": 128000, + "max_output": 16384, "supported_parameters": [ "temperature", "max_tokens", @@ -9679,14 +14246,14 @@ "free": false }, { - "id": "gpt-4.1-mini", - "name": "GPT-4.1 Mini", - "display_name": "GPT-4.1 Mini", - "created": 1744588800, - "description": "gpt-4.1-mini provided by openai, azure", + "id": "gpt-4o-mini-transcribe", + "name": "GPT-4o Mini Transcribe", + "display_name": "GPT-4o Mini Transcribe", + "created": 1742428800, + "description": "Cost-efficient token-metered OpenAI speech-to-text model. Used as the default input-audio transcription model for realtime sessions on the gateway's /v1/realtime WebSocket endpoint.", "family": "openai", "architecture": { - "input_modalities": ["text", "image"], + "input_modalities": ["text", "audio"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -9696,55 +14263,44 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4.1-mini", - "pricing": { - "prompt": "0.4e-6", - "completion": "1.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.1e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": true, - "reasoning": false - }, - { - "providerId": "azure", - "externalId": "gpt-4.1-mini", + "externalId": "gpt-4o-mini-transcribe", "pricing": { - "prompt": "0.4e-6", - "completion": "1.6e-6", + "prompt": "1.25e-6", + "completion": "5.0e-6", "image": "0", + "input_audio": "3.0e-6", "request": "0", - "input_cache_read": "0.1e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": true, + "context_length": 16000, + "streaming": false, + "vision": false, + "audio": true, "cancellation": true, - "tools": true, - "parallelToolCalls": true, - "reasoning": false + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false, + "max_output": 2000, + "stability": "beta" } ], "pricing": { - "prompt": "0.4e-6", - "completion": "1.6e-6", + "prompt": "1.25e-6", + "completion": "5.0e-6", "image": "0", + "input_audio": "3.0e-6", "request": "0", - "input_cache_read": "0.1e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1000000, + "context_length": 16000, + "max_output": 2000, "supported_parameters": [ "temperature", "max_tokens", @@ -9755,20 +14311,21 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, - "free": false + "json_output": false, + "structured_outputs": false, + "free": false, + "stability": "beta" }, { - "id": "gpt-4.1-nano", - "name": "GPT-4.1 Nano", - "display_name": "GPT-4.1 Nano", - "created": 1744588800, - "description": "gpt-4.1-nano provided by openai, azure", + "id": "gpt-4o-mini-tts", + "name": "GPT-4o Mini TTS", + "display_name": "GPT-4o Mini TTS", + "created": 1742428800, + "description": "OpenAI text-to-speech model with steerable delivery via instructions. Generates speech via the /v1/audio/speech endpoint.", "family": "openai", "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], + "input_modalities": ["text"], + "output_modalities": ["audio"], "tokenizer": "GPT" }, "top_provider": { @@ -9777,55 +14334,56 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4.1-nano", - "pricing": { - "prompt": "0.1e-6", - "completion": "0.4e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.025e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": true, - "reasoning": false - }, - { - "providerId": "azure", - "externalId": "gpt-4.1-nano", + "externalId": "gpt-4o-mini-tts", "pricing": { - "prompt": "0.1e-6", - "completion": "0.4e-6", + "prompt": "0.6e-6", + "completion": "12.0e-6", "image": "0", + "output_audio": "12.0e-6", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": true, + "context_length": 2000, + "streaming": false, + "vision": false, "cancellation": true, - "tools": true, - "parallelToolCalls": true, - "reasoning": false + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false, + "supported_voices": [ + "alloy", + "ash", + "ballad", + "cedar", + "coral", + "echo", + "fable", + "marin", + "nova", + "onyx", + "sage", + "shimmer", + "verse" + ], + "deactivated_at": "2027-01-06T00:00:00.000Z" } ], "pricing": { - "prompt": "0.1e-6", - "completion": "0.4e-6", + "prompt": "0.6e-6", + "completion": "12.0e-6", "image": "0", + "output_audio": "12.0e-6", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1000000, + "context_length": 2000, "supported_parameters": [ "temperature", "max_tokens", @@ -9836,20 +14394,20 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, + "json_output": false, + "structured_outputs": false, "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "deactivated_at": "2027-01-06T00:00:00.000Z" }, { - "id": "gpt-4o", - "name": "GPT-4o", - "display_name": "GPT-4o", - "created": 1715558400, - "description": "gpt-4o provided by openai, azure", + "id": "gpt-4o-transcribe", + "name": "GPT-4o Transcribe", + "display_name": "GPT-4o Transcribe", + "created": 1742428800, + "description": "Token-metered OpenAI speech-to-text model. Used as the input-audio transcription model for realtime sessions on the gateway's /v1/realtime WebSocket endpoint.", "family": "openai", "architecture": { - "input_modalities": ["text", "image"], + "input_modalities": ["text", "audio"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -9859,58 +14417,44 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4o", - "pricing": { - "prompt": "2.5e-6", - "completion": "10.0e-6", - "image": "0.00553", - "request": "0", - "input_cache_read": "1.25e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 16384 - }, - { - "providerId": "azure", - "externalId": "gpt-4o", + "externalId": "gpt-4o-transcribe", "pricing": { "prompt": "2.5e-6", "completion": "10.0e-6", - "image": "0.00553", + "image": "0", + "input_audio": "6.0e-6", "request": "0", - "input_cache_read": "1.25e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": true, + "context_length": 16000, + "streaming": false, + "vision": false, + "audio": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 16384 + "max_output": 2000, + "stability": "beta" } ], "pricing": { "prompt": "2.5e-6", "completion": "10.0e-6", - "image": "0.00553", + "image": "0", + "input_audio": "6.0e-6", "request": "0", - "input_cache_read": "1.25e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 128000, - "max_output": 16384, + "context_length": 16000, + "max_output": 2000, "supported_parameters": [ "temperature", "max_tokens", @@ -9921,16 +14465,17 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, - "free": false + "json_output": false, + "structured_outputs": false, + "free": false, + "stability": "beta" }, { - "id": "gpt-4o-mini", - "name": "GPT-4o Mini", - "display_name": "GPT-4o Mini", - "created": 1721260800, - "description": "gpt-4o-mini provided by openai, azure", + "id": "gpt-5", + "name": "GPT-5", + "display_name": "GPT-5", + "created": 1754006400, + "description": "Latest flagship model with reasoning, vision, and enhanced capabilities.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -9943,81 +14488,115 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4o-mini", + "externalId": "gpt-5", "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", + "prompt": "1.25e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.075e-6", + "input_cache_read": "0.125e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 16384 + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice", + "verbosity" + ], + "deactivated_at": "2026-12-10T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-4o-mini", + "externalId": "gpt-5", "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", + "prompt": "1.25e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.075e-6", + "input_cache_read": "0.125e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 16384 + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "deactivated_at": "2027-02-09T00:00:00.000Z" } ], "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", + "prompt": "1.25e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.075e-6", + "input_cache_read": "0.125e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, - "context_length": 128000, - "max_output": 16384, + "context_length": 400000, + "max_output": 128000, "supported_parameters": [ "temperature", - "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "verbosity", + "reasoning" ], "json_output": true, "structured_outputs": true, - "free": false + "free": false, + "deactivated_at": "2027-02-09T00:00:00.000Z" }, { - "id": "gpt-4o-mini-transcribe", - "name": "GPT-4o Mini Transcribe", - "display_name": "GPT-4o Mini Transcribe", - "created": 1742428800, - "description": "gpt-4o-mini-transcribe provided by openai", + "id": "gpt-5-mini", + "name": "GPT-5 Mini", + "display_name": "GPT-5 Mini", + "created": 1754006400, + "description": "Compact GPT-5 variant with reasoning and vision at reduced cost.", "family": "openai", "architecture": { - "input_modalities": ["text", "audio"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -10027,66 +14606,116 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4o-mini-transcribe", + "externalId": "gpt-5-mini", "pricing": { - "prompt": "1.25e-6", - "completion": "5.0e-6", + "prompt": "0.25e-6", + "completion": "2e-6", "image": "0", - "input_audio": "3.0e-6", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.025e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 400000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice", + "verbosity" + ], + "deactivated_at": "2026-12-10T00:00:00.000Z" + }, + { + "providerId": "azure", + "externalId": "gpt-5-mini", + "pricing": { + "prompt": "0.25e-6", + "completion": "2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.025e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": false, + "context_length": 400000, + "streaming": true, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 2000, - "stability": "beta" + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "deactivated_at": "2027-02-09T00:00:00.000Z" } ], "pricing": { - "prompt": "1.25e-6", - "completion": "5.0e-6", + "prompt": "0.25e-6", + "completion": "2e-6", "image": "0", - "input_audio": "3.0e-6", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.025e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, - "context_length": 16000, - "max_output": 2000, + "context_length": 400000, + "max_output": 128000, "supported_parameters": [ "temperature", - "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "verbosity", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false, - "stability": "beta" + "deactivated_at": "2027-02-09T00:00:00.000Z" }, { - "id": "gpt-4o-mini-tts", - "name": "GPT-4o Mini TTS", - "display_name": "GPT-4o Mini TTS", - "created": 1742428800, - "description": "gpt-4o-mini-tts provided by openai", + "id": "gpt-5-nano", + "name": "GPT-5 Nano", + "display_name": "GPT-5 Nano", + "created": 1754006400, + "description": "Ultra-efficient GPT-5 variant for high-volume applications with reasoning support.", "family": "openai", "architecture": { "input_modalities": ["text"], - "output_modalities": ["audio"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -10095,127 +14724,112 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-4o-mini-tts", + "externalId": "gpt-5-nano", "pricing": { - "prompt": "0.6e-6", - "completion": "12.0e-6", + "prompt": "0.05e-6", + "completion": "0.4e-6", "image": "0", - "output_audio": "12.0e-6", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.005e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, - "streaming": false, + "context_length": 400000, + "streaming": true, "vision": false, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.6e-6", - "completion": "12.0e-6", - "image": "0", - "output_audio": "12.0e-6", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 2000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": false, - "structured_outputs": false, - "free": false, - "deactivated_at": "2027-01-06T00:00:00.000Z" - }, - { - "id": "gpt-4o-transcribe", - "name": "GPT-4o Transcribe", - "display_name": "GPT-4o Transcribe", - "created": 1742428800, - "description": "gpt-4o-transcribe provided by openai", - "family": "openai", - "architecture": { - "input_modalities": ["text", "audio"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice", + "verbosity" + ], + "deactivated_at": "2026-12-10T00:00:00.000Z" + }, { - "providerId": "openai", - "externalId": "gpt-4o-transcribe", + "providerId": "azure", + "externalId": "gpt-5-nano", "pricing": { - "prompt": "2.5e-6", - "completion": "10.0e-6", + "prompt": "0.05e-6", + "completion": "0.4e-6", "image": "0", - "input_audio": "6.0e-6", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.005e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 400000, + "streaming": true, "vision": false, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 2000, - "stability": "beta" + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "deactivated_at": "2027-02-09T00:00:00.000Z" } ], "pricing": { - "prompt": "2.5e-6", - "completion": "10.0e-6", + "prompt": "0.05e-6", + "completion": "0.4e-6", "image": "0", - "input_audio": "6.0e-6", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.005e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, - "context_length": 16000, - "max_output": 2000, + "context_length": 400000, + "max_output": 128000, "supported_parameters": [ "temperature", - "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "verbosity", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false, - "stability": "beta" + "deactivated_at": "2027-02-09T00:00:00.000Z" }, { - "id": "gpt-5", - "name": "GPT-5", - "display_name": "GPT-5", + "id": "gpt-5-pro", + "name": "GPT-5 Pro", + "display_name": "GPT-5 Pro", "created": 1754006400, - "description": "gpt-5 provided by openai, azure", + "description": "Premium GPT-5 tier with extended output limits and advanced reasoning for complex tasks.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10228,82 +14842,95 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5", + "externalId": "gpt-5-pro", "pricing": { - "prompt": "1.25e-6", - "completion": "10.0e-6", + "prompt": "15e-6", + "completion": "120.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.125e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 128000 + "reasoning_efforts": ["high"], + "max_output": 272000, + "deactivated_at": "2026-12-10T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-5", + "externalId": "gpt-5-pro", "pricing": { - "prompt": "1.25e-6", - "completion": "10.0e-6", + "prompt": "15e-6", + "completion": "120e-6", "image": "0", "request": "0", - "input_cache_read": "0.125e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"], + "reasoning_efforts": ["high"], "max_output": 128000 } ], "pricing": { - "prompt": "1.25e-6", - "completion": "10.0e-6", + "prompt": "15e-6", + "completion": "120.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.125e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, "max_output": 128000, "supported_parameters": [ "temperature", + "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", "tools", "tool_choice", - "verbosity", "reasoning" ], "json_output": true, "structured_outputs": true, - "free": false, - "deactivated_at": "2027-02-09T00:00:00.000Z" + "free": false }, { - "id": "gpt-5-mini", - "name": "GPT-5 Mini", - "display_name": "GPT-5 Mini", - "created": 1754006400, - "description": "gpt-5-mini provided by openai, azure", + "id": "gpt-5.1", + "name": "GPT-5.1", + "display_name": "GPT-5.1", + "created": 1761955200, + "description": "Iterative improvement on GPT-5 with enhanced reasoning and tool support.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10316,56 +14943,118 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5-mini", + "externalId": "gpt-5.1", "pricing": { - "prompt": "0.25e-6", - "completion": "2e-6", + "prompt": "1.25e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0.125e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 128000 + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh" + ], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ], + "deactivated_at": "2027-04-01T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-5-mini", + "externalId": "gpt-5.1", "pricing": { - "prompt": "0.25e-6", - "completion": "2e-6", + "prompt": "1.25e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0.125e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 128000 + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh" + ], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format" + ], + "deactivated_at": "2027-05-15T00:00:00.000Z" } ], "pricing": { - "prompt": "0.25e-6", - "completion": "2e-6", + "prompt": "1.25e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0.125e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, @@ -10376,25 +15065,23 @@ "frequency_penalty", "presence_penalty", "response_format", - "tools", - "tool_choice", "verbosity", "reasoning" ], "json_output": true, "structured_outputs": true, "free": false, - "deactivated_at": "2027-02-09T00:00:00.000Z" + "deactivated_at": "2027-05-15T00:00:00.000Z" }, { - "id": "gpt-5-nano", - "name": "GPT-5 Nano", - "display_name": "GPT-5 Nano", - "created": 1754006400, - "description": "gpt-5-nano provided by openai, azure", + "id": "gpt-5.1-codex", + "name": "GPT-5.1 Codex", + "display_name": "GPT-5.1 Codex", + "created": 1762992000, + "description": "GPT-5.1 specialized for code generation and software development tasks.", "family": "openai", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -10404,82 +15091,98 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5-nano", + "externalId": "gpt-5.1-codex", "pricing": { - "prompt": "0.05e-6", - "completion": "0.4e-6", + "prompt": "1.25e-6", + "completion": "10e-6", "image": "0", "request": "0", - "input_cache_read": "0.005e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 400000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 128000 + "max_output": 272000, + "deactivated_at": "2026-07-23T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-5-nano", + "externalId": "gpt-5.1-codex", "pricing": { - "prompt": "0.05e-6", - "completion": "0.4e-6", + "prompt": "1.25e-6", + "completion": "10e-6", "image": "0", "request": "0", - "input_cache_read": "0.005e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 400000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"], - "max_output": 128000 + "max_output": 272000, + "deactivated_at": "2027-05-15T00:00:00.000Z" } ], "pricing": { - "prompt": "0.05e-6", - "completion": "0.4e-6", + "prompt": "1.25e-6", + "completion": "10e-6", "image": "0", "request": "0", - "input_cache_read": "0.005e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, "context_length": 400000, - "max_output": 128000, + "max_output": 272000, "supported_parameters": [ "temperature", + "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", "tools", "tool_choice", - "verbosity", "reasoning" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false, - "deactivated_at": "2027-02-09T00:00:00.000Z" + "deactivated_at": "2027-05-15T00:00:00.000Z" }, { - "id": "gpt-5-pro", - "name": "GPT-5 Pro", - "display_name": "GPT-5 Pro", - "created": 1754006400, - "description": "gpt-5-pro provided by openai", + "id": "gpt-5.1-codex-mini", + "name": "GPT-5.1 Codex mini", + "display_name": "GPT-5.1 Codex mini", + "created": 1762905600, + "description": "Lightweight code-focused model for efficient software development workflows.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10492,39 +15195,68 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5-pro", + "externalId": "gpt-5.1-codex-mini", "pricing": { - "prompt": "15e-6", - "completion": "120.0e-6", + "prompt": "0.25e-6", + "completion": "2e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.025e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 400000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, + "reasoning": true, + "max_output": 128000, + "deactivated_at": "2026-07-23T00:00:00.000Z" + }, + { + "providerId": "azure", + "externalId": "gpt-5.1-codex-mini", + "pricing": { + "prompt": "0.25e-6", + "completion": "2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.025e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, - "reasoning_efforts": ["high"], - "max_output": 272000 + "max_output": 128000, + "deactivated_at": "2027-05-15T00:00:00.000Z" } ], "pricing": { - "prompt": "15e-6", - "completion": "120.0e-6", + "prompt": "0.25e-6", + "completion": "2e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.025e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, "context_length": 400000, - "max_output": 272000, + "max_output": 128000, "supported_parameters": [ "temperature", "max_tokens", @@ -10537,16 +15269,16 @@ "reasoning" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false, - "deactivated_at": "2026-12-10T00:00:00.000Z" + "deactivated_at": "2027-05-15T00:00:00.000Z" }, { - "id": "gpt-5.1", - "name": "GPT-5.1", - "display_name": "GPT-5.1", - "created": 1761955200, - "description": "gpt-5.1 provided by openai, azure", + "id": "gpt-5.2", + "name": "GPT-5.2", + "display_name": "GPT-5.2", + "created": 1765411200, + "description": "Latest GPT-5 model with enhanced reasoning and tool support.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10559,70 +15291,103 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.1", + "externalId": "gpt-5.2", "pricing": { - "prompt": "1.25e-6", - "completion": "10.0e-6", + "prompt": "1.75e-6", + "completion": "14.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.125e-6", + "input_cache_read": "0.175e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": [ - "none", - "minimal", - "low", - "medium", - "high", - "xhigh" - ], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ] }, { "providerId": "azure", - "externalId": "gpt-5.1", + "externalId": "gpt-5.2", "pricing": { - "prompt": "1.25e-6", - "completion": "10.0e-6", + "prompt": "1.75e-6", + "completion": "14.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.125e-6", + "input_cache_read": "0.175e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": [ - "none", - "minimal", - "low", - "medium", - "high", - "xhigh" + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format" ], - "max_output": 128000 + "deactivated_at": "2027-06-08T00:00:00.000Z" } ], "pricing": { - "prompt": "1.25e-6", - "completion": "10.0e-6", + "prompt": "1.75e-6", + "completion": "14.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.125e-6", + "input_cache_read": "0.175e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, @@ -10638,15 +15403,14 @@ ], "json_output": true, "structured_outputs": true, - "free": false, - "deactivated_at": "2027-05-15T00:00:00.000Z" + "free": false }, { - "id": "gpt-5.1-codex", - "name": "GPT-5.1 Codex", - "display_name": "GPT-5.1 Codex", - "created": 1762992000, - "description": "gpt-5.1-codex provided by openai, azure", + "id": "gpt-5.2-codex", + "name": "GPT-5.2 Codex", + "display_name": "GPT-5.2 Codex", + "created": 1768348800, + "description": "Upgraded codex model optimized for software engineering and agentic coding workflows with steerable reasoning.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10659,58 +15423,70 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.1-codex", + "externalId": "gpt-5.2-codex", "pricing": { - "prompt": "1.25e-6", - "completion": "10e-6", + "prompt": "1.75e-6", + "completion": "14.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.175e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, "reasoning": true, - "max_output": 272000 + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2026-07-23T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-5.1-codex", + "externalId": "gpt-5.2-codex", "pricing": { - "prompt": "1.25e-6", - "completion": "10e-6", + "prompt": "1.75e-6", + "completion": "14.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.175e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, - "max_output": 272000 + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-07-13T00:00:00.000Z" } ], "pricing": { - "prompt": "1.25e-6", - "completion": "10e-6", + "prompt": "1.75e-6", + "completion": "14.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.175e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, "context_length": 400000, - "max_output": 272000, + "max_output": 128000, "supported_parameters": [ "temperature", "max_tokens", @@ -10725,14 +15501,14 @@ "json_output": true, "structured_outputs": false, "free": false, - "deactivated_at": "2027-05-15T00:00:00.000Z" + "deactivated_at": "2027-07-13T00:00:00.000Z" }, { - "id": "gpt-5.1-codex-mini", - "name": "GPT-5.1 Codex mini", - "display_name": "GPT-5.1 Codex mini", - "created": 1762905600, - "description": "gpt-5.1-codex-mini provided by openai, azure", + "id": "gpt-5.2-pro", + "name": "GPT-5.2 Pro", + "display_name": "GPT-5.2 Pro", + "created": 1765411200, + "description": "Premium GPT-5.2 model with extended output limits and advanced reasoning for complex tasks.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10745,58 +15521,70 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.1-codex-mini", + "externalId": "gpt-5.2-pro", "pricing": { - "prompt": "0.25e-6", - "completion": "2e-6", + "prompt": "21.0e-6", + "completion": "168.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, + "verbosity": true, "reasoning": true, - "max_output": 128000 + "reasoning_efforts": ["medium", "high", "xhigh"], + "max_output": 272000 }, { "providerId": "azure", - "externalId": "gpt-5.1-codex-mini", + "externalId": "gpt-5.2-pro", "pricing": { - "prompt": "0.25e-6", - "completion": "2e-6", + "prompt": "21.0e-6", + "completion": "168.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, - "max_output": 128000 + "reasoning_efforts": ["medium", "high", "xhigh"], + "max_output": 272000, + "deactivated_at": "2026-09-29T00:00:00.000Z" } ], "pricing": { - "prompt": "0.25e-6", - "completion": "2e-6", + "prompt": "21.0e-6", + "completion": "168.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.025e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, - "max_output": 128000, + "max_output": 272000, "supported_parameters": [ "temperature", "max_tokens", @@ -10810,15 +15598,14 @@ ], "json_output": true, "structured_outputs": false, - "free": false, - "deactivated_at": "2027-05-15T00:00:00.000Z" + "free": false }, { - "id": "gpt-5.2", - "name": "GPT-5.2", - "display_name": "GPT-5.2", - "created": 1765411200, - "description": "gpt-5.2 provided by openai, azure", + "id": "gpt-5.3-codex", + "name": "GPT-5.3 Codex", + "display_name": "GPT-5.3 Codex", + "created": 1771891200, + "description": "Most advanced agentic coding model combining frontier coding performance with broader reasoning capabilities.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10831,7 +15618,7 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.2", + "externalId": "gpt-5.3-codex", "pricing": { "prompt": "1.75e-6", "completion": "14.0e-6", @@ -10839,20 +15626,35 @@ "request": "0", "input_cache_read": "0.175e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-04-01T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-5.2", + "externalId": "gpt-5.3-codex", "pricing": { "prompt": "1.75e-6", "completion": "14.0e-6", @@ -10862,14 +15664,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-08-24T00:00:00.000Z" } ], "pricing": { @@ -10880,30 +15686,33 @@ "input_cache_read": "0.175e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, "max_output": 128000, "supported_parameters": [ "temperature", + "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", - "verbosity", + "tools", + "tool_choice", "reasoning" ], "json_output": true, - "structured_outputs": true, - "free": false + "structured_outputs": false, + "free": false, + "deactivated_at": "2027-08-24T00:00:00.000Z" }, { - "id": "gpt-5.2-codex", - "name": "GPT-5.2 Codex", - "display_name": "GPT-5.2 Codex", - "created": 1768348800, - "description": "gpt-5.2-codex provided by openai, azure", + "id": "gpt-5.4", + "name": "GPT-5.4", + "display_name": "GPT-5.4", + "created": 1772755200, + "description": "Most capable model for complex professional work with reasoning support.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -10916,82 +15725,176 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.2-codex", + "externalId": "gpt-5.4", "pricing": { - "prompt": "1.75e-6", - "completion": "14.0e-6", + "prompt": "2.5e-6", + "completion": "15.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.175e-6", + "input_cache_read": "0.25e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.5e-6", + "completion": "15.0e-6", + "input_cache_read": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "5.0e-6", + "completion": "22.5e-6", + "input_cache_read": "0.5e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ] }, { "providerId": "azure", - "externalId": "gpt-5.2-codex", + "externalId": "gpt-5.4", "pricing": { - "prompt": "1.75e-6", - "completion": "14.0e-6", + "prompt": "2.5e-6", + "completion": "15.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.175e-6", + "input_cache_read": "0.25e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.5e-6", + "completion": "15.0e-6", + "input_cache_read": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "5.0e-6", + "completion": "22.5e-6", + "input_cache_read": "0.5e-6" + } + ] + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"], - "max_output": 128000 - } + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format" + ], + "deactivated_at": "2027-09-02T00:00:00.000Z" + } ], "pricing": { - "prompt": "1.75e-6", - "completion": "14.0e-6", + "prompt": "2.5e-6", + "completion": "15.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.175e-6", + "input_cache_read": "0.25e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.5e-6", + "completion": "15.0e-6", + "input_cache_read": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "5.0e-6", + "completion": "22.5e-6", + "input_cache_read": "0.5e-6" + } + ], "internal_reasoning": "0" }, - "context_length": 400000, + "context_length": 1050000, "max_output": 128000, "supported_parameters": [ "temperature", - "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", - "tools", - "tool_choice", + "verbosity", "reasoning" ], "json_output": true, - "structured_outputs": false, - "free": false, - "deactivated_at": "2027-07-13T00:00:00.000Z" + "structured_outputs": true, + "free": false }, { - "id": "gpt-5.2-pro", - "name": "GPT-5.2 Pro", - "display_name": "GPT-5.2 Pro", - "created": 1765411200, - "description": "gpt-5.2-pro provided by openai, azure", + "id": "gpt-5.4-mini", + "name": "GPT-5.4 Mini", + "display_name": "GPT-5.4 Mini", + "created": 1773705600, + "description": "Strong mini model for coding, computer use, and subagents in high-volume workloads.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11004,60 +15907,94 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.2-pro", + "externalId": "gpt-5.4-mini", "pricing": { - "prompt": "21.0e-6", - "completion": "168.0e-6", + "prompt": "0.75e-6", + "completion": "4.5e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.075e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["medium", "high", "xhigh"], - "max_output": 272000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000 }, { "providerId": "azure", - "externalId": "gpt-5.2-pro", + "externalId": "gpt-5.4-mini", "pricing": { - "prompt": "21.0e-6", - "completion": "168.0e-6", + "prompt": "0.75e-6", + "completion": "4.5e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.075e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, - "reasoning_efforts": ["medium", "high", "xhigh"], - "max_output": 272000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-09-21T00:00:00.000Z" } ], "pricing": { - "prompt": "21.0e-6", - "completion": "168.0e-6", + "prompt": "0.75e-6", + "completion": "4.5e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.075e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, - "max_output": 272000, + "max_output": 128000, "supported_parameters": [ "temperature", "max_tokens", @@ -11070,15 +16007,15 @@ "reasoning" ], "json_output": true, - "structured_outputs": false, + "structured_outputs": true, "free": false }, { - "id": "gpt-5.3-codex", - "name": "GPT-5.3 Codex", - "display_name": "GPT-5.3 Codex", - "created": 1771891200, - "description": "gpt-5.3-codex provided by openai, azure", + "id": "gpt-5.4-nano", + "name": "GPT-5.4 Nano", + "display_name": "GPT-5.4 Nano", + "created": 1773705600, + "description": "Cheapest GPT-5.4-class model for simple high-volume tasks like classification and data extraction.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11091,56 +16028,77 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.3-codex", + "externalId": "gpt-5.4-nano", "pricing": { - "prompt": "1.75e-6", - "completion": "14.0e-6", + "prompt": "0.2e-6", + "completion": "1.25e-6", "image": "0", "request": "0", - "input_cache_read": "0.175e-6", + "input_cache_read": "0.02e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + } + ], + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-04-01T00:00:00.000Z" }, { "providerId": "azure", - "externalId": "gpt-5.3-codex", + "externalId": "gpt-5.4-nano", "pricing": { - "prompt": "1.75e-6", - "completion": "14.0e-6", + "prompt": "0.2e-6", + "completion": "1.25e-6", "image": "0", "request": "0", - "input_cache_read": "0.175e-6", + "input_cache_read": "0.02e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01" }, + "context_length": 400000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-09-21T00:00:00.000Z" } ], "pricing": { - "prompt": "1.75e-6", - "completion": "14.0e-6", + "prompt": "0.2e-6", + "completion": "1.25e-6", "image": "0", "request": "0", - "input_cache_read": "0.175e-6", + "input_cache_read": "0.02e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 400000, @@ -11157,16 +16115,16 @@ "reasoning" ], "json_output": true, - "structured_outputs": false, + "structured_outputs": true, "free": false, - "deactivated_at": "2027-08-24T00:00:00.000Z" + "deactivated_at": "2027-09-21T00:00:00.000Z" }, { - "id": "gpt-5.4", - "name": "GPT-5.4", - "display_name": "GPT-5.4", - "created": 1772755200, - "description": "gpt-5.4 provided by openai, azure", + "id": "gpt-5.4-pro", + "name": "GPT-5.4 Pro", + "display_name": "GPT-5.4 Pro", + "created": 1772323200, + "description": "Version of GPT-5.4 that uses more compute for smarter and more precise responses.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11179,79 +16137,143 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.4", + "externalId": "gpt-5.4-pro", "pricing": { - "prompt": "2.5e-6", - "completion": "15.0e-6", + "prompt": "30.0e-6", + "completion": "180.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.25e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "30.0e-6", + "completion": "180.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "60.0e-6", + "completion": "270.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "reasoning_efforts": ["medium", "high", "xhigh"], "max_output": 128000 }, { "providerId": "azure", - "externalId": "gpt-5.4", + "externalId": "gpt-5.4-pro", "pricing": { - "prompt": "2.5e-6", - "completion": "15.0e-6", + "prompt": "30.0e-6", + "completion": "180.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.25e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "30.0e-6", + "completion": "180.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "60.0e-6", + "completion": "270.0e-6" + } + ] }, + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["medium", "high", "xhigh"], + "max_output": 128000, + "deactivated_at": "2027-09-07T00:00:00.000Z" } ], "pricing": { - "prompt": "2.5e-6", - "completion": "15.0e-6", + "prompt": "30.0e-6", + "completion": "180.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.25e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "30.0e-6", + "completion": "180.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "60.0e-6", + "completion": "270.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, "max_output": 128000, "supported_parameters": [ "temperature", + "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", - "verbosity", + "tools", + "tool_choice", "reasoning" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false }, { - "id": "gpt-5.4-mini", - "name": "GPT-5.4 Mini", - "display_name": "GPT-5.4 Mini", - "created": 1773705600, - "description": "gpt-5.4-mini provided by openai, azure", + "id": "gpt-5.5", + "name": "GPT-5.5", + "display_name": "GPT-5.5", + "created": 1776902400, + "description": "A new class of intelligence for coding and professional work.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11264,69 +16286,164 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.4-mini", + "externalId": "gpt-5.5", "pricing": { - "prompt": "0.75e-6", - "completion": "4.5e-6", + "prompt": "5.0e-6", + "completion": "30.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.075e-6", + "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10.0e-6", + "completion": "45.0e-6", + "input_cache_read": "1.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2.5, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ] }, { "providerId": "azure", - "externalId": "gpt-5.4-mini", + "externalId": "gpt-5.5", "pricing": { - "prompt": "0.75e-6", - "completion": "4.5e-6", + "prompt": "5.0e-6", + "completion": "30.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.075e-6", + "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10.0e-6", + "completion": "45.0e-6", + "input_cache_read": "1.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2.5, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format" + ], + "deactivated_at": "2027-10-26T00:00:00.000Z" } ], "pricing": { - "prompt": "0.75e-6", - "completion": "4.5e-6", + "prompt": "5.0e-6", + "completion": "30.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.075e-6", + "input_cache_read": "0.5e-6", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "5.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "10.0e-6", + "completion": "45.0e-6", + "input_cache_read": "1.0e-6" + } + ], "internal_reasoning": "0" }, - "context_length": 400000, + "context_length": 1050000, "max_output": 128000, "supported_parameters": [ "temperature", - "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "response_format", - "tools", - "tool_choice", + "verbosity", "reasoning" ], "json_output": true, @@ -11334,11 +16451,11 @@ "free": false }, { - "id": "gpt-5.4-nano", - "name": "GPT-5.4 Nano", - "display_name": "GPT-5.4 Nano", - "created": 1773705600, - "description": "gpt-5.4-nano provided by openai, azure", + "id": "gpt-5.5-pro", + "name": "GPT-5.5 Pro", + "display_name": "GPT-5.5 Pro", + "created": 1776902400, + "description": "Version of GPT-5.5 that uses more compute for smarter and more precise responses.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11351,59 +16468,80 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.4-nano", + "externalId": "gpt-5.5-pro", "pricing": { - "prompt": "0.2e-6", - "completion": "1.25e-6", + "prompt": "30.0e-6", + "completion": "180.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.02e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "30.0e-6", + "completion": "180.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "60.0e-6", + "completion": "270.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 - }, - { - "providerId": "azure", - "externalId": "gpt-5.4-nano", - "pricing": { - "prompt": "0.2e-6", - "completion": "1.25e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.02e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], + "reasoning_efforts": ["medium", "high", "xhigh"], "max_output": 128000 } ], "pricing": { - "prompt": "0.2e-6", - "completion": "1.25e-6", + "prompt": "30.0e-6", + "completion": "180.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.02e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "30.0e-6", + "completion": "180.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "60.0e-6", + "completion": "270.0e-6" + } + ], "internal_reasoning": "0" }, - "context_length": 400000, + "context_length": 1050000, "max_output": 128000, "supported_parameters": [ "temperature", @@ -11417,16 +16555,15 @@ "reasoning" ], "json_output": true, - "structured_outputs": true, - "free": false, - "deactivated_at": "2027-09-21T00:00:00.000Z" + "structured_outputs": false, + "free": false }, { - "id": "gpt-5.4-pro", - "name": "GPT-5.4 Pro", - "display_name": "GPT-5.4 Pro", - "created": 1772323200, - "description": "gpt-5.4-pro provided by openai, azure", + "id": "gpt-5.6-luna", + "name": "GPT-5.6 Luna", + "display_name": "GPT-5.6 Luna", + "created": 1783555200, + "description": "Cost-optimized GPT-5.6 model for high-volume tasks like classification and data extraction.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11439,56 +16576,340 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.4-pro", + "externalId": "gpt-5.6-luna", "pricing": { - "prompt": "30.0e-6", - "completion": "180.0e-6", + "prompt": "0.2e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.2e-6", + "completion": "1.2e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.4e-6", + "completion": "1.8e-6", + "input_cache_read": "0.04e-6", + "input_cache_write": "0.5e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "reasoning_modes": ["standard", "pro"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ] }, { "providerId": "azure", - "externalId": "gpt-5.4-pro", + "externalId": "gpt-5.6-luna", "pricing": { - "prompt": "30.0e-6", - "completion": "180.0e-6", + "prompt": "0.2e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.2e-6", + "completion": "1.2e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.4e-6", + "completion": "1.8e-6", + "input_cache_read": "0.04e-6", + "input_cache_write": "0.5e-6" + } + ] }, + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ], + "deactivated_at": "2028-01-11T00:00:00.000Z" + }, + { + "providerId": "aws-mantle", + "externalId": "openai.gpt-5.6-luna", + "pricing": { + "prompt": "0.22e-6", + "completion": "1.32e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.22e-6", + "completion": "1.32e-6", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.44e-6", + "completion": "1.98e-6", + "input_cache_read": "0.044e-6", + "input_cache_write": "0.55e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "0.2e-6", + "completion": "1.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.2e-6", + "completion": "1.2e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.4e-6", + "completion": "1.8e-6", + "input_cache_read": "0.04e-6", + "input_cache_write": "0.5e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-east-1", + "pricing": { + "prompt": "0.22e-6", + "completion": "1.32e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.22e-6", + "completion": "1.32e-6", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.44e-6", + "completion": "1.98e-6", + "input_cache_read": "0.044e-6", + "input_cache_write": "0.55e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-east-2", + "pricing": { + "prompt": "0.22e-6", + "completion": "1.32e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.22e-6", + "completion": "1.32e-6", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.44e-6", + "completion": "1.98e-6", + "input_cache_read": "0.044e-6", + "input_cache_write": "0.55e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-west-2", + "pricing": { + "prompt": "0.22e-6", + "completion": "1.32e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.22e-6", + "completion": "1.32e-6", + "input_cache_read": "0.022e-6", + "input_cache_write": "0.275e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.44e-6", + "completion": "1.98e-6", + "input_cache_read": "0.044e-6", + "input_cache_write": "0.55e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 921600, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { - "prompt": "30.0e-6", - "completion": "180.0e-6", + "prompt": "0.2e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.2e-6", + "completion": "1.2e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.4e-6", + "completion": "1.8e-6", + "input_cache_read": "0.04e-6", + "input_cache_write": "0.5e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, @@ -11500,20 +16921,19 @@ "frequency_penalty", "presence_penalty", "response_format", - "tools", - "tool_choice", + "verbosity", "reasoning" ], "json_output": true, - "structured_outputs": false, + "structured_outputs": true, "free": false }, { - "id": "gpt-5.5", - "name": "GPT-5.5", - "display_name": "GPT-5.5", - "created": 1776902400, - "description": "gpt-5.5 provided by openai, azure", + "id": "gpt-5.6-sol", + "name": "GPT-5.6 Sol", + "display_name": "GPT-5.6 Sol", + "created": 1783555200, + "description": "Frontier GPT-5.6 model for complex professional work with the highest reasoning capabilities.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11526,62 +16946,322 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.5", + "externalId": "gpt-5.6-sol", "pricing": { - "prompt": "5.0e-6", - "completion": "30.0e-6", + "prompt": "4.0e-6", + "completion": "20.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.0e-6", + "completion": "20.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.8e-6", + "input_cache_write": "10.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "reasoning_modes": ["standard", "pro"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ] }, { "providerId": "azure", - "externalId": "gpt-5.5", + "externalId": "gpt-5.6-sol", "pricing": { - "prompt": "5.0e-6", - "completion": "30.0e-6", + "prompt": "4.0e-6", + "completion": "20.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.0e-6", + "completion": "20.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.8e-6", + "input_cache_write": "10.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh"], - "max_output": 128000 + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ], + "deactivated_at": "2028-01-11T00:00:00.000Z" + }, + { + "providerId": "aws-mantle", + "externalId": "openai.gpt-5.6-sol", + "pricing": { + "prompt": "4.4e-6", + "completion": "22.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.4e-6", + "completion": "22.0e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.8e-6", + "completion": "33.0e-6", + "input_cache_read": "0.88e-6", + "input_cache_write": "11.0e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "4.0e-6", + "completion": "20.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.0e-6", + "completion": "20.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.8e-6", + "input_cache_write": "10.0e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-east-1", + "pricing": { + "prompt": "4.4e-6", + "completion": "22.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.4e-6", + "completion": "22.0e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.8e-6", + "completion": "33.0e-6", + "input_cache_read": "0.88e-6", + "input_cache_write": "11.0e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-east-2", + "pricing": { + "prompt": "4.4e-6", + "completion": "22.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.4e-6", + "completion": "22.0e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.8e-6", + "completion": "33.0e-6", + "input_cache_read": "0.88e-6", + "input_cache_write": "11.0e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 921600, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { - "prompt": "5.0e-6", - "completion": "30.0e-6", + "prompt": "4.0e-6", + "completion": "20.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", - "input_cache_write": "0", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "4.0e-6", + "completion": "20.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "8.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0.8e-6", + "input_cache_write": "10.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, "max_output": 128000, "supported_parameters": [ "temperature", + "max_tokens", "top_p", "frequency_penalty", "presence_penalty", @@ -11594,11 +17274,11 @@ "free": false }, { - "id": "gpt-5.5-pro", - "name": "GPT-5.5 Pro", - "display_name": "GPT-5.5 Pro", - "created": 1776902400, - "description": "gpt-5.5-pro provided by openai", + "id": "gpt-5.6-terra", + "name": "GPT-5.6 Terra", + "display_name": "GPT-5.6 Terra", + "created": 1783555200, + "description": "GPT-5.6 model that balances intelligence and cost for everyday workloads.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11611,144 +17291,348 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.5-pro", + "externalId": "gpt-5.6-terra", "pricing": { - "prompt": "30.0e-6", - "completion": "180.0e-6", + "prompt": "2.0e-6", + "completion": "12.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["medium", "high", "xhigh"], - "max_output": 128000 - } - ], - "pricing": { - "prompt": "30.0e-6", - "completion": "180.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1050000, - "max_output": 128000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice", - "reasoning" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "gpt-5.6-luna", - "name": "GPT-5.6 Luna", - "display_name": "GPT-5.6 Luna", - "created": 1783555200, - "description": "gpt-5.6-luna provided by openai, azure, aws-mantle", - "family": "openai", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "openai", - "externalId": "gpt-5.6-luna", - "pricing": { - "prompt": "0.2e-6", - "completion": "1.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.02e-6", - "input_cache_write": "0.25e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "18.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "reasoning_modes": ["standard", "pro"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ] }, { "providerId": "azure", - "externalId": "gpt-5.6-luna", + "externalId": "gpt-5.6-terra", "pricing": { - "prompt": "0.2e-6", - "completion": "1.2e-6", + "prompt": "2.0e-6", + "completion": "12.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.02e-6", - "input_cache_write": "0.25e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "18.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "temperature", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "verbosity" + ], + "deactivated_at": "2028-01-11T00:00:00.000Z" }, { "providerId": "aws-mantle", - "externalId": "openai.gpt-5.6-luna", + "externalId": "openai.gpt-5.6-terra", "pricing": { - "prompt": "0.22e-6", - "completion": "1.32e-6", + "prompt": "2.2e-6", + "completion": "13.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.022e-6", - "input_cache_write": "0.275e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.2e-6", + "completion": "13.2e-6", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.4e-6", + "completion": "19.8e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "12.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "18.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-east-1", + "pricing": { + "prompt": "2.2e-6", + "completion": "13.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.2e-6", + "completion": "13.2e-6", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.4e-6", + "completion": "19.8e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-east-2", + "pricing": { + "prompt": "2.2e-6", + "completion": "13.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.2e-6", + "completion": "13.2e-6", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.4e-6", + "completion": "19.8e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-west-2", + "pricing": { + "prompt": "2.2e-6", + "completion": "13.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.2e-6", + "completion": "13.2e-6", + "input_cache_read": "0.22e-6", + "input_cache_write": "2.75e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.4e-6", + "completion": "19.8e-6", + "input_cache_read": "0.44e-6", + "input_cache_write": "5.5e-6" + } + ] + }, + "context_length": 921600, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 921600, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { - "prompt": "0.2e-6", - "completion": "1.2e-6", + "prompt": "2.0e-6", + "completion": "12.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.02e-6", - "input_cache_write": "0.25e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "18.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, @@ -11768,11 +17652,11 @@ "free": false }, { - "id": "gpt-5.6-sol", - "name": "GPT-5.6 Sol", - "display_name": "GPT-5.6 Sol", - "created": 1783555200, - "description": "gpt-5.6-sol provided by openai, azure, aws-mantle", + "id": "gpt-6-astra", + "name": "GPT-6 Astra", + "display_name": "GPT-6 Astra", + "created": 1788393600, + "description": "OpenAI's most capable model for the hardest end-to-end work.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11785,90 +17669,314 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.6-sol", + "externalId": "gpt-6-astra", "pricing": { - "prompt": "4.0e-6", - "completion": "20.0e-6", + "prompt": "10.0e-6", + "completion": "50.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.4e-6", - "input_cache_write": "5.0e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "10.0e-6", + "completion": "50.0e-6", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "20.0e-6", + "completion": "75.0e-6", + "input_cache_read": "2.0e-6", + "input_cache_write": "25.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "reasoning_modes": ["standard", "pro"], - "max_output": 128000 + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] }, { "providerId": "azure", - "externalId": "gpt-5.6-sol", + "externalId": "gpt-6-astra", "pricing": { - "prompt": "4.0e-6", - "completion": "20.0e-6", + "prompt": "10.0e-6", + "completion": "50.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.4e-6", - "input_cache_write": "5.0e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "10.0e-6", + "completion": "50.0e-6", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "20.0e-6", + "completion": "75.0e-6", + "input_cache_read": "2.0e-6", + "input_cache_write": "25.0e-6" + } + ] + }, + "context_length": 1050000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] }, { "providerId": "aws-mantle", - "externalId": "openai.gpt-5.6-sol", + "externalId": "openai.gpt-6-astra", "pricing": { - "prompt": "4.4e-6", - "completion": "22.0e-6", + "prompt": "10.0e-6", + "completion": "50.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.44e-6", - "input_cache_write": "5.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "10.0e-6", + "completion": "50.0e-6", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "20.0e-6", + "completion": "75.0e-6", + "input_cache_read": "2.0e-6", + "input_cache_write": "25.0e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "10.0e-6", + "completion": "50.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "10.0e-6", + "completion": "50.0e-6", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "20.0e-6", + "completion": "75.0e-6", + "input_cache_read": "2.0e-6", + "input_cache_write": "25.0e-6" + } + ] + }, + "context_length": 1050000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "11.0e-6", + "completion": "55.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "1.1e-6", + "input_cache_write": "13.75e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "11.0e-6", + "completion": "55.0e-6", + "input_cache_read": "1.1e-6", + "input_cache_write": "13.75e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "22.0e-6", + "completion": "82.5e-6", + "input_cache_read": "2.2e-6", + "input_cache_write": "27.5e-6" + } + ] + }, + "context_length": 1050000, + "max_output": 128000, + "streaming": true + }, + { + "id": "us-west-2", + "pricing": { + "prompt": "11.0e-6", + "completion": "55.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "1.1e-6", + "input_cache_write": "13.75e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "11.0e-6", + "completion": "55.0e-6", + "input_cache_read": "1.1e-6", + "input_cache_write": "13.75e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "22.0e-6", + "completion": "82.5e-6", + "input_cache_read": "2.2e-6", + "input_cache_write": "27.5e-6" + } + ] + }, + "context_length": 1050000, + "max_output": 128000, + "streaming": true + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "verbosity": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { - "prompt": "4.0e-6", - "completion": "20.0e-6", + "prompt": "10.0e-6", + "completion": "50.0e-6", "image": "0", "request": "0", - "input_cache_read": "0.4e-6", - "input_cache_write": "5.0e-6", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "10.0e-6", + "completion": "50.0e-6", + "input_cache_read": "1.0e-6", + "input_cache_write": "12.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "20.0e-6", + "completion": "75.0e-6", + "input_cache_read": "2.0e-6", + "input_cache_write": "25.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, "max_output": 128000, "supported_parameters": [ - "temperature", "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", "response_format", "verbosity", + "tools", + "tool_choice", "reasoning" ], "json_output": true, @@ -11876,11 +17984,11 @@ "free": false }, { - "id": "gpt-5.6-terra", - "name": "GPT-5.6 Terra", - "display_name": "GPT-5.6 Terra", - "created": 1783555200, - "description": "gpt-5.6-terra provided by openai, azure, aws-mantle", + "id": "gpt-6-luna", + "name": "GPT-6 Luna", + "display_name": "GPT-6 Luna", + "created": 1790035200, + "description": "OpenAI's most efficient GPT-6 model for focused, high-volume tasks.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -11893,270 +18001,153 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-5.6-terra", + "externalId": "gpt-6-luna", "pricing": { - "prompt": "2.0e-6", - "completion": "12.0e-6", + "prompt": "0.1e-6", + "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.2e-6", - "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.1e-6", + "completion": "0.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0.75e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "reasoning_modes": ["standard", "pro"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] }, { "providerId": "azure", - "externalId": "gpt-5.6-terra", - "pricing": { - "prompt": "2.0e-6", - "completion": "12.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.2e-6", - "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 - }, - { - "providerId": "aws-mantle", - "externalId": "openai.gpt-5.6-terra", + "externalId": "gpt-6-luna", "pricing": { - "prompt": "2.2e-6", - "completion": "13.2e-6", + "prompt": "0.1e-6", + "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.22e-6", - "input_cache_write": "2.75e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.1e-6", + "completion": "0.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0.75e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + } + ] + }, + "context_length": 1050000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { - "prompt": "2.0e-6", - "completion": "12.0e-6", + "prompt": "0.1e-6", + "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.2e-6", - "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1050000, - "max_output": 128000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "verbosity", - "reasoning" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, - { - "id": "gpt-6-astra", - "name": "GPT-6 Astra", - "display_name": "GPT-6 Astra", - "created": 1788393600, - "description": "gpt-6-astra provided by openai, azure, aws-mantle", - "family": "openai", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "openai", - "externalId": "gpt-6-astra", - "pricing": { - "prompt": "10.0e-6", - "completion": "50.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "1.0e-6", - "input_cache_write": "12.5e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 128000 - }, - { - "providerId": "azure", - "externalId": "gpt-6-astra", - "pricing": { - "prompt": "10.0e-6", - "completion": "50.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "1.0e-6", - "input_cache_write": "12.5e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 128000 - }, - { - "providerId": "aws-mantle", - "externalId": "openai.gpt-6-astra", - "pricing": { - "prompt": "10.0e-6", - "completion": "50.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "1.0e-6", - "input_cache_write": "12.5e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 128000 - } - ], - "pricing": { - "prompt": "10.0e-6", - "completion": "50.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "1.0e-6", - "input_cache_write": "12.5e-6", + "input_cache_read": "0.01e-6", + "input_cache_write": "0.125e-6", "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1050000, - "max_output": 128000, - "supported_parameters": [ - "max_tokens", - "response_format", - "verbosity", - "tools", - "tool_choice", - "reasoning" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, - { - "id": "gpt-6-luna", - "name": "GPT-6 Luna", - "display_name": "GPT-6 Luna", - "created": 1790035200, - "description": "gpt-6-luna provided by openai, azure", - "family": "openai", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "openai", - "externalId": "gpt-6-luna", - "pricing": { - "prompt": "0.1e-6", - "completion": "0.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.01e-6", - "input_cache_write": "0.125e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "reasoning_modes": ["standard", "pro"], - "max_output": 128000 - }, - { - "providerId": "azure", - "externalId": "gpt-6-luna", - "pricing": { + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, "prompt": "0.1e-6", "completion": "0.5e-6", - "image": "0", - "request": "0", "input_cache_read": "0.01e-6", - "input_cache_write": "0.125e-6", - "input_cache_write_1h": "0" + "input_cache_write": "0.125e-6" }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 - } - ], - "pricing": { - "prompt": "0.1e-6", - "completion": "0.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.01e-6", - "input_cache_write": "0.125e-6", - "input_cache_write_1h": "0", - "web_search": "0", + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0.75e-6", + "input_cache_read": "0.02e-6", + "input_cache_write": "0.25e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, @@ -12178,7 +18169,7 @@ "name": "GPT-6 Luna Decisions", "display_name": "GPT-6 Luna Decisions", "created": 1791244800, - "description": "gpt-6-luna-decisions provided by openai", + "description": "GPT-6 Luna served through OpenAI's Decisions API. Reads text or images and returns typed predicate, choice and score answers with probabilities instead of generated text. Served via the /v1/decisions endpoint.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -12199,13 +18190,29 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.1e-6", + "completion": "0" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0" + } + ] + }, + "context_length": 1050000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "stability": "beta" } @@ -12219,6 +18226,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "0.1e-6", + "completion": "0" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, @@ -12242,7 +18263,7 @@ "name": "GPT-6 Sol", "display_name": "GPT-6 Sol", "created": 1790035200, - "description": "gpt-6-sol provided by openai, azure", + "description": "GPT-6 model built for complex coding and agentic workflows.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -12263,17 +18284,63 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "10.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "reasoning_modes": ["standard", "pro"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] }, { "providerId": "azure", @@ -12285,16 +18352,56 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "10.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier at a 100% premium. Requires a Global Standard or Data Zone (US) deployment." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -12305,7 +18412,25 @@ "input_cache_read": "0.2e-6", "input_cache_write": "2.5e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "10.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.4e-6", + "input_cache_write": "5.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, @@ -12327,7 +18452,7 @@ "name": "GPT-6.1 Sol", "display_name": "GPT-6.1 Sol", "created": 1790640000, - "description": "gpt-6.1-sol provided by openai, azure", + "description": "Near-Astra performance at a lower cost for complex coding, computer use, and professional work.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -12348,16 +18473,62 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "10.0e-6", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] }, { "providerId": "azure", @@ -12369,16 +18540,48 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "10.0e-6", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "5.0e-6" + } + ] + }, + "context_length": 1050000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 128000 + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -12389,7 +18592,25 @@ "input_cache_read": "0.1e-6", "input_cache_write": "2.5e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "2.0e-6", + "completion": "10.0e-6", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "5.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 1050000, @@ -12407,15 +18628,15 @@ "free": false }, { - "id": "gpt-image-2", - "name": "GPT Image 2", - "display_name": "GPT Image 2", - "created": 1776729600, - "description": "gpt-image-2 provided by openai, azure", + "id": "gpt-6.1-terra", + "name": "GPT-6.1 Terra", + "display_name": "GPT-6.1 Terra", + "created": 1792022400, + "description": "A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -12424,21 +18645,205 @@ "providers": [ { "providerId": "openai", - "externalId": "gpt-image-2", + "externalId": "gpt-6.1-terra", "pricing": { - "prompt": "5e-6", - "completion": "0", - "image": "8e-6", + "prompt": "1.0e-6", + "completion": "5.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.05e-6", + "input_cache_write": "1.25e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "1.0e-6", + "completion": "5.0e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "1.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "2.0e-6", + "completion": "7.5e-6", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6" + } + ] + }, + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "50% lower cost in exchange for slower responses and occasional resource unavailability." + }, + { + "id": "priority", + "name": "Priority", + "multiplier": 2, + "description": "Premium low-latency tier with faster, more consistent processing." + } + ], + "context_length": 1050000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] + }, + { + "providerId": "azure", + "externalId": "gpt-6.1-terra", + "pricing": { + "prompt": "1.0e-6", + "completion": "5.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.05e-6", + "input_cache_write": "1.25e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "1.0e-6", + "completion": "5.0e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "1.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "2.0e-6", + "completion": "7.5e-6", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6" + } + ] + }, + "context_length": 1050000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required", "function"], + "json_output": true, + "structured_outputs": true, + "web_search": true, + "verbosity": true, + "reasoning": true, + "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice" + ] + } + ], + "pricing": { + "prompt": "1.0e-6", + "completion": "5.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.05e-6", + "input_cache_write": "1.25e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 272K", + "up_to_tokens": 272000, + "prompt": "1.0e-6", + "completion": "5.0e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "1.25e-6" + }, + { + "name": "Over 272K", + "up_to_tokens": null, + "prompt": "2.0e-6", + "completion": "7.5e-6", + "input_cache_read": "0.1e-6", + "input_cache_write": "2.5e-6" + } + ], + "internal_reasoning": "0" + }, + "context_length": 1050000, + "max_output": 128000, + "supported_parameters": [ + "max_tokens", + "response_format", + "verbosity", + "tools", + "tool_choice", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, + { + "id": "gpt-image-2", + "name": "GPT Image 2", + "display_name": "GPT Image 2", + "created": 1776729600, + "description": "OpenAI's next-generation image model with improved quality and prompt adherence, supporting text and image inputs.", + "family": "openai", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["image"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "openai", + "externalId": "gpt-image-2", + "pricing": { + "prompt": "5e-6", + "completion": "0", + "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 272000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 128000 }, @@ -12449,24 +18854,31 @@ "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 272000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 128000 + "max_output": 128000, + "deactivated_at": "2027-10-21T00:00:00.000Z" } ], "pricing": { "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12495,7 +18907,7 @@ "name": "GPT Image 2.5 Flare", "display_name": "GPT Image 2.5 Flare", "created": 1788825600, - "description": "gpt-image-2.5-flare provided by openai, azure", + "description": "OpenAI's fast image generation and editing model for everyday workflows, supporting text and image inputs.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -12513,6 +18925,8 @@ "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12523,6 +18937,7 @@ "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false }, { @@ -12532,6 +18947,8 @@ "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12542,13 +18959,17 @@ "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "deactivated_at": "2027-09-08T00:00:00.000Z" } ], "pricing": { "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12576,7 +18997,7 @@ "name": "GPT Image 2.5 Sunburst", "display_name": "GPT Image 2.5 Sunburst", "created": 1788825600, - "description": "gpt-image-2.5-sunburst provided by openai, azure", + "description": "OpenAI's most capable image generation and editing model, built for precise edits from text and image inputs.", "family": "openai", "architecture": { "input_modalities": ["text", "image"], @@ -12594,6 +19015,8 @@ "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12604,6 +19027,7 @@ "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false }, { @@ -12613,6 +19037,8 @@ "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12623,13 +19049,17 @@ "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "deactivated_at": "2027-09-08T00:00:00.000Z" } ], "pricing": { "prompt": "5e-6", "completion": "0", "image": "8e-6", + "image_output": "30e-6", + "image_input_cache_read": "2e-6", "request": "0", "input_cache_read": "1.25e-6", "input_cache_write": "0", @@ -12657,7 +19087,7 @@ "name": "GPT Live Transcribe", "display_name": "GPT Live Transcribe", "created": 1785196800, - "description": "gpt-live-transcribe provided by openai", + "description": "OpenAI's low-latency streaming speech-to-text model. Served only through the gateway's /v1/realtime WebSocket endpoint as a transcription session (intent=transcription) or as the input-audio transcription model of a speech-to-speech session, billed per minute of audio.", "family": "openai", "architecture": { "input_modalities": ["text", "audio"], @@ -12683,9 +19113,11 @@ }, "streaming": false, "vision": false, + "audio": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "stability": "beta" } @@ -12698,8 +19130,8 @@ "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "input_audio_hour": "1.02", "web_search": "0", + "input_audio_hour": "1.02", "internal_reasoning": "0" }, "context_length": 0, @@ -12723,7 +19155,7 @@ "name": "GPT OSS 120B", "display_name": "GPT OSS 120B", "created": 1754352000, - "description": "gpt-oss-120b provided by groq, cerebras, nanogpt, bytedance, nebius, together-ai, azure, scx-ai, runware", + "description": "Open-source 120B parameter model with reasoning capabilities via Groq inference.", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -12746,11 +19178,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], "max_output": 32766 @@ -12767,35 +19201,25 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 32768, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ], "stability": "unstable" }, - { - "providerId": "nanogpt", - "externalId": "openai/gpt-oss-120b", - "pricing": { - "prompt": "0.05e-6", - "completion": "0.25e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 32766 - }, { "providerId": "bytedance", "externalId": "gpt-oss-120b-250805", @@ -12808,11 +19232,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "max_output": 32000 }, @@ -12828,14 +19254,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 32768, - "stability": "unstable" + "quantization": "fp4", + "stability": "unstable", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "together-ai", @@ -12849,11 +19279,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], "max_output": 32768 @@ -12870,11 +19302,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": false, "reasoning": true, "max_output": 32768 }, @@ -12890,43 +19325,29 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 32768, - "stability": "stable" - }, - { - "providerId": "runware", - "externalId": "openai-gpt-oss-120b", - "pricing": { - "prompt": "0.000000032", - "completion": "0.00000014", - "image": "0", - "request": "0", - "input_cache_read": "0.000000032", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, + "reasoning_max_tokens": false, "max_output": 32768, + "quantization": "fp8", "stability": "stable" } ], "pricing": { - "prompt": "0.000000032", - "completion": "0.00000014", + "prompt": "0.1e-6", + "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.000000032", + "input_cache_read": "0.02e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -12952,7 +19373,7 @@ "name": "GPT OSS 20B", "display_name": "GPT OSS 20B", "created": 1754352000, - "description": "gpt-oss-20b provided by groq, nanogpt, together-ai, consensusprotocol", + "description": "Lightweight open-source 20B model with reasoning support for efficient inference.", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -12975,35 +19396,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], "max_output": 32766 }, - { - "providerId": "nanogpt", - "externalId": "openai/gpt-oss-20b", - "pricing": { - "prompt": "0.04e-6", - "completion": "0.15e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 32766 - }, { "providerId": "together-ai", "externalId": "openai/gpt-oss-20b", @@ -13016,14 +19419,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2026-09-15T00:00:00.000Z" }, { "providerId": "consensusprotocol", @@ -13037,13 +19443,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high"], + "reasoning_max_tokens": false, + "quantization": "fp4", "stability": "stable" } ], @@ -13081,7 +19494,7 @@ "display_name": "GPT Realtime", "aliases": ["gpt-realtime-2025-08-28"], "created": 1756339200, - "description": "gpt-realtime provided by openai", + "description": "Legacy OpenAI speech-to-speech realtime model, superseded by gpt-realtime-2.1. Served via the gateway's /v1/realtime WebSocket endpoint with text and audio input/output and function calling.", "family": "openai", "architecture": { "input_modalities": ["text", "audio"], @@ -13099,6 +19512,7 @@ "prompt": "4.0e-6", "completion": "16.0e-6", "image": "5.0e-6", + "image_input_cache_read": "0.5e-6", "input_audio": "32.0e-6", "input_audio_cache_read": "0.4e-6", "output_audio": "64.0e-6", @@ -13107,21 +19521,39 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096, - "stability": "beta" + "supported_voices": [ + "marin", + "cedar", + "alloy", + "ash", + "ballad", + "coral", + "echo", + "sage", + "shimmer", + "verse" + ], + "stability": "beta", + "deprecated_at": "2026-07-20T00:00:00.000Z", + "deactivated_at": "2027-01-20T00:00:00.000Z" } ], "pricing": { "prompt": "4.0e-6", "completion": "16.0e-6", "image": "5.0e-6", + "image_input_cache_read": "0.5e-6", "input_audio": "32.0e-6", "input_audio_cache_read": "0.4e-6", "output_audio": "64.0e-6", @@ -13156,7 +19588,7 @@ "name": "GPT Realtime 2.1", "display_name": "GPT Realtime 2.1", "created": 1783296000, - "description": "gpt-realtime-2.1 provided by openai", + "description": "OpenAI's current speech-to-speech realtime model. Served via the gateway's /v1/realtime WebSocket endpoint with text and audio input/output and function calling.", "family": "openai", "architecture": { "input_modalities": ["text", "audio"], @@ -13174,6 +19606,7 @@ "prompt": "4.0e-6", "completion": "24.0e-6", "image": "5.0e-6", + "image_input_cache_read": "0.5e-6", "input_audio": "32.0e-6", "input_audio_cache_read": "0.4e-6", "output_audio": "64.0e-6", @@ -13182,14 +19615,29 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "max_output": 32000, + "supported_voices": [ + "marin", + "cedar", + "alloy", + "ash", + "ballad", + "coral", + "echo", + "sage", + "shimmer", + "verse" + ], "stability": "beta" } ], @@ -13197,6 +19645,7 @@ "prompt": "4.0e-6", "completion": "24.0e-6", "image": "5.0e-6", + "image_input_cache_read": "0.5e-6", "input_audio": "32.0e-6", "input_audio_cache_read": "0.4e-6", "output_audio": "64.0e-6", @@ -13230,7 +19679,7 @@ "name": "GPT Realtime 2.1 Mini", "display_name": "GPT Realtime 2.1 Mini", "created": 1783296000, - "description": "gpt-realtime-2.1-mini provided by openai", + "description": "Cost-efficient variant of OpenAI's current speech-to-speech realtime model. Served via the gateway's /v1/realtime WebSocket endpoint with text and audio input/output and function calling.", "family": "openai", "architecture": { "input_modalities": ["text", "audio"], @@ -13248,6 +19697,7 @@ "prompt": "0.6e-6", "completion": "2.4e-6", "image": "0.8e-6", + "image_input_cache_read": "0.08e-6", "input_audio": "10.0e-6", "input_audio_cache_read": "0.3e-6", "output_audio": "20.0e-6", @@ -13256,14 +19706,29 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 32000, + "supported_voices": [ + "marin", + "cedar", + "alloy", + "ash", + "ballad", + "coral", + "echo", + "sage", + "shimmer", + "verse" + ], "stability": "beta" } ], @@ -13271,6 +19736,7 @@ "prompt": "0.6e-6", "completion": "2.4e-6", "image": "0.8e-6", + "image_input_cache_read": "0.08e-6", "input_audio": "10.0e-6", "input_audio_cache_read": "0.3e-6", "output_audio": "20.0e-6", @@ -13304,7 +19770,7 @@ "display_name": "GPT Realtime Mini", "aliases": ["gpt-realtime-mini-2025-10-06"], "created": 1759708800, - "description": "gpt-realtime-mini provided by openai", + "description": "Legacy cost-efficient OpenAI speech-to-speech realtime model, superseded by gpt-realtime-2.1-mini. Served via the gateway's /v1/realtime WebSocket endpoint with text and audio input/output and function calling.", "family": "openai", "architecture": { "input_modalities": ["text", "audio"], @@ -13330,15 +19796,32 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096, - "stability": "beta" + "supported_voices": [ + "marin", + "cedar", + "alloy", + "ash", + "ballad", + "coral", + "echo", + "sage", + "shimmer", + "verse" + ], + "stability": "beta", + "deprecated_at": "2026-07-20T00:00:00.000Z", + "deactivated_at": "2027-01-20T00:00:00.000Z" } ], "pricing": { @@ -13379,7 +19862,7 @@ "name": "GPT Transcribe", "display_name": "GPT Transcribe", "created": 1785196800, - "description": "gpt-transcribe provided by openai", + "description": "OpenAI's speech-to-text model for completed audio, billed per minute. Served through the gateway's /v1/realtime WebSocket endpoint as a transcription session (intent=transcription) or as the input-audio transcription model of a speech-to-speech session, transcribing each turn once its audio is committed.", "family": "openai", "architecture": { "input_modalities": ["text", "audio"], @@ -13405,9 +19888,11 @@ }, "streaming": false, "vision": false, + "audio": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "stability": "beta" } @@ -13420,8 +19905,8 @@ "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "input_audio_hour": "0.27", "web_search": "0", + "input_audio_hour": "0.27", "internal_reasoning": "0" }, "context_length": 0, @@ -13445,7 +19930,7 @@ "name": "Granite 4.2 8B", "display_name": "Granite 4.2 8B", "created": 1788220800, - "description": "granite-4.2-8b provided by deepinfra", + "description": "IBM's dense 8B reasoning model for math, code generation, multilingual dialogue, and agentic workflows.", "family": "ibm", "architecture": { "input_modalities": ["text"], @@ -13468,14 +19953,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "function"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 117964 + "max_output": 117964, + "max_temperature": 1, + "quantization": "bf16" } ], "pricing": { @@ -13511,7 +20001,7 @@ "name": "Grok 4", "display_name": "Grok 4", "created": 1752019200, - "description": "grok-4 provided by xai", + "description": "Latest Grok 4 with vision and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -13532,15 +20022,43 @@ "request": "0", "input_cache_read": "0.75e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "3.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.75e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "6.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0" + } + ] }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 256000 + "max_output": 256000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { @@ -13552,6 +20070,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "3.0e-6", + "completion": "15.0e-6", + "input_cache_read": "0.75e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "6.0e-6", + "completion": "30.0e-6", + "input_cache_read": "0" + } + ], "internal_reasoning": "0" }, "context_length": 256000, @@ -13571,11 +20106,11 @@ "free": false }, { - "id": "grok-4-1-fast-non-reasoning", - "name": "Grok 4.1 Fast Non-Reasoning", - "display_name": "Grok 4.1 Fast Non-Reasoning", + "id": "grok-4-1-fast-reasoning", + "name": "Grok 4.1 Fast Reasoning", + "display_name": "Grok 4.1 Fast Reasoning", "created": 1763510400, - "description": "grok-4-1-fast-non-reasoning provided by xai, azure-ai-foundry", + "description": "Grok 4.1 with fast reasoning and vision support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -13588,7 +20123,7 @@ "providers": [ { "providerId": "xai", - "externalId": "grok-4-1-fast-non-reasoning", + "externalId": "grok-4-1-fast-reasoning", "pricing": { "prompt": "0.2e-6", "completion": "0.5e-6", @@ -13596,97 +20131,74 @@ "request": "0", "input_cache_read": "0.05e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 30000 + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "0.2e-6", + "completion": "0.5e-6", + "input_cache_read": "0.05e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "0.4e-6", + "completion": "1.0e-6", + "input_cache_read": "0" + } + ] + }, + "context_length": 2000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "reasoning": true, + "max_output": 30000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ], + "deactivated_at": "2026-05-15T00:00:00.000Z" }, { - "providerId": "azure-ai-foundry", - "externalId": "grok-4-1-fast-non-reasoning", - "pricing": { - "prompt": "0.2e-6", - "completion": "0.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 30000 - } - ], - "pricing": { - "prompt": "0.2e-6", - "completion": "0.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 2000000, - "max_output": 30000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "grok-4-1-fast-reasoning", - "name": "Grok 4.1 Fast Reasoning", - "display_name": "Grok 4.1 Fast Reasoning", - "created": 1763510400, - "description": "grok-4-1-fast-reasoning provided by xai, azure-ai-foundry", - "family": "xai", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "xai", + "providerId": "azure", "externalId": "grok-4-1-fast-reasoning", "pricing": { "prompt": "0.2e-6", "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.05e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 30000 + "max_output": 128000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "azure-ai-foundry", @@ -13700,13 +20212,25 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 30000 + "max_output": 30000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ], + "deactivated_at": "2026-11-07T00:00:00.000Z" } ], "pricing": { @@ -13740,7 +20264,7 @@ "name": "Grok 4.20 Beta Non-Reasoning (0309)", "display_name": "Grok 4.20 Beta Non-Reasoning (0309)", "created": 1773014400, - "description": "grok-4-20-beta-0309-non-reasoning provided by xai", + "description": "Grok 4.20 non-reasoning model with vision and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -13761,15 +20285,42 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.4e-6" + } + ] }, + "context_length": 2000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 30000 + "max_output": 30000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -13781,9 +20332,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 2000000, + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.4e-6" + } + ], + "internal_reasoning": "0" + }, + "context_length": 2000000, "max_output": 30000, "supported_parameters": [ "temperature", @@ -13802,7 +20370,7 @@ "name": "Grok 4.20 Beta Reasoning (0309)", "display_name": "Grok 4.20 Beta Reasoning (0309)", "created": 1773014400, - "description": "grok-4-20-beta-0309-reasoning provided by xai", + "description": "Grok 4.20 reasoning model with vision and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -13823,15 +20391,42 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.4e-6" + } + ] }, + "context_length": 2000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 30000 + "max_output": 30000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -13843,6 +20438,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.4e-6" + } + ], "internal_reasoning": "0" }, "context_length": 2000000, @@ -13865,7 +20477,7 @@ "name": "Grok 4.20 Non-Reasoning", "display_name": "Grok 4.20 Non-Reasoning", "created": 1773014400, - "description": "grok-4-20-non-reasoning provided by vertex-openai", + "description": "Grok 4.20 non-reasoning model with vision and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -13888,13 +20500,40 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "1.25e-6", + "completion": "2.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 2000000, + "max_output": 30000, + "streaming": true + } + ], + "context_length": 2000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 30000 + "max_output": 30000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -13927,7 +20566,7 @@ "name": "Grok 4.20 Reasoning", "display_name": "Grok 4.20 Reasoning", "created": 1773014400, - "description": "grok-4-20-reasoning provided by vertex-openai", + "description": "Grok 4.20 reasoning model with vision and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -13950,13 +20589,41 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "1.25e-6", + "completion": "2.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 2000000, + "max_output": 30000, + "streaming": true + } + ], + "context_length": 2000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 30000 + "max_output": 30000, + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -13990,7 +20657,7 @@ "name": "Grok 4.3", "display_name": "Grok 4.3", "created": 1777507200, - "description": "grok-4-3 provided by xai, aws-bedrock, azure-ai-foundry", + "description": "xAI's flagship reasoning model with 1M context, vision, and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14011,15 +20678,43 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "1.25e-6", + "completion": "2.5e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "2.5e-6", + "completion": "5.0e-6", + "input_cache_read": "0" + } + ] }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high"] + "reasoning_efforts": ["none", "low", "medium", "high"], + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "aws-bedrock", @@ -14033,14 +20728,104 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "1.25e-6", + "completion": "2.50e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.20e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "1.375e-6", + "completion": "2.75e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + }, + { + "id": "us-west-2", + "pricing": { + "prompt": "1.375e-6", + "completion": "2.75e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.22e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "max_output": 131072, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] + }, + { + "providerId": "azure", + "externalId": "grok-4.3", + "pricing": { + "prompt": "1.25e-6", + "completion": "2.50e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.20e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 200000, + "streaming": true, + "vision": false, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": false, + "reasoning": true, + "max_output": 8192, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "azure-ai-foundry", @@ -14054,13 +20839,24 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 20000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, - "max_output": 8192 + "max_output": 8192, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "tools", + "tool_choice", + "reasoning_effort" + ], + "deactivated_at": "2026-11-07T00:00:00.000Z" } ], "pricing": { @@ -14072,6 +20868,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "1.25e-6", + "completion": "2.5e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "2.5e-6", + "completion": "5.0e-6", + "input_cache_read": "0" + } + ], "internal_reasoning": "0" }, "context_length": 1000000, @@ -14096,7 +20909,7 @@ "display_name": "Grok 4.5", "aliases": ["grok-4.5-latest", "grok-build-latest"], "created": 1783468800, - "description": "grok-4-5 provided by xai", + "description": "xAI's flagship reasoning model with a 500K context window, vision, and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14117,15 +20930,43 @@ "request": "0", "input_cache_read": "0.3e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.3e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.6e-6" + } + ] }, + "context_length": 500000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high"] + "reasoning_efforts": ["low", "medium", "high"], + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { @@ -14137,6 +20978,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.3e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "0.6e-6" + } + ], "internal_reasoning": "0" }, "context_length": 500000, @@ -14159,7 +21017,7 @@ "name": "Grok 4.6", "display_name": "Grok 4.6", "created": 1785974400, - "description": "grok-4-6 provided by xai, aws-bedrock, vertex-openai", + "description": "xAI's flagship reasoning model with frontier coding, knowledge work, and STEM performance, a 500K context window, vision, and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14180,15 +21038,43 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ] }, + "context_length": 500000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"] + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "aws-bedrock", @@ -14202,13 +21088,70 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "6.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 500000, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "2.2e-6", + "completion": "6.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 500000, + "streaming": true + }, + { + "id": "us-west-2", + "pricing": { + "prompt": "2.2e-6", + "completion": "6.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 500000, + "streaming": true + } + ], + "context_length": 500000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"] + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "vertex-openai", @@ -14220,15 +21163,77 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "6.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ] + }, + "context_length": 500000, + "streaming": true + } + ], + "context_length": 500000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"] + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { @@ -14240,6 +21245,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 500000, @@ -14262,7 +21284,7 @@ "name": "Grok 4.7", "display_name": "Grok 4.7", "created": 1789948800, - "description": "grok-4-7 provided by xai, aws-bedrock, vertex-openai", + "description": "xAI's flagship reasoning model on a new, larger base model with frontier coding, agentic, and knowledge-work performance, a 500K context window, vision, and tool support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14283,15 +21305,43 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ] }, + "context_length": 500000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"] + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "aws-bedrock", @@ -14305,13 +21355,56 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "6.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 524288, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "2.2e-6", + "completion": "6.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.55e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 524288, + "streaming": true + } + ], + "context_length": 524288, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high", "xhigh"] + "reasoning_efforts": ["low", "medium", "high", "xhigh"], + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "vertex-openai", @@ -14323,15 +21416,77 @@ "request": "0", "input_cache_read": "0.5e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ] + }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "2.0e-6", + "completion": "6.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ] + }, + "context_length": 524288, + "streaming": true + } + ], + "context_length": 524288, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high"] + "reasoning_efforts": ["minimal", "low", "medium", "high"], + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { @@ -14343,6 +21498,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "2.0e-6", + "completion": "6.0e-6", + "input_cache_read": "0.5e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "4.0e-6", + "completion": "12.0e-6", + "input_cache_read": "1.0e-6" + } + ], "internal_reasoning": "0" }, "context_length": 524288, @@ -14365,7 +21537,7 @@ "name": "Grok Build 0.1", "display_name": "Grok Build 0.1", "created": 1779235200, - "description": "grok-build-0-1 provided by xai", + "description": "xAI's fast coding model for agentic software engineering workflows.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14386,15 +21558,42 @@ "request": "0", "input_cache_read": "0.2e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "1.0e-6", + "completion": "2.0e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "2.0e-6", + "completion": "4.0e-6", + "input_cache_read": "0.4e-6" + } + ] }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 256000 + "max_output": 256000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -14406,6 +21605,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "content_filter": "0.05", + "tiers": [ + { + "name": "Up to 200K", + "up_to_tokens": 200000, + "prompt": "1.0e-6", + "completion": "2.0e-6", + "input_cache_read": "0.2e-6" + }, + { + "name": "Over 200K", + "up_to_tokens": null, + "prompt": "2.0e-6", + "completion": "4.0e-6", + "input_cache_read": "0.4e-6" + } + ], "internal_reasoning": "0" }, "context_length": 256000, @@ -14428,7 +21644,7 @@ "name": "Grok Imagine Image", "display_name": "Grok Imagine Image", "created": 1772409600, - "description": "grok-imagine-image provided by xai", + "description": "xAI's fast image generation model with image-to-image support.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14451,11 +21667,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -14492,7 +21710,7 @@ "name": "Grok Imagine Image 2.0", "display_name": "Grok Imagine Image 2.0", "created": 1786147200, - "description": "grok-imagine-image-2-0 provided by xai", + "description": "xAI's second-generation image model for text-to-image generation and reference-image editing, with low and medium quality modes at 1k or 2k resolution.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14522,11 +21740,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -14570,7 +21790,7 @@ "name": "Grok Imagine Video 1.5", "display_name": "Grok Imagine Video 1.5", "created": 1781654400, - "description": "grok-imagine-video-1-5 provided by xai", + "description": "xAI's image-to-video generation model. Requires an input image. Creates videos up to 15 seconds at 480p or 720p.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14587,6 +21807,7 @@ "supportedVideoSizes": ["848x480", "1280x720"], "supportsVideoAudio": true, "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [6, 8, 10, 12, 15], "pricing": { "prompt": "0", "completion": "0", @@ -14601,11 +21822,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -14640,14 +21863,15 @@ ], "json_output": false, "structured_outputs": false, - "free": false + "free": false, + "image_input_required": true }, { "id": "grok-imagine-video-1-5-lite", "name": "Grok Imagine Video 1.5 Lite", "display_name": "Grok Imagine Video 1.5 Lite", "created": 1791417600, - "description": "grok-imagine-video-1-5-lite provided by xai", + "description": "xAI's lightweight video generation model. Creates videos from a text prompt or an input image at a low per-second price. Served from us-east-1 and us-west-2.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14664,6 +21888,7 @@ "supportedVideoSizes": ["848x480", "1280x720"], "supportsVideoAudio": true, "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [6, 8, 10, 12, 15], "pricing": { "prompt": "0", "completion": "0", @@ -14678,11 +21903,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -14724,7 +21951,7 @@ "name": "Grok Imagine Video 1.5 Preview", "display_name": "Grok Imagine Video 1.5 Preview", "created": 1780099200, - "description": "grok-imagine-video-1-5-preview provided by xai", + "description": "xAI's image-to-video generation model. Requires an input image. Creates videos up to 15 seconds at 480p or 720p.", "family": "xai", "architecture": { "input_modalities": ["text", "image"], @@ -14741,6 +21968,7 @@ "supportedVideoSizes": ["848x480", "1280x720"], "supportsVideoAudio": true, "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [6, 8, 10, 12, 15], "pricing": { "prompt": "0", "completion": "0", @@ -14755,11 +21983,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -14794,14 +22024,15 @@ ], "json_output": false, "structured_outputs": false, - "free": false + "free": false, + "image_input_required": true }, { "id": "grok-stt-1-0", "name": "Grok STT 1.0", "display_name": "Grok STT 1.0", "created": 1784764800, - "description": "grok-stt-1-0 provided by xai", + "description": "xAI's speech-to-text model. Transcribes audio files into text with word-level timestamps, speaker diarization, multichannel transcription, and inverse text normalization across 25 languages via the /v1/audio/transcriptions endpoint.", "family": "xai", "architecture": { "input_modalities": ["text"], @@ -14830,6 +22061,7 @@ "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -14841,8 +22073,8 @@ "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "input_audio_hour": "0.10", "web_search": "0", + "input_audio_hour": "0.10", "internal_reasoning": "0" }, "context_length": 0, @@ -14865,7 +22097,7 @@ "name": "Grok Voice 3.0", "display_name": "Grok Voice 3.0", "created": 1791936000, - "description": "grok-voice-3-0 provided by xai", + "description": "xAI's speech-to-speech voice agent model. Served via the gateway's /v1/realtime WebSocket endpoint with text and audio input/output and function calling.", "family": "xai", "architecture": { "input_modalities": ["text", "audio"], @@ -14886,6 +22118,7 @@ "input_audio": "0", "input_audio_cache_read": "0", "output_audio": "0", + "input_text_item": "0.004", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -14894,11 +22127,43 @@ }, "streaming": false, "vision": false, + "audio": true, "realtime": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, + "supported_voices": [ + "ara", + "altair", + "atlas", + "aurora", + "carina", + "castor", + "celeste", + "cosmo", + "eve", + "helios", + "helix", + "iris", + "kepler", + "leo", + "liora", + "lumen", + "luna", + "lux", + "naksh", + "orion", + "perseus", + "rex", + "rigel", + "sal", + "sirius", + "ursa", + "zagan", + "zenith" + ], "stability": "beta" } ], @@ -14909,12 +22174,13 @@ "input_audio": "0", "input_audio_cache_read": "0", "output_audio": "0", + "input_text_item": "0.004", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "input_audio_hour": "4.80", "web_search": "0", + "input_audio_hour": "4.80", "internal_reasoning": "0" }, "context_length": 0, @@ -14938,7 +22204,7 @@ "name": "Hy Image 3.5 Preview", "display_name": "Hy Image 3.5 Preview", "created": 1791158400, - "description": "hy-image-v3.5-preview provided by tencent", + "description": "Tencent's unified image generation and editing model, built on the Hy Image 3.0 MoE base, with up to 20 reference images, output up to 4K, and strong Chinese and English text rendering.", "family": "tencent", "architecture": { "input_modalities": ["text", "image"], @@ -14956,16 +22222,22 @@ "prompt": "0", "completion": "0", "image": "0", + "image_output": "1.6e-6", + "image_output_tokens_by_resolution": { + "default": 20000 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 100000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -14974,6 +22246,10 @@ "prompt": "0", "completion": "0", "image": "0", + "image_output": "1.6e-6", + "image_output_tokens_by_resolution": { + "default": 20000 + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -15002,7 +22278,7 @@ "name": "Hy-MT2 Plus", "display_name": "Hy-MT2 Plus", "created": 1779321600, - "description": "hy-mt2-plus provided by tencent", + "description": "Tencent's Hunyuan translation model, tuned for translation quality and instruction following across a short 8K context.", "family": "tencent", "architecture": { "input_modalities": ["text"], @@ -15025,11 +22301,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8192, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -15066,7 +22344,7 @@ "name": "Hy3", "display_name": "Hy3", "created": 1783296000, - "description": "hy3 provided by deepinfra, novita, tencent", + "description": "Tencent's 295B Mixture-of-Experts model with 21B active parameters, native 256K context support, and three reasoning modes for complex reasoning and agentic tasks.", "family": "tencent", "architecture": { "input_modalities": ["text"], @@ -15089,15 +22367,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high"], "max_output": 131072, - "stability": "unstable" + "quantization": "fp8", + "stability": "unstable", + "deactivated_at": "2026-10-08T00:00:00.000Z" }, { "providerId": "novita", @@ -15111,11 +22394,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "high"], "max_output": 262144 @@ -15132,11 +22418,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -15182,7 +22471,7 @@ "name": "Hy4 Preview", "display_name": "Hy4 Preview", "created": 1787875200, - "description": "hy4-preview provided by tencent", + "description": "Tencent's preview release of Hy4, its next-generation Hunyuan reasoning model, with a 1M context window and preserved thinking.", "family": "tencent", "architecture": { "input_modalities": ["text"], @@ -15205,11 +22494,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -15220,7 +22512,8 @@ "xhigh", "max" ], - "max_output": 65536 + "max_output": 65536, + "max_temperature": 1 } ], "pricing": { @@ -15255,12 +22548,11 @@ "id": "jev-1.13.0", "name": "Jev 1.13", "display_name": "Jev 1.13", - "aliases": ["jev", "jev-latest", "jev-preview"], "created": 1789430400, - "description": "jev-1.13.0 provided by typesafe", + "description": "TypeSafe's System One decision model. Takes a state plus named typed questions and returns calibrated yes/no, choice and score answers with probabilities instead of generated text. Served via the /v1/decisions endpoint and the TypeSafe-compatible /v1/systemone endpoint.", "family": "typesafe", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["decision"], "tokenizer": "GPT" }, @@ -15280,11 +22572,78 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": false, - "vision": false, + "vision": true, + "cancellation": true, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false + } + ], + "pricing": { + "prompt": "0.042e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 262144, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false + }, + { + "id": "jev-1.14.0", + "name": "Jev 1.14", + "display_name": "Jev 1.14", + "aliases": ["jev", "jev-latest", "jev-preview"], + "created": 1791936000, + "description": "TypeSafe's System One decision model. Takes a state plus named typed questions and returns calibrated yes/no, choice and score answers with probabilities instead of generated text. Served via the /v1/decisions endpoint and the TypeSafe-compatible /v1/systemone endpoint.", + "family": "typesafe", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["decision"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "typesafe", + "externalId": "jev-1.14.0", + "pricing": { + "prompt": "0.042e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "streaming": false, + "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -15299,7 +22658,7 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 64000, + "context_length": 262144, "supported_parameters": [ "temperature", "max_tokens", @@ -15319,7 +22678,7 @@ "name": "Kimi K2", "display_name": "Kimi K2", "created": 1752192000, - "description": "kimi-k2 provided by groq, novita, moonshot, nebius, bytedance, alibaba", + "description": "Moonshot's Kimi K2 model for general tasks.", "family": "moonshot", "architecture": { "input_modalities": ["text"], @@ -15342,14 +22701,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 16384, - "stability": "unstable" + "stability": "unstable", + "deactivated_at": "2026-06-05T00:00:00.000Z" }, { "providerId": "novita", @@ -15363,13 +22725,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 131072, + "quantization": "fp8", "stability": "unstable" }, { @@ -15384,13 +22749,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 128000 + "max_output": 128000, + "deactivated_at": "2026-06-05T00:00:00.000Z" }, { "providerId": "nebius", @@ -15404,13 +22772,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 8192 + "max_output": 8192, + "deactivated_at": "2026-04-25T00:00:00.000Z" }, { "providerId": "bytedance", @@ -15424,13 +22795,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "deactivated_at": "2026-06-05T00:00:00.000Z" }, { "providerId": "alibaba", @@ -15444,13 +22818,34 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.574e-6", + "completion": "2.294e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 131072, + "max_output": 8192, + "streaming": true + } + ], + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, + "web_search": true, "reasoning": false, - "max_output": 8192 + "max_output": 8192, + "deactivated_at": "2026-07-08T00:00:00.000Z" } ], "pricing": { @@ -15485,7 +22880,7 @@ "name": "Kimi K2.5", "display_name": "Kimi K2.5", "created": 1769385600, - "description": "kimi-k2.5 provided by moonshot, together-ai, nebius, alibaba, embercloud, deepinfra", + "description": "Moonshot's native multimodal model with visual coding and agentic capabilities.", "family": "moonshot", "architecture": { "input_modalities": ["text", "image"], @@ -15508,11 +22903,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -15523,7 +22921,14 @@ "xhigh", "max" ], - "max_output": 32768 + "max_output": 32768, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "together-ai", @@ -15537,14 +22942,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "max_output": 32768, - "stability": "unstable" + "stability": "unstable", + "deprecated_at": "2026-05-21T00:00:00.000Z", + "deactivated_at": "2026-08-18T00:00:00.000Z" }, { "providerId": "nebius", @@ -15558,14 +22967,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 32768, - "stability": "unstable" + "stability": "unstable", + "deactivated_at": "2026-06-22T00:00:00.000Z" }, { "providerId": "alibaba", @@ -15579,11 +22991,60 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.574e-6", + "completion": "3.011e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "max_output": 98304, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.574e-6", + "completion": "3.011e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "max_output": 98304, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.574e-6", + "completion": "3.011e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "max_output": 98304, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -15594,28 +23055,9 @@ "xhigh", "max" ], + "reasoning_max_tokens": true, "max_output": 98304 }, - { - "providerId": "embercloud", - "externalId": "kimi-k2.5", - "pricing": { - "prompt": "0.405e-6", - "completion": "1.98e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.225e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 262144 - }, { "providerId": "deepinfra", "externalId": "moonshotai/Kimi-K2.5", @@ -15628,13 +23070,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "quantization": "fp4", + "deactivated_at": "2026-09-07T00:00:00.000Z" } ], "pricing": { @@ -15667,7 +23113,7 @@ "name": "Kimi K2.6", "display_name": "Kimi K2.6", "created": 1776643200, - "description": "kimi-k2.6 provided by moonshot, canopywave, novita, together-ai, nebius, baidu, tencent, runware", + "description": "Moonshot's latest native multimodal model with long-term code writing, thinking, and agentic capabilities.", "family": "moonshot", "architecture": { "input_modalities": ["text", "image"], @@ -15690,11 +23136,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -15705,7 +23154,14 @@ "xhigh", "max" ], - "max_output": 262144 + "max_output": 262144, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "canopywave", @@ -15719,11 +23175,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 32768, "stability": "unstable" @@ -15740,11 +23198,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 262144 }, @@ -15760,14 +23220,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["none"], - "max_output": 32768 + "max_output": 32768, + "deprecated_at": "2026-08-07T00:00:00.000Z", + "deactivated_at": "2026-08-19T00:00:00.000Z" }, { "providerId": "nebius", @@ -15781,13 +23245,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, - "stability": "unstable" + "quantization": "int4", + "stability": "unstable", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "baidu", @@ -15801,11 +23270,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -15816,7 +23288,8 @@ "xhigh", "max" ], - "max_output": 262144 + "max_output": 262144, + "deactivated_at": "2026-10-28T00:00:00.000Z" }, { "providerId": "tencent", @@ -15830,11 +23303,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -15846,35 +23323,14 @@ "max" ], "max_output": 262144 - }, - { - "providerId": "runware", - "externalId": "moonshotai-kimi-k2-6", - "pricing": { - "prompt": "0.0000006", - "completion": "0.00000305", - "image": "0", - "request": "0", - "input_cache_read": "0.00000013", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": false, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 131072, - "stability": "stable" } ], "pricing": { - "prompt": "0.0000006", - "completion": "0.00000305", + "prompt": "0.8e-6", + "completion": "3.4e-6", "image": "0", "request": "0", - "input_cache_read": "0.00000013", + "input_cache_read": "0.16e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -15899,7 +23355,7 @@ "name": "Kimi K2.7 Code", "display_name": "Kimi K2.7 Code", "created": 1781222400, - "description": "kimi-k2.7-code provided by moonshot, novita, nebius, tencent, scx-ai-gp", + "description": "Kimi's most intelligent coding model with a native multimodal architecture supporting text, image, and video input, thinking modes, and agent tasks.", "family": "moonshot", "architecture": { "input_modalities": ["text", "image"], @@ -15922,14 +23378,24 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 262144 + "max_output": 262144, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -15943,11 +23409,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 262144 @@ -15964,12 +23434,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": false, + "reasoning": true, + "quantization": "fp4", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "tencent", @@ -15983,11 +23457,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "minimal", @@ -16011,11 +23489,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -16025,7 +23508,9 @@ "high", "xhigh" ], + "reasoning_max_tokens": false, "max_output": 262144, + "quantization": "fp8", "stability": "stable" } ], @@ -16059,7 +23544,7 @@ "name": "Kimi K2.7 Code Highspeed", "display_name": "Kimi K2.7 Code Highspeed", "created": 1781222400, - "description": "kimi-k2.7-code-highspeed provided by moonshot, tencent", + "description": "High-speed inference variant of Kimi's most intelligent coding model with a native multimodal architecture supporting text, image, and video input, thinking modes, and agent tasks.", "family": "moonshot", "architecture": { "input_modalities": ["text", "image"], @@ -16082,14 +23567,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 262144 + "max_output": 262144, + "supported_parameters": [ + "max_tokens", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "tencent", @@ -16103,11 +23597,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "minimal", @@ -16145,11 +23643,11 @@ "free": false }, { - "id": "kimi-k3", - "name": "Kimi K3", - "display_name": "Kimi K3", - "created": 1784160000, - "description": "kimi-k3 provided by alibaba, moonshot, runpod, novita, together-ai, nebius, fireworks, canopywave, tencent, aws-bedrock, runware, scx-ai-gp", + "id": "kimi-k2.8-preview", + "name": "Kimi K2.8 Preview", + "display_name": "Kimi K2.8 Preview", + "created": 1789084800, + "description": "Moonshot's Kimi K2.8 preview model with vision, reasoning, tool calling, and a 1M-token context window.", "family": "moonshot", "architecture": { "input_modalities": ["text", "image"], @@ -16161,8 +23659,90 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "kimi-k3", + "providerId": "tencent", + "externalId": "kimi-k2.8-preview", + "pricing": { + "prompt": "1e-6", + "completion": "4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 1000000, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] + } + ], + "pricing": { + "prompt": "1e-6", + "completion": "4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 1000000, + "max_output": 1000000, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, + { + "id": "kimi-k3", + "name": "Kimi K3", + "display_name": "Kimi K3", + "created": 1784160000, + "description": "Kimi's flagship model for long-horizon coding and end-to-end knowledge work with a 1M-token context window.", + "family": "moonshot", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "alibaba", + "externalId": "kimi-k3", "pricing": { "prompt": "3e-6", "completion": "15e-6", @@ -16172,11 +23752,77 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "3e-6", + "completion": "15e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.3e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 1048576, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "2.827e-6", + "completion": "14.133e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.283e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 1048576, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "2.827e-6", + "completion": "14.133e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.283e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 1048576, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "2.827e-6", + "completion": "14.133e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.283e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 1048576, + "streaming": true + } + ], + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -16187,7 +23833,14 @@ "xhigh", "max" ], - "max_output": 1048576 + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "moonshot", @@ -16201,14 +23854,23 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["low", "high", "max"], - "max_output": 1048576 + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "runpod", @@ -16222,11 +23884,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": false, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -16237,7 +23903,14 @@ "xhigh", "max" ], - "max_output": 1048576 + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -16251,11 +23924,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 1048576 }, @@ -16271,14 +23946,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none"], - "max_output": 1000000 + "max_output": 1000000, + "quantization": "fp4" }, { "providerId": "nebius", @@ -16292,14 +23970,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": false, "reasoning": true, "max_output": 1048576, - "stability": "unstable" + "quantization": "fp4", + "stability": "unstable", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "fireworks", @@ -16313,11 +23996,21 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "service_tiers": [ + { + "id": "priority", + "name": "Priority", + "multiplier": 1.25, + "description": "Queue precedence over standard traffic and protection from load shedding during congestion, at a 25% premium." + } + ], + "context_length": 1040384, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "max_output": 1040384 @@ -16334,11 +24027,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -16363,11 +24059,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -16392,14 +24092,105 @@ "input_cache_write": "3.75e-6", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "global", + "pricing": { + "prompt": "3.0e-6", + "completion": "15.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.3e-6", + "input_cache_write": "3.75e-6", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 1048576, + "streaming": true + }, + { + "id": "us", + "pricing": { + "prompt": "3.3e-6", + "completion": "16.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_write": "4.125e-6", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "max_output": 1048576, + "streaming": true + } + ], + "service_tiers": [ + { + "id": "flex", + "name": "Flex", + "multiplier": 0.5, + "description": "Lower-priority processing at a 50% discount, with longer and less predictable latency." + } + ], + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], - "max_output": 1048576 + "max_output": 1048576, + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] + }, + { + "providerId": "baidu", + "externalId": "qianfan-vl-v1", + "pricing": { + "prompt": "3.0e-6", + "completion": "15.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.3e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] }, { "providerId": "runware", @@ -16413,13 +24204,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": ["none", "low", "high", "max"], + "reasoning_max_tokens": false, "max_output": 1048576, "stability": "stable" }, @@ -16435,11 +24232,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, "reasoning_efforts": [ "none", @@ -16450,7 +24252,9 @@ "xhigh", "max" ], + "reasoning_max_tokens": false, "max_output": 1048576, + "quantization": "fp8", "stability": "stable" } ], @@ -16484,7 +24288,7 @@ "name": "Kimi K3 Fast", "display_name": "Kimi K3 Fast", "created": 1784160000, - "description": "kimi-k3-fast provided by fireworks", + "description": "Kimi K3 served on Fireworks' low-latency Fast router, trading a higher token price for faster generation.", "family": "moonshot", "architecture": { "input_modalities": ["text", "image"], @@ -16507,11 +24311,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1040384, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high", "xhigh", "max"], "max_output": 1040384 @@ -16546,15 +24352,15 @@ "free": false }, { - "id": "kinfra-text-embedding-0.6b", - "name": "Kinfra Text Embedding 0.6B", - "display_name": "Kinfra Text Embedding 0.6B", - "created": 1782777600, - "description": "kinfra-text-embedding-0.6b provided by tencent", - "family": "kinfra", + "id": "kimi-k3.1-pro", + "name": "Kimi K3.1 Pro", + "display_name": "Kimi K3.1 Pro", + "created": 1792713600, + "description": "Kimi's flagship reasoning model with always-on thinking, vision input, tool calling, and a 1M-token context window.", + "family": "moonshot", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["embedding"], + "input_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -16562,61 +24368,113 @@ }, "providers": [ { - "providerId": "tencent", - "externalId": "kinfra-text-embedding-0.6b", + "providerId": "runpod", + "externalId": "kimi-k3.1-pro", "pricing": { - "prompt": "0.07e-6", - "completion": "0", + "prompt": "2.0e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": false, + "context_length": 1048576, + "streaming": true, + "vision": true, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] + }, + { + "providerId": "moonshot", + "externalId": "kimi-k3.1-pro", + "pricing": { + "prompt": "2.0e-6", + "completion": "10.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.0e-6", + "input_cache_write_1h": "4.0e-6" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["low", "high", "max"], + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { - "prompt": "0.07e-6", - "completion": "0", + "prompt": "2.0e-6", + "completion": "10.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 32768, + "context_length": 1048576, + "max_output": 1048576, "supported_parameters": [ - "temperature", "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning_effort", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false }, { - "id": "kinfra-text-embedding-4b", - "name": "Kinfra Text Embedding 4B", - "display_name": "Kinfra Text Embedding 4B", - "created": 1782777600, - "description": "kinfra-text-embedding-4b provided by tencent", - "family": "kinfra", + "id": "kimi-k3.1-pro-highspeed", + "name": "Kimi K3.1 Pro Highspeed", + "display_name": "Kimi K3.1 Pro Highspeed", + "created": 1792713600, + "description": "High-speed inference variant of Kimi K3.1 Pro with always-on thinking, vision input, tool calling, and a 1M-token context window.", + "family": "moonshot", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["embedding"], + "input_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -16624,38 +24482,218 @@ }, "providers": [ { - "providerId": "tencent", - "externalId": "kinfra-text-embedding-4b", + "providerId": "runpod", + "externalId": "kimi-k3.1-pro-highspeed", "pricing": { - "prompt": "0.084e-6", - "completion": "0", + "prompt": "4.0e-6", + "completion": "20.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": false, + "context_length": 1048576, + "streaming": true, + "vision": true, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] + }, + { + "providerId": "moonshot", + "externalId": "kimi-k3.1-pro-highspeed", + "pricing": { + "prompt": "4.0e-6", + "completion": "20.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.2e-6", + "input_cache_write": "4.0e-6", + "input_cache_write_1h": "8.0e-6" + }, + "context_length": 1048576, + "streaming": true, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "supported_tool_choices": ["auto", "none", "required"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["low", "high", "max"], + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort" + ] } ], "pricing": { - "prompt": "0.084e-6", - "completion": "0", + "prompt": "4.0e-6", + "completion": "20.0e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 32768, - "supported_parameters": [ + "context_length": 1048576, + "max_output": 1048576, + "supported_parameters": [ + "max_tokens", + "response_format", + "tools", + "tool_choice", + "reasoning_effort", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, + { + "id": "kinfra-text-embedding-0.6b", + "name": "Kinfra Text Embedding 0.6B", + "display_name": "Kinfra Text Embedding 0.6B", + "created": 1782777600, + "description": "Lightweight text embedding model with 1024-dimensional output and a 32K context, aimed at large-scale retrieval where latency and cost matter most.", + "family": "kinfra", + "architecture": { + "input_modalities": ["text"], + "output_modalities": ["embedding"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "tencent", + "externalId": "kinfra-text-embedding-0.6b", + "pricing": { + "prompt": "0.07e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 32768, + "streaming": false, + "vision": false, + "cancellation": true, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false + } + ], + "pricing": { + "prompt": "0.07e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 32768, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false + }, + { + "id": "kinfra-text-embedding-4b", + "name": "Kinfra Text Embedding 4B", + "display_name": "Kinfra Text Embedding 4B", + "created": 1782777600, + "description": "High-quality text embedding model with 2560-dimensional output and a 32K context, aimed at deep semantic search.", + "family": "kinfra", + "architecture": { + "input_modalities": ["text"], + "output_modalities": ["embedding"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "tencent", + "externalId": "kinfra-text-embedding-4b", + "pricing": { + "prompt": "0.084e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 32768, + "streaming": false, + "vision": false, + "cancellation": true, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false + } + ], + "pricing": { + "prompt": "0.084e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 32768, + "supported_parameters": [ "temperature", "max_tokens", "top_p", @@ -16674,7 +24712,7 @@ "name": "KLING v3.0", "display_name": "KLING v3.0", "created": 1781913600, - "description": "kling-v3-0 provided by atlascloud", + "description": "AtlasCloud KLING v3.0 video generation. Routes text, image, duration, and 4K requests to the matching upstream KLING v3.0 model.", "family": "atlascloud", "architecture": { "input_modalities": ["text", "image"], @@ -16698,6 +24736,7 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [5, 10], "pricing": { "prompt": "0", "completion": "0", @@ -16717,11 +24756,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": false, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1, "stability": "beta" @@ -16768,12 +24809,99 @@ "free": false, "stability": "beta" }, + { + "id": "kling-v3-0-pro", + "name": "KLING v3.0 Pro", + "display_name": "KLING v3.0 Pro", + "created": 1781913600, + "description": "AtlasCloud KLING v3.0 Pro video generation. Routes text and image requests to the matching upstream KLING v3.0 Pro model at 1080p.", + "family": "atlascloud", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["video"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "atlascloud", + "externalId": "kwaivgi/kling-v3.0-pro", + "supportedVideoSizes": ["1920x1080", "1080x1920"], + "supportsVideoAudio": true, + "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [5, 10], + "pricing": { + "prompt": "0", + "completion": "0", + "image": "0", + "per_second": { + "default_audio": "0.168", + "default_video": "0.112", + "1080p_audio": "0.168", + "1080p_video": "0.112" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 2000, + "streaming": false, + "vision": true, + "cancellation": false, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false, + "max_output": 1, + "stability": "beta" + } + ], + "pricing": { + "prompt": "0", + "completion": "0", + "image": "0", + "per_second": { + "default_audio": "0.168", + "default_video": "0.112", + "1080p_audio": "0.168", + "1080p_video": "0.112" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 2000, + "max_output": 1, + "per_request_limits": { + "max_video_duration_seconds": "10" + }, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false, + "stability": "beta" + }, { "id": "kling-v3-0-turbo", "name": "KLING v3.0 Turbo", "display_name": "KLING v3.0 Turbo", "created": 1781913600, - "description": "kling-v3-0-turbo provided by atlascloud", + "description": "AtlasCloud KLING v3.0 Turbo video generation. Routes text, image, and duration requests to the matching upstream KLING v3.0 Turbo model.", "family": "atlascloud", "architecture": { "input_modalities": ["text", "image"], @@ -16795,6 +24923,7 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [5, 10], "pricing": { "prompt": "0", "completion": "0", @@ -16809,11 +24938,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": false, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1, "stability": "beta" @@ -16860,7 +24991,7 @@ "name": "Ling 3.0 Flash", "display_name": "Ling 3.0 Flash", "created": 1785628800, - "description": "ling-3.0-flash provided by deepinfra, novita", + "description": "InclusionAI's native hybrid-reasoning MoE model (124B total, 5.1B active) with strong agentic and coding performance.", "family": "inclusionai", "architecture": { "input_modalities": ["text"], @@ -16883,14 +25014,28 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["none"], - "max_output": 32768 + "max_output": 32768, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "tool_choice" + ] }, { "providerId": "novita", @@ -16904,14 +25049,27 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": [], - "max_output": 32768 + "max_output": 32768, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -16949,7 +25107,7 @@ "name": "Ling 3.0 Flash VL", "display_name": "Ling 3.0 Flash VL", "created": 1788998400, - "description": "ling-3.0-flash-vl provided by deepinfra", + "description": "InclusionAI's Ling 3.0 Flash MoE with native image and video understanding added on top of its language capabilities.", "family": "inclusionai", "architecture": { "input_modalities": ["text", "image"], @@ -16972,14 +25130,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 32768 + "max_output": 32768, + "max_temperature": 1, + "quantization": "fp16" } ], "pricing": { @@ -17011,11 +25174,11 @@ "free": false }, { - "id": "llama-3-70b-instruct", - "name": "Llama 3 70B Instruct", - "display_name": "Llama 3 70B Instruct", - "created": 1713398400, - "description": "llama-3-70b-instruct provided by novita", + "id": "llama-3.1-70b-instruct", + "name": "Llama 3.1 70B Instruct", + "display_name": "Llama 3.1 70B Instruct", + "created": 1721692800, + "description": "Mid-size Llama 3.1 with balanced performance.", "family": "meta", "architecture": { "input_modalities": ["text"], @@ -17027,29 +25190,51 @@ }, "providers": [ { - "providerId": "novita", - "externalId": "meta-llama/llama-3-70b-instruct", + "providerId": "aws-bedrock", + "externalId": "meta.llama3-1-70b-instruct-v1:0", "pricing": { - "prompt": "0.51e-6", - "completion": "0.74e-6", + "prompt": "0.72e-6", + "completion": "0.72e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "us", + "pricing": { + "prompt": "0.792e-6", + "completion": "0.792e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 128000, + "max_output": 2048, + "streaming": true + } + ], + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 8000 + "max_output": 2048, + "stability": "unstable", + "deprecated_at": "2026-09-30T00:00:00.000Z", + "deactivated_at": "2027-03-30T00:00:00.000Z" } ], "pricing": { - "prompt": "0.51e-6", - "completion": "0.74e-6", + "prompt": "0.72e-6", + "completion": "0.72e-6", "image": "0", "request": "0", "input_cache_read": "0", @@ -17058,8 +25243,8 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 8192, - "max_output": 8000, + "context_length": 128000, + "max_output": 2048, "supported_parameters": [ "temperature", "max_tokens", @@ -17070,16 +25255,18 @@ "tools", "tool_choice" ], - "json_output": true, + "json_output": false, "structured_outputs": false, - "free": false + "free": false, + "deprecated_at": "2026-09-30T00:00:00.000Z", + "deactivated_at": "2027-03-30T00:00:00.000Z" }, { - "id": "llama-3.1-70b-instruct", - "name": "Llama 3.1 70B Instruct", - "display_name": "Llama 3.1 70B Instruct", - "created": 1721692800, - "description": "llama-3.1-70b-instruct provided by aws-bedrock", + "id": "llama-3.2-11b-instruct", + "name": "Llama 3.2 11B Instruct", + "display_name": "Llama 3.2 11B Instruct", + "created": 1727222400, + "description": "Llama 3.2 with improved instruction following.", "family": "meta", "architecture": { "input_modalities": ["text"], @@ -17091,30 +25278,31 @@ }, "providers": [ { - "providerId": "aws-bedrock", - "externalId": "meta.llama3-1-70b-instruct-v1:0", + "providerId": "inference.net", + "externalId": "meta-llama/llama-3.2-11b-instruct/fp-16", "pricing": { - "prompt": "0.72e-6", - "completion": "0.72e-6", + "prompt": "0.07e-6", + "completion": "0.33e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 2048, "stability": "unstable" } ], "pricing": { - "prompt": "0.72e-6", - "completion": "0.72e-6", + "prompt": "0.07e-6", + "completion": "0.33e-6", "image": "0", "request": "0", "input_cache_read": "0", @@ -17124,7 +25312,6 @@ "internal_reasoning": "0" }, "context_length": 128000, - "max_output": 2048, "supported_parameters": [ "temperature", "max_tokens", @@ -17135,146 +25322,16 @@ "tools", "tool_choice" ], - "json_output": false, + "json_output": true, "structured_outputs": false, - "free": false, - "deprecated_at": "2026-09-30T00:00:00.000Z", - "deactivated_at": "2027-03-30T00:00:00.000Z" - }, - { - "id": "llama-3.2-11b-instruct", - "name": "Llama 3.2 11B Instruct", - "display_name": "Llama 3.2 11B Instruct", - "created": 1727222400, - "description": "llama-3.2-11b-instruct provided by inference.net", - "family": "meta", - "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "inference.net", - "externalId": "meta-llama/llama-3.2-11b-instruct/fp-16", - "pricing": { - "prompt": "0.07e-6", - "completion": "0.33e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false, - "stability": "unstable" - } - ], - "pricing": { - "prompt": "0.07e-6", - "completion": "0.33e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 128000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "llama-3.2-3b-instruct", - "name": "Llama 3.2 3B Instruct", - "display_name": "Llama 3.2 3B Instruct", - "created": 1726617600, - "description": "llama-3.2-3b-instruct provided by novita", - "family": "meta", - "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "novita", - "externalId": "meta-llama/llama-3.2-3b-instruct", - "pricing": { - "prompt": "0.03e-6", - "completion": "0.05e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 32000, - "stability": "unstable" - } - ], - "pricing": { - "prompt": "0.03e-6", - "completion": "0.05e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 32768, - "max_output": 32000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false + "free": false }, { "id": "llama-3.3-70b-instruct", "name": "Llama 3.3 70B Instruct", "display_name": "Llama 3.3 70B Instruct", "created": 1733443200, - "description": "llama-3.3-70b-instruct provided by nebius, cerebras, novita", + "description": "Latest Llama 3.3 70B with enhanced capabilities.", "family": "meta", "architecture": { "input_modalities": ["text"], @@ -17297,12 +25354,27 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "quantization": "fp8", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools" + ], + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "cerebras", @@ -17316,12 +25388,21 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format" + ], + "deactivated_at": "2026-10-28T00:00:00.000Z" }, { "providerId": "novita", @@ -17335,13 +25416,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 120000 + "max_output": 120000, + "quantization": "bf16" } ], "pricing": { @@ -17368,7 +25452,7 @@ "response_format", "tools" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, @@ -17377,7 +25461,7 @@ "name": "Llama 4 Maverick 17B Instruct", "display_name": "Llama 4 Maverick 17B Instruct", "created": 1743811200, - "description": "llama-4-maverick-17b-instruct provided by aws-bedrock, novita", + "description": "Llama 4 Maverick variant with vision capabilities.", "family": "meta", "architecture": { "input_modalities": ["text", "image"], @@ -17400,14 +25484,35 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "us", + "pricing": { + "prompt": "0.264e-6", + "completion": "1.067e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 8192, + "max_output": 2048, + "streaming": true + } + ], + "context_length": 8192, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 2048, - "stability": "unstable" + "stability": "unstable", + "deprecated_at": "2026-09-30T00:00:00.000Z", + "deactivated_at": "2027-03-30T00:00:00.000Z" }, { "providerId": "novita", @@ -17421,13 +25526,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 8192 + "max_output": 8192, + "quantization": "fp8" } ], "pricing": { @@ -17462,7 +25570,7 @@ "name": "Llama 4 Scout 17B Instruct", "display_name": "Llama 4 Scout 17B Instruct", "created": 1743811200, - "description": "llama-4-scout-17b-instruct provided by aws-bedrock, novita", + "description": "Compact Llama 4 Scout with vision support.", "family": "meta", "architecture": { "input_modalities": ["text", "image"], @@ -17485,14 +25593,35 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "us", + "pricing": { + "prompt": "0.187e-6", + "completion": "0.726e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 8192, + "max_output": 2048, + "streaming": true + } + ], + "context_length": 8192, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 2048, - "stability": "unstable" + "stability": "unstable", + "deprecated_at": "2026-09-30T00:00:00.000Z", + "deactivated_at": "2027-03-30T00:00:00.000Z" }, { "providerId": "novita", @@ -17506,13 +25635,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 131072, + "quantization": "bf16", "stability": "unstable" } ], @@ -17548,7 +25680,7 @@ "name": "Microsoft-Decision-1", "display_name": "Microsoft-Decision-1", "created": 1791504000, - "description": "microsoft-decision-1 provided by azure", + "description": "Microsoft's small decision model for classification, routing, ranking, grading and binary decisions. Reads text or JSON and returns typed predicate, choice and score answers with probabilities instead of generated text. Served via the /v1/decisions endpoint.", "family": "microsoft", "architecture": { "input_modalities": ["text"], @@ -17571,11 +25703,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -17606,11 +25740,11 @@ "free": false }, { - "id": "mimo-v2.5", - "name": "MiMo V2.5", - "display_name": "MiMo V2.5", - "created": 1776902400, - "description": "mimo-v2.5 provided by xiaomi, novita, deepinfra", + "id": "mimo-v2.6-flash", + "name": "MiMo V2.6 Flash", + "display_name": "MiMo V2.6 Flash", + "created": 1790035200, + "description": "Xiaomi's low-cost omni-modal reasoning model with 1M context, balancing intelligence and price for high-volume workloads.", "family": "xiaomi", "architecture": { "input_modalities": ["text", "image", "audio"], @@ -17623,7 +25757,7 @@ "providers": [ { "providerId": "xiaomi", - "externalId": "mimo-v2.5", + "externalId": "mimo-v2.6-flash", "pricing": { "prompt": "0.14e-6", "completion": "0.28e-6", @@ -17633,53 +25767,67 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, + "audio": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1.5 }, { - "providerId": "novita", - "externalId": "xiaomimimo/mimo-v2.5", + "providerId": "tencent", + "externalId": "mimo-v2.6-flash", "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" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 + "reasoning_efforts": ["none", "low", "medium", "high", "max"], + "max_output": 131072, + "max_temperature": 1.5 }, { "providerId": "deepinfra", - "externalId": "XiaomiMiMo/MiMo-V2.5", + "externalId": "XiaomiMiMo/MiMo-V2.6-Flash", "pricing": { - "prompt": "0.4e-6", - "completion": "2e-6", + "prompt": "0.14e-6", + "completion": "0.28e-6", "image": "0", "request": "0", - "input_cache_read": "0.08e-6", + "input_cache_read": "0.0028e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, + "audio": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -17690,22 +25838,49 @@ "xhigh", "max" ], - "max_output": 16384 + "max_output": 65536, + "quantization": "fp8" + }, + { + "providerId": "consensusprotocol", + "externalId": "MiMo-V2.6-Flash", + "pricing": { + "prompt": "0.00000012", + "completion": "0.00000025", + "image": "0", + "request": "0", + "input_cache_read": "0.0000000025", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": false, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": true, + "reasoning_max_tokens": false, + "stability": "stable" } ], "pricing": { - "prompt": "0.14e-6", - "completion": "0.28e-6", + "prompt": "0.00000012", + "completion": "0.00000025", "image": "0", "request": "0", - "input_cache_read": "0.0028e-6", + "input_cache_read": "0.0000000025", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, "context_length": 1048576, - "max_output": 131072, + "max_output": 65536, "supported_parameters": [ "temperature", "max_tokens", @@ -17718,19 +25893,18 @@ "reasoning" ], "json_output": true, - "structured_outputs": false, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "structured_outputs": true, + "free": false }, { - "id": "mimo-v2.5-pro", - "name": "MiMo V2.5 Pro", - "display_name": "MiMo V2.5 Pro", - "created": 1776902400, - "description": "mimo-v2.5-pro provided by xiaomi, novita, deepinfra, tencent", + "id": "mimo-v2.6-pro", + "name": "MiMo V2.6 Pro", + "display_name": "MiMo V2.6 Pro", + "created": 1790035200, + "description": "Xiaomi's flagship trillion-parameter omni-modal reasoning model with 1M context, built for complex, long-horizon agentic work.", "family": "xiaomi", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -17740,7 +25914,7 @@ "providers": [ { "providerId": "xiaomi", - "externalId": "mimo-v2.5-pro", + "externalId": "mimo-v2.6-pro", "pricing": { "prompt": "0.435e-6", "completion": "0.87e-6", @@ -17750,53 +25924,67 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, - "vision": false, + "vision": true, + "audio": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1.5 }, { - "providerId": "novita", - "externalId": "xiaomimimo/mimo-v2.5-pro", + "providerId": "tencent", + "externalId": "mimo-v2.6-pro", "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" }, + "context_length": 1000000, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["none", "minimal", "low", "medium", "high"], - "max_output": 131072 + "reasoning_efforts": ["none", "low", "medium", "high", "max"], + "max_output": 131072, + "max_temperature": 1.5 }, { "providerId": "deepinfra", - "externalId": "XiaomiMiMo/MiMo-V2.5-Pro", + "externalId": "XiaomiMiMo/MiMo-V2.6-Pro", "pricing": { - "prompt": "1e-6", - "completion": "3e-6", + "prompt": "0.435e-6", + "completion": "0.87e-6", "image": "0", "request": "0", - "input_cache_read": "0.2e-6", + "input_cache_read": "0.0036e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, - "vision": false, + "vision": true, + "audio": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -17807,28 +25995,8 @@ "xhigh", "max" ], - "max_output": 16384 - }, - { - "providerId": "tencent", - "externalId": "mimo-v2.5-pro", - "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.0036e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 + "max_output": 65536, + "quantization": "fp8" } ], "pricing": { @@ -17843,7 +26011,7 @@ "internal_reasoning": "0" }, "context_length": 1048576, - "max_output": 131072, + "max_output": 65536, "supported_parameters": [ "temperature", "max_tokens", @@ -17856,226 +26024,15 @@ "reasoning" ], "json_output": true, - "structured_outputs": false, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" - }, - { - "id": "mimo-v2.6-flash", - "name": "MiMo V2.6 Flash", - "display_name": "MiMo V2.6 Flash", - "created": 1790035200, - "description": "mimo-v2.6-flash provided by xiaomi, deepinfra, consensusprotocol", - "family": "xiaomi", - "architecture": { - "input_modalities": ["text", "image", "audio"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "xiaomi", - "externalId": "mimo-v2.6-flash", - "pricing": { - "prompt": "0.14e-6", - "completion": "0.28e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.0028e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 - }, - { - "providerId": "deepinfra", - "externalId": "XiaomiMiMo/MiMo-V2.6-Flash", - "pricing": { - "prompt": "0.14e-6", - "completion": "0.28e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.0028e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": [ - "none", - "minimal", - "low", - "medium", - "high", - "xhigh", - "max" - ], - "max_output": 65536 - }, - { - "providerId": "consensusprotocol", - "externalId": "MiMo-V2.6-Flash", - "pricing": { - "prompt": "0.00000012", - "completion": "0.00000025", - "image": "0", - "request": "0", - "input_cache_read": "0.0000000025", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "stability": "stable" - } - ], - "pricing": { - "prompt": "0.00000012", - "completion": "0.00000025", - "image": "0", - "request": "0", - "input_cache_read": "0.0000000025", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1048576, - "max_output": 65536, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice", - "reasoning" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, - { - "id": "mimo-v2.6-pro", - "name": "MiMo V2.6 Pro", - "display_name": "MiMo V2.6 Pro", - "created": 1790035200, - "description": "mimo-v2.6-pro provided by xiaomi, deepinfra", - "family": "xiaomi", - "architecture": { - "input_modalities": ["text", "image", "audio"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "xiaomi", - "externalId": "mimo-v2.6-pro", - "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.0036e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 131072 - }, - { - "providerId": "deepinfra", - "externalId": "XiaomiMiMo/MiMo-V2.6-Pro", - "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.0036e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": [ - "none", - "minimal", - "low", - "medium", - "high", - "xhigh", - "max" - ], - "max_output": 65536 - } - ], - "pricing": { - "prompt": "0.435e-6", - "completion": "0.87e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.0036e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1048576, - "max_output": 65536, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice", - "reasoning" - ], - "json_output": true, - "structured_outputs": true, - "free": false + "structured_outputs": true, + "free": false }, { "id": "minimax-h3-max", "name": "MiniMax H3 Max", "display_name": "MiniMax H3 Max", "created": 1788825600, - "description": "minimax-h3-max provided by minimax", + "description": "MiniMax's fast H3 video model with native synchronized audio, supporting text-to-video and first/last-frame image-to-video from 5 to 15 seconds at 480p or 768p.", "family": "minimax", "architecture": { "input_modalities": ["text", "image"], @@ -18098,6 +26055,9 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [ + 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 + ], "pricing": { "prompt": "0", "completion": "0", @@ -18111,11 +26071,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 7000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -18159,7 +26121,7 @@ "name": "MiniMax Hailuo 2.3", "display_name": "MiniMax Hailuo 2.3", "created": 1762473600, - "description": "minimax-hailuo-2-3 provided by minimax", + "description": "MiniMax's video generation model supporting text-to-video and image-to-video up to 10 seconds at 768p or 1080p resolution.", "family": "minimax", "architecture": { "input_modalities": ["text", "image"], @@ -18176,6 +26138,8 @@ "supportedVideoSizes": ["1280x720", "1366x768", "1920x1080"], "supportsVideoAudio": false, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [6, 10], + "supported_video_durations_seconds_image_to_video": [6, 10], "pricing": { "prompt": "0", "completion": "0", @@ -18190,11 +26154,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -18236,7 +26202,7 @@ "name": "MiniMax M2", "display_name": "MiniMax M2", "created": 1761523200, - "description": "minimax-m2 provided by minimax", + "description": "MiniMax M2 model with reasoning and tool support.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18259,11 +26225,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 196608, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131072 @@ -18302,7 +26270,7 @@ "name": "MiniMax M2.1", "display_name": "MiniMax M2.1", "created": 1766448000, - "description": "minimax-m2.1 provided by minimax, novita", + "description": "MiniMax M2.1 is a 10B-activated open-source coding and agent model with function calling, structured output, and reasoning support.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18325,11 +26293,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 196608, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131072 @@ -18346,13 +26316,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "quantization": "fp8", + "deactivated_at": "2026-10-28T00:00:00.000Z" } ], "pricing": { @@ -18379,7 +26354,7 @@ "tool_choice", "reasoning" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, @@ -18388,7 +26363,7 @@ "name": "MiniMax M2.1 Lightning", "display_name": "MiniMax M2.1 Lightning", "created": 1766448000, - "description": "minimax-m2.1-lightning provided by minimax", + "description": "MiniMax M2.1 Lightning is a faster variant of M2.1 with lower latency for coding tasks.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18411,11 +26386,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 196608, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131072 @@ -18454,7 +26431,7 @@ "name": "MiniMax M2.5", "display_name": "MiniMax M2.5", "created": 1771113600, - "description": "minimax-m2.5 provided by minimax, novita, together-ai, embercloud, nebius", + "description": "MiniMax M2.5 with enhanced reasoning and tool support.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18477,11 +26454,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131100 @@ -18498,13 +26477,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131100 + "max_output": 131100, + "quantization": "fp8" }, { "providerId": "together-ai", @@ -18518,33 +26500,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 228700, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131100 - }, - { - "providerId": "embercloud", - "externalId": "minimax-m2.5", - "pricing": { - "prompt": "0.2e-6", - "completion": "1.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.04e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 196608 + "max_output": 131100, + "deactivated_at": "2026-04-27T00:00:00.000Z" }, { "providerId": "nebius", @@ -18558,14 +26523,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 196608, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "max_output": 131100, - "stability": "unstable" + "quantization": "fp4", + "stability": "unstable", + "deactivated_at": "2026-08-31T00:00:00.000Z" } ], "pricing": { @@ -18582,20 +26551,14 @@ "context_length": 228700, "max_output": 131100, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", "tool_choice", - "parallel_tool_calls", "reasoning" ], "json_output": true, @@ -18607,7 +26570,7 @@ "name": "MiniMax M2.5 Highspeed", "display_name": "MiniMax M2.5 Highspeed", "created": 1771113600, - "description": "minimax-m2.5-highspeed provided by minimax", + "description": "Highspeed MiniMax M2.5 variant with the same model quality and lower latency.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18630,11 +26593,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131100 @@ -18673,7 +26638,7 @@ "name": "MiniMax M2.7", "display_name": "MiniMax M2.7", "created": 1773792000, - "description": "minimax-m2.7 provided by minimax, novita, together-ai, tencent, gonka24, scx-ai", + "description": "MiniMax M2.7 with stronger reasoning and coding performance for complex tasks.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18696,11 +26661,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131100 @@ -18717,13 +26684,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 131100 + "max_output": 131100, + "quantization": "fp8" }, { "providerId": "together-ai", @@ -18737,13 +26707,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 196608, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 196608 + "max_output": 196608, + "deactivated_at": "2026-07-27T00:00:00.000Z" }, { "providerId": "tencent", @@ -18757,64 +26730,51 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 128000 }, { - "providerId": "gonka24", - "externalId": "minimax-m2.7", + "providerId": "scx-ai", + "externalId": "MiniMax-M2.7", "pricing": { - "prompt": "0.00000008", - "completion": "0.00000032", + "prompt": "0.00000048", + "completion": "0.00000179", "image": "0", "request": "0", - "input_cache_read": "0.000000017", + "input_cache_read": "0.00000005", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 196608, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": false, "reasoning": true, - "max_output": 131100, - "stability": "stable" - }, - { - "providerId": "scx-ai", - "externalId": "MiniMax-M2.7", - "pricing": { - "prompt": "0.00000048", - "completion": "0.00000179", - "image": "0", - "request": "0", - "input_cache_read": "0.00000005", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 196608, + "reasoning_max_tokens": false, + "max_output": 196608, "stability": "stable" } ], "pricing": { - "prompt": "0.00000008", - "completion": "0.00000032", + "prompt": "0.3e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.000000017", + "input_cache_read": "0.06e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", @@ -18842,7 +26802,7 @@ "name": "MiniMax M2.7 Highspeed", "display_name": "MiniMax M2.7 Highspeed", "created": 1773792000, - "description": "minimax-m2.7-highspeed provided by minimax", + "description": "Highspeed MiniMax M2.7 variant with the same model quality and lower latency.", "family": "minimax", "architecture": { "input_modalities": ["text"], @@ -18865,11 +26825,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 204800, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131100 @@ -18908,7 +26870,7 @@ "name": "MiniMax M3", "display_name": "MiniMax M3", "created": 1780272000, - "description": "minimax-m3 provided by minimax, together-ai, nebius, tencent, consensusprotocol", + "description": "MiniMax M3 is a multimodal foundation model with 512K token context, native multimodal understanding, and MiniMax Sparse Attention (MSA) for efficient long-context inference.", "family": "minimax", "architecture": { "input_modalities": ["text", "image"], @@ -18931,11 +26893,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 512000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -18960,14 +26924,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 524288, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none"], - "max_output": 131072 + "max_output": 131072, + "quantization": "fp4", + "deactivated_at": "2026-11-06T00:00:00.000Z" }, { "providerId": "nebius", @@ -18981,12 +26950,16 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": false, + "reasoning": true, + "quantization": "fp8", + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { "providerId": "tencent", @@ -18998,13 +26971,31 @@ "request": "0", "input_cache_read": "0.06e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 512K", + "up_to_tokens": 512000, + "prompt": "0.3e-6", + "completion": "1.2e-6", + "input_cache_read": "0.06e-6" + }, + { + "name": "Over 512K", + "up_to_tokens": null, + "prompt": "0.6e-6", + "completion": "2.4e-6", + "input_cache_read": "0.12e-6" + } + ] }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], "max_output": 131072 @@ -19021,12 +27012,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": false, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": true, + "reasoning_max_tokens": false, "stability": "stable" } ], @@ -19063,7 +27060,7 @@ "name": "MiniMax M3.1 Flash", "display_name": "MiniMax M3.1 Flash", "created": 1792368000, - "description": "minimax-m3.1-flash provided by minimax", + "description": "MiniMax M3.1 Flash is a multimodal M-series model for agentic reasoning, tool use, coding, and long-context tasks, with a 1M token context window and tunable thinking depth.", "family": "minimax", "architecture": { "input_modalities": ["text", "image"], @@ -19086,773 +27083,105 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": false, "reasoning": true, "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], - "max_output": 524288 - } - ], - "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.015e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1048576, - "max_output": 524288, - "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", - "temperature", - "top_p", - "max_tokens", - "max_completion_tokens", - "frequency_penalty", - "presence_penalty", - "seed", - "stop", - "tools", - "tool_choice", - "reasoning_effort", - "reasoning" - ], - "json_output": false, - "structured_outputs": false, - "free": false - }, - { - "id": "minimax-text-01", - "name": "MiniMax Text 01", - "display_name": "MiniMax Text 01", - "created": 1736899200, - "description": "minimax-text-01 provided by minimax", - "family": "minimax", - "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "minimax", - "externalId": "MiniMax-Text-01", - "pricing": { - "prompt": "0.2e-6", - "completion": "1.1e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 131072 - } - ], - "pricing": { - "prompt": "0.2e-6", - "completion": "1.1e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1000000, - "max_output": 131072, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice", - "reasoning" - ], - "json_output": false, - "structured_outputs": false, - "free": false - }, - { - "id": "ministral-14b-2512", - "name": "Ministral 14B", - "display_name": "Ministral 14B", - "created": 1764633600, - "description": "ministral-14b-2512 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "ministral-14b-2512", - "pricing": { - "prompt": "0.2e-6", - "completion": "0.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.2e-6", - "completion": "0.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 262144, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "ministral-3b-2512", - "name": "Ministral 3B", - "display_name": "Ministral 3B", - "created": 1764633600, - "description": "ministral-3b-2512 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ + "max_output": 524288, + "supported_parameters": [ + "messages", + "model", + "stream", + "stream_options", + "temperature", + "top_p", + "max_tokens", + "max_completion_tokens", + "frequency_penalty", + "presence_penalty", + "seed", + "stop", + "tools", + "tool_choice", + "reasoning_effort" + ] + }, { - "providerId": "mistral", - "externalId": "ministral-3b-2512", + "providerId": "inference.net", + "externalId": "minimax-m3.1-flash", "pricing": { "prompt": "0.1e-6", - "completion": "0.1e-6", + "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.005e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.1e-6", - "completion": "0.1e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 131072, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "ministral-8b-2512", - "name": "Ministral 8B", - "display_name": "Ministral 8B", - "created": 1764633600, - "description": "ministral-8b-2512 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "ministral-8b-2512", - "pricing": { - "prompt": "0.15e-6", - "completion": "0.15e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.15e-6", - "completion": "0.15e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 262144, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "mistral-large-2512", - "name": "Mistral Large 3", - "display_name": "Mistral Large 3", - "created": 1764633600, - "description": "mistral-large-2512 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-large-2512", - "pricing": { - "prompt": "0.5e-6", - "completion": "1.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.5e-6", - "completion": "1.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 262144, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "mistral-large-4", - "name": "Mistral Large 4", - "display_name": "Mistral Large 4", - "created": 1791244800, - "description": "mistral-large-4 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-large-4-0", - "pricing": { - "prompt": "1.36e-6", - "completion": "4.18e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.14e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "1.36e-6", - "completion": "4.18e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.14e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 1000000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, - { - "id": "mistral-large-latest", - "name": "Mistral Large Latest", - "display_name": "Mistral Large Latest", - "created": 1764633600, - "description": "mistral-large-latest provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-large-latest", - "pricing": { - "prompt": "0.000004", - "completion": "0.000012", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.000004", - "completion": "0.000012", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 128000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": false, - "structured_outputs": false, - "free": false - }, - { - "id": "mistral-medium-3-5", - "name": "Mistral Medium 3.5", - "display_name": "Mistral Medium 3.5", - "created": 1777593600, - "description": "mistral-medium-3-5 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-medium-3-5", - "pricing": { - "prompt": "1.5e-6", - "completion": "7.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "1.5e-6", - "completion": "7.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 262144, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, - { - "id": "mistral-ocr-latest", - "name": "Mistral OCR", - "display_name": "Mistral OCR", - "created": 1741219200, - "description": "mistral-ocr-latest provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["ocr"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-ocr-latest", - "pricing": { - "prompt": "0", - "completion": "0", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "ocr_page": "0.004" - }, - "streaming": false, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0", - "completion": "0", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "ocr_page": "0.004", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 0, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": false, - "structured_outputs": false, - "free": false - }, - { - "id": "mistral-small-2506", - "name": "Mistral Small 3.2", - "display_name": "Mistral Small 3.2", - "created": 1750377600, - "description": "mistral-small-2506 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-small-2506", - "pricing": { - "prompt": "0.1e-6", - "completion": "0.3e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.1e-6", - "completion": "0.3e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 128000, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "mistral-small-2603", - "name": "Mistral Small 4", - "display_name": "Mistral Small 4", - "created": 1773705600, - "description": "mistral-small-2603 provided by mistral", - "family": "mistral", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "mistral", - "externalId": "mistral-small-2603", - "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false - } - ], - "pricing": { - "prompt": "0.15e-6", - "completion": "0.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 262144, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": true, - "structured_outputs": true, - "free": false - }, - { - "id": "muse-glimmer-30b", - "name": "Muse Glimmer 30B", - "display_name": "Muse Glimmer 30B", - "created": 1786320000, - "description": "muse-glimmer-30b provided by deepinfra, together-ai", - "family": "meta", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "reasoning": true, + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 524288 + }, { - "providerId": "deepinfra", - "externalId": "meta-models/Muse-Glimmer-30B", + "providerId": "novita", + "externalId": "minimax/minimax-m3.1-flash", "pricing": { - "prompt": "0.3e-6", - "completion": "1.2e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.04e-6", + "input_cache_read": "0.015e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": false, + "reasoning": true, + "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"], + "max_output": 524288 + }, + { + "providerId": "nebius", + "externalId": "MiniMaxAI/MiniMax-M3.1-Flash", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.015e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, "reasoning_efforts": [ + "none", "minimal", "low", "medium", @@ -19860,75 +27189,78 @@ "xhigh", "max" ], - "max_output": 16384 + "max_output": 1048576, + "quantization": "fp4" }, { "providerId": "together-ai", - "externalId": "meta-models/Muse-Glimmer-30B", + "externalId": "MiniMaxAI/MiniMax-M3.1-Flash", "pricing": { - "prompt": "0.35e-6", - "completion": "1.5e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.04e-6", + "input_cache_read": "0.015e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": true, - "reasoning_efforts": [ - "minimal", - "low", - "medium", - "high", - "xhigh", - "max" - ], - "max_output": 117964 + "reasoning_efforts": ["none"], + "max_output": 1048576 } ], "pricing": { - "prompt": "0.3e-6", - "completion": "1.2e-6", + "prompt": "0.1e-6", + "completion": "0.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.04e-6", + "input_cache_read": "0.005e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 131072, - "max_output": 16384, + "context_length": 1048576, + "max_output": 524288, "supported_parameters": [ + "messages", + "model", + "stream", + "stream_options", "temperature", - "max_tokens", "top_p", + "max_tokens", + "max_completion_tokens", "frequency_penalty", "presence_penalty", - "response_format", + "seed", + "stop", "tools", "tool_choice", + "reasoning_effort", "reasoning" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false }, { - "id": "muse-image-1.0", - "name": "Muse Image 1.0", - "display_name": "Muse Image 1.0", - "created": 1783382400, - "description": "muse-image-1.0 provided by meta", - "family": "meta", + "id": "minimax-text-01", + "name": "MiniMax Text 01", + "display_name": "MiniMax Text 01", + "created": 1736899200, + "description": "MiniMax-Text-01 is a 456B parameter model with 4M token context using Lightning Attention.", + "family": "minimax", "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["image"], + "input_modalities": ["text"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -19936,35 +27268,32 @@ }, "providers": [ { - "providerId": "meta", - "externalId": "muse-image-1.0", + "providerId": "minimax", + "externalId": "MiniMax-Text-01", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.2e-6", + "completion": "1.1e-6", "image": "0", - "per_image": { - "default": "0.01" - }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": true, + "context_length": 1000000, + "streaming": true, + "vision": false, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": false, + "reasoning": true, + "max_output": 131072 } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.2e-6", + "completion": "1.1e-6", "image": "0", - "per_image": { - "default": "0.01" - }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -19972,7 +27301,8 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 0, + "context_length": 1000000, + "max_output": 131072, "supported_parameters": [ "temperature", "max_tokens", @@ -19989,12 +27319,12 @@ "free": false }, { - "id": "muse-spark-1.1", - "name": "Muse Spark 1.1", - "display_name": "Muse Spark 1.1", - "created": 1783555200, - "description": "muse-spark-1.1 provided by meta", - "family": "meta", + "id": "ministral-14b-2512", + "name": "Ministral 14B", + "display_name": "Ministral 14B", + "created": 1764633600, + "description": "Largest Ministral model optimized for edge and local deployment.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20005,41 +27335,39 @@ }, "providers": [ { - "providerId": "meta", - "externalId": "muse-spark-1.1", + "providerId": "mistral", + "externalId": "ministral-14b-2512", "pricing": { - "prompt": "1.25e-6", - "completion": "4.25e-6", + "prompt": "0.2e-6", + "completion": "0.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.15e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], - "max_output": 131072, - "stability": "beta" + "json_output": true, + "reasoning": false } ], "pricing": { - "prompt": "1.25e-6", - "completion": "4.25e-6", + "prompt": "0.2e-6", + "completion": "0.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.15e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, - "max_output": 131072, + "context_length": 262144, "supported_parameters": [ "temperature", "max_tokens", @@ -20048,20 +27376,19 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false }, { - "id": "muse-spark-1.2", - "name": "Muse Spark 1.2", - "display_name": "Muse Spark 1.2", - "created": 1785974400, - "description": "muse-spark-1.2 provided by meta", - "family": "meta", + "id": "ministral-3b-2512", + "name": "Ministral 3B", + "display_name": "Ministral 3B", + "created": 1764633600, + "description": "Smallest Ministral model for efficient edge deployment.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20072,41 +27399,39 @@ }, "providers": [ { - "providerId": "meta", - "externalId": "muse-spark-1.2", + "providerId": "mistral", + "externalId": "ministral-3b-2512", "pricing": { - "prompt": "1.25e-6", - "completion": "4.25e-6", + "prompt": "0.1e-6", + "completion": "0.1e-6", "image": "0", "request": "0", - "input_cache_read": "0.15e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], - "max_output": 131072, - "stability": "beta" + "json_output": true, + "reasoning": false } ], "pricing": { - "prompt": "1.25e-6", - "completion": "4.25e-6", + "prompt": "0.1e-6", + "completion": "0.1e-6", "image": "0", "request": "0", - "input_cache_read": "0.15e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, - "max_output": 131072, + "context_length": 131072, "supported_parameters": [ "temperature", "max_tokens", @@ -20115,20 +27440,19 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false }, { - "id": "muse-spark-1.2-contributor", - "name": "Muse Spark 1.2 Contributor", - "display_name": "Muse Spark 1.2 Contributor", - "created": 1785974400, - "description": "muse-spark-1.2-contributor provided by meta-contributor", - "family": "meta", + "id": "ministral-8b-2512", + "name": "Ministral 8B", + "display_name": "Ministral 8B", + "created": 1764633600, + "description": "Mid-size Ministral model for edge and local deployment.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20139,41 +27463,39 @@ }, "providers": [ { - "providerId": "meta-contributor", - "externalId": "muse-spark-1.2-contributor", + "providerId": "mistral", + "externalId": "ministral-8b-2512", "pricing": { - "prompt": "0.10e-6", - "completion": "0.20e-6", + "prompt": "0.15e-6", + "completion": "0.15e-6", "image": "0", "request": "0", - "input_cache_read": "0.002e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], - "max_output": 131072, - "stability": "beta" + "json_output": true, + "reasoning": false } ], "pricing": { - "prompt": "0.10e-6", - "completion": "0.20e-6", + "prompt": "0.15e-6", + "completion": "0.15e-6", "image": "0", "request": "0", - "input_cache_read": "0.002e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, - "max_output": 131072, + "context_length": 262144, "supported_parameters": [ "temperature", "max_tokens", @@ -20182,20 +27504,19 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false }, - { - "id": "muse-spark-1.3", - "name": "Muse Spark 1.3", - "display_name": "Muse Spark 1.3", - "created": 1788307200, - "description": "muse-spark-1.3 provided by meta", - "family": "meta", + { + "id": "mistral-large-2512", + "name": "Mistral Large 3", + "display_name": "Mistral Large 3", + "created": 1764633600, + "description": "Mistral's latest flagship model with 675B parameters and MoE architecture.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20206,41 +27527,39 @@ }, "providers": [ { - "providerId": "meta", - "externalId": "muse-spark-1.3", + "providerId": "mistral", + "externalId": "mistral-large-2512", "pricing": { - "prompt": "1.25e-6", - "completion": "4.25e-6", + "prompt": "0.5e-6", + "completion": "1.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.15e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], - "max_output": 1048576, - "stability": "beta" + "json_output": true, + "reasoning": false } ], "pricing": { - "prompt": "1.25e-6", - "completion": "4.25e-6", + "prompt": "0.5e-6", + "completion": "1.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.15e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, - "max_output": 1048576, + "context_length": 262144, "supported_parameters": [ "temperature", "max_tokens", @@ -20249,20 +27568,19 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, - "structured_outputs": true, + "structured_outputs": false, "free": false }, { - "id": "muse-spark-1.3-contributor", - "name": "Muse Spark 1.3 Contributor", - "display_name": "Muse Spark 1.3 Contributor", - "created": 1788307200, - "description": "muse-spark-1.3-contributor provided by meta-contributor", - "family": "meta", + "id": "mistral-large-4", + "name": "Mistral Large 4", + "display_name": "Mistral Large 4", + "created": 1791244800, + "description": "Mistral's open-weight multimodal flagship: a granular Mixture-of-Experts model with 49B active and 1.05T total parameters, plus a 1.6B vision encoder.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20273,41 +27591,41 @@ }, "providers": [ { - "providerId": "meta-contributor", - "externalId": "muse-spark-1.3-contributor", + "providerId": "mistral", + "externalId": "mistral-large-4-0", "pricing": { - "prompt": "0.10e-6", - "completion": "0.20e-6", + "prompt": "1.36e-6", + "completion": "4.18e-6", "image": "0", "request": "0", - "input_cache_read": "0.002e-6", + "input_cache_read": "0.14e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], - "max_output": 1048576, - "stability": "beta" + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "max_temperature": 1.5 } ], "pricing": { - "prompt": "0.10e-6", - "completion": "0.20e-6", + "prompt": "1.36e-6", + "completion": "4.18e-6", "image": "0", "request": "0", - "input_cache_read": "0.002e-6", + "input_cache_read": "0.14e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, - "max_output": 1048576, + "context_length": 1000000, "supported_parameters": [ "temperature", "max_tokens", @@ -20316,22 +27634,21 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, "structured_outputs": true, "free": false }, { - "id": "muse-wonder-1.0", - "name": "Muse Wonder 1.0", - "display_name": "Muse Wonder 1.0", - "created": 1791763200, - "description": "muse-wonder-1.0 provided by meta", - "family": "meta", + "id": "mistral-large-latest", + "name": "Mistral Large Latest", + "display_name": "Mistral Large Latest", + "created": 1764633600, + "description": "Mistral's flagship large model for complex reasoning tasks.", + "family": "mistral", "architecture": { - "input_modalities": ["text", "image"], + "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -20340,41 +27657,39 @@ }, "providers": [ { - "providerId": "meta", - "externalId": "muse-wonder-1.0", + "providerId": "mistral", + "externalId": "mistral-large-latest", "pricing": { - "prompt": "4e-6", - "completion": "20e-6", + "prompt": "0.000004", + "completion": "0.000012", "image": "0", "request": "0", - "input_cache_read": "0.2e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 128000, "streaming": true, - "vision": true, + "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], - "max_output": 1048576, - "stability": "beta" + "json_output": false, + "reasoning": false } ], "pricing": { - "prompt": "4e-6", - "completion": "20e-6", + "prompt": "0.000004", + "completion": "0.000012", "image": "0", "request": "0", - "input_cache_read": "0.2e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, - "max_output": 1048576, + "context_length": 128000, "supported_parameters": [ "temperature", "max_tokens", @@ -20383,20 +27698,19 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], - "json_output": true, - "structured_outputs": true, + "json_output": false, + "structured_outputs": false, "free": false }, { - "id": "nemotron-3-ultra-550b", - "name": "Nemotron 3 Ultra 550B", - "display_name": "Nemotron 3 Ultra 550B", - "created": 1780272000, - "description": "nemotron-3-ultra-550b provided by deepinfra, nebius", - "family": "nvidia", + "id": "mistral-medium-3-5", + "name": "Mistral Medium 3.5", + "display_name": "Mistral Medium 3.5", + "created": 1777593600, + "description": "Mistral's dense 128B instruction-following model for agentic and enterprise workloads, with text and image input.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20407,56 +27721,41 @@ }, "providers": [ { - "providerId": "deepinfra", - "externalId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", - "pricing": { - "prompt": "0.5e-6", - "completion": "2.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.1e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false - }, - { - "providerId": "nebius", - "externalId": "nvidia/Nemotron-3-Ultra-550b-a55b", + "providerId": "mistral", + "externalId": "mistral-medium-3-5", "pricing": { - "prompt": "1.0e-6", - "completion": "3.0e-6", + "prompt": "1.5e-6", + "completion": "7.5e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": true + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "max_temperature": 1.5 } ], "pricing": { - "prompt": "0.5e-6", - "completion": "2.2e-6", + "prompt": "1.5e-6", + "completion": "7.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.1e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1048576, + "context_length": 262144, "supported_parameters": [ "temperature", "max_tokens", @@ -20465,23 +27764,22 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, - "structured_outputs": false, + "structured_outputs": true, "free": false }, { - "id": "o1", - "name": "o1", - "display_name": "o1", - "created": 1726099200, - "description": "o1 provided by openai, azure", - "family": "openai", + "id": "mistral-ocr-latest", + "name": "Mistral OCR", + "display_name": "Mistral OCR", + "created": 1741219200, + "description": "Mistral's OCR model that extracts text, tables, and structure from documents and images as markdown via the /v1/ocr endpoint.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["text"], + "output_modalities": ["ocr"], "tokenizer": "GPT" }, "top_provider": { @@ -20489,58 +27787,41 @@ }, "providers": [ { - "providerId": "openai", - "externalId": "o1", - "pricing": { - "prompt": "15.0e-6", - "completion": "60.0e-6", - "image": "0", - "request": "0", - "input_cache_read": "7.5e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["low", "medium", "high"] - }, - { - "providerId": "azure", - "externalId": "o1", + "providerId": "mistral", + "externalId": "mistral-ocr-latest", "pricing": { - "prompt": "15.0e-6", - "completion": "60.0e-6", + "prompt": "0", + "completion": "0", "image": "0", "request": "0", - "input_cache_read": "7.5e-6", + "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "ocr_page": "0.004" }, - "streaming": true, + "context_length": 0, + "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": true, - "reasoning_efforts": ["low", "medium", "high"] + "json_output": false, + "reasoning": false } ], "pricing": { - "prompt": "15.0e-6", - "completion": "60.0e-6", + "prompt": "0", + "completion": "0", "image": "0", "request": "0", - "input_cache_read": "7.5e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "ocr_page": "0.004", "internal_reasoning": "0" }, - "context_length": 200000, + "context_length": 0, "supported_parameters": [ "temperature", "max_tokens", @@ -20549,21 +27830,19 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], - "json_output": true, - "structured_outputs": true, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "json_output": false, + "structured_outputs": false, + "free": false }, { - "id": "o3", - "name": "o3", - "display_name": "o3", - "created": 1748736000, - "description": "o3 provided by openai, azure", - "family": "openai", + "id": "mistral-small-2506", + "name": "Mistral Small 3.2", + "display_name": "Mistral Small 3.2", + "created": 1750377600, + "description": "Lightweight 24B model for fast, efficient tasks.", + "family": "mistral", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20572,73 +27851,64 @@ "top_provider": { "is_moderated": true }, - "providers": [ - { - "providerId": "openai", - "externalId": "o3", - "pricing": { - "prompt": "2e-6", - "completion": "8e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.5e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": false, - "vision": true, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - }, + "providers": [ { - "providerId": "azure", - "externalId": "o3", + "providerId": "mistral", + "externalId": "mistral-small-2506", "pricing": { - "prompt": "2e-6", - "completion": "8e-6", + "prompt": "0.1e-6", + "completion": "0.3e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 128000, + "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false } ], "pricing": { - "prompt": "2e-6", - "completion": "8e-6", + "prompt": "0.1e-6", + "completion": "0.3e-6", "image": "0", "request": "0", - "input_cache_read": "0.5e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 200000, - "supported_parameters": ["reasoning_effort", "response_format"], + "context_length": 128000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], "json_output": true, - "structured_outputs": true, - "free": false, - "deactivated_at": "2026-12-10T00:00:00.000Z" + "structured_outputs": false, + "free": false }, { - "id": "o3-mini", - "name": "o3 Mini", - "display_name": "o3 Mini", - "created": 1748736000, - "description": "o3-mini provided by openai, azure", - "family": "openai", + "id": "mistral-small-2603", + "name": "Mistral Small 4", + "display_name": "Mistral Small 4", + "created": 1773705600, + "description": "Mistral's hybrid MoE small model (119B total, 6.5B active) unifying instruction, reasoning, and coding with image input.", + "family": "mistral", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -20647,69 +27917,62 @@ }, "providers": [ { - "providerId": "openai", - "externalId": "o3-mini", - "pricing": { - "prompt": "1.1e-6", - "completion": "4.4e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.55e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": false, - "parallelToolCalls": false, - "reasoning": false - }, - { - "providerId": "azure", - "externalId": "o3-mini", + "providerId": "mistral", + "externalId": "mistral-small-2603", "pricing": { - "prompt": "1.1e-6", - "completion": "4.4e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.55e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "max_temperature": 1.5 } ], "pricing": { - "prompt": "1.1e-6", - "completion": "4.4e-6", + "prompt": "0.15e-6", + "completion": "0.6e-6", "image": "0", "request": "0", - "input_cache_read": "0.55e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 200000, - "supported_parameters": ["reasoning_effort", "response_format"], + "context_length": 262144, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], "json_output": true, "structured_outputs": true, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "free": false }, { - "id": "o4-mini", - "name": "o4 Mini", - "display_name": "o4 Mini", - "created": 1744761600, - "description": "o4-mini provided by openai, azure", - "family": "openai", + "id": "muse-glimmer-30b", + "name": "Muse Glimmer 30B", + "display_name": "Muse Glimmer 30B", + "created": 1786320000, + "description": "Meta Superintelligence Labs' dense open-weight multimodal model distilled from Muse Spark, optimized for autonomous agents.", + "family": "meta", "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"], @@ -20720,78 +27983,109 @@ }, "providers": [ { - "providerId": "openai", - "externalId": "o4-mini", + "providerId": "deepinfra", + "externalId": "meta-models/Muse-Glimmer-30B", "pricing": { - "prompt": "1.1e-6", - "completion": "4.4e-6", + "prompt": "0.3e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.275e-6", + "input_cache_read": "0.04e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high"] + "reasoning_efforts": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 16384, + "max_temperature": 1, + "quantization": "bf16" }, { - "providerId": "azure", - "externalId": "o4-mini", + "providerId": "together-ai", + "externalId": "meta-models/Muse-Glimmer-30B", "pricing": { - "prompt": "1.1e-6", - "completion": "4.4e-6", + "prompt": "0.35e-6", + "completion": "1.5e-6", "image": "0", "request": "0", - "input_cache_read": "0.275e-6", + "input_cache_read": "0.04e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, - "reasoning_efforts": ["low", "medium", "high"] + "reasoning_efforts": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 117964, + "max_temperature": 1 } ], "pricing": { - "prompt": "1.1e-6", - "completion": "4.4e-6", + "prompt": "0.3e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.275e-6", + "input_cache_read": "0.04e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 200000, + "context_length": 131072, + "max_output": 16384, "supported_parameters": [ - "reasoning_effort", + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", + "tools", + "tool_choice", "reasoning" ], "json_output": true, "structured_outputs": true, - "free": false, - "deactivated_at": "2026-10-23T00:00:00.000Z" + "free": false }, { - "id": "perplexity-search", - "name": "Perplexity Search", - "display_name": "Perplexity Search", - "created": 1758758400, - "description": "perplexity-search provided by perplexity", - "family": "perplexity", + "id": "muse-image-1.0", + "name": "Muse Image 1.0", + "display_name": "Muse Image 1.0", + "created": 1783382400, + "description": "Meta's agentic image model for generation, editing, multi-reference composition, and iterative refinement.", + "family": "meta", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["search"], + "input_modalities": ["text", "image"], + "output_modalities": ["image"], "tokenizer": "GPT" }, "top_provider": { @@ -20799,30 +28093,37 @@ }, "providers": [ { - "providerId": "perplexity", - "externalId": "web", + "providerId": "meta", + "externalId": "muse-image-1.0", "pricing": { "prompt": "0", "completion": "0", "image": "0", - "request": "0.005", + "per_image": { + "default": "0.01" + }, + "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, "streaming": false, - "vision": false, + "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": true } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", - "request": "0.005", + "per_image": { + "default": "0.01" + }, + "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", @@ -20838,22 +28139,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], "json_output": false, "structured_outputs": false, "free": false }, { - "id": "perplexity-search-fast", - "name": "Perplexity Search Fast", - "display_name": "Perplexity Search Fast", - "created": 1790208000, - "description": "perplexity-search-fast provided by perplexity", - "family": "perplexity", + "id": "muse-spark-1.1", + "name": "Muse Spark 1.1", + "display_name": "Muse Spark 1.1", + "created": 1783555200, + "description": "Meta's multimodal reasoning model built for agentic tool calling, coding, structured output, and long-context workflows with image and video understanding.", + "family": "meta", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["search"], + "input_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -20861,37 +28163,45 @@ }, "providers": [ { - "providerId": "perplexity", - "externalId": "fast", + "providerId": "meta", + "externalId": "muse-spark-1.1", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "1.25e-6", + "completion": "4.25e-6", "image": "0", - "request": "0.001", - "input_cache_read": "0", + "request": "0", + "input_cache_read": "0.15e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": false, + "context_length": 1048576, + "streaming": true, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], + "max_output": 131072, + "stability": "beta" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "1.25e-6", + "completion": "4.25e-6", "image": "0", - "request": "0.001", - "input_cache_read": "0", + "request": "0", + "input_cache_read": "0.15e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 0, + "context_length": 1048576, + "max_output": 131072, "supported_parameters": [ "temperature", "max_tokens", @@ -20900,22 +28210,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false }, { - "id": "qwen-audio-3.0-tts-flash", - "name": "Qwen-Audio-3.0-TTS Flash", - "display_name": "Qwen-Audio-3.0-TTS Flash", - "created": 1784505600, - "description": "qwen-audio-3.0-tts-flash provided by alibaba", - "family": "alibaba", + "id": "muse-spark-1.2", + "name": "Muse Spark 1.2", + "display_name": "Muse Spark 1.2", + "created": 1785974400, + "description": "Meta's latest multimodal reasoning model, improving on Muse Spark 1.1's agentic tool calling, coding, structured output, and long-context workflows with image and video understanding.", + "family": "meta", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["audio"], + "input_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -20923,37 +28234,46 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-audio-3.0-tts-flash", + "providerId": "meta", + "externalId": "muse-spark-1.2", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "1.25e-6", + "completion": "4.25e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.15e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": false, + "context_length": 1048576, + "streaming": true, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], + "max_output": 131072, + "max_temperature": 1, + "stability": "beta" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "1.25e-6", + "completion": "4.25e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.15e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 20000, + "context_length": 1048576, + "max_output": 131072, "supported_parameters": [ "temperature", "max_tokens", @@ -20962,22 +28282,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false }, { - "id": "qwen-audio-3.0-tts-plus", - "name": "Qwen-Audio-3.0-TTS Plus", - "display_name": "Qwen-Audio-3.0-TTS Plus", - "created": 1784505600, - "description": "qwen-audio-3.0-tts-plus provided by alibaba", - "family": "alibaba", + "id": "muse-spark-1.2-contributor", + "name": "Muse Spark 1.2 Contributor", + "display_name": "Muse Spark 1.2 Contributor", + "created": 1785974400, + "description": "A discounted, training-eligible Muse Spark 1.2 variant for prototyping and large-scale experiments.", + "family": "meta", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["audio"], + "input_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -20985,37 +28306,46 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-audio-3.0-tts-plus", + "providerId": "meta-contributor", + "externalId": "muse-spark-1.2-contributor", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.10e-6", + "completion": "0.20e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.002e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, - "vision": false, + "context_length": 1048576, + "streaming": true, + "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], + "max_output": 131072, + "max_temperature": 1, + "stability": "beta" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.10e-6", + "completion": "0.20e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.002e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 20000, + "context_length": 1048576, + "max_output": 131072, "supported_parameters": [ "temperature", "max_tokens", @@ -21024,21 +28354,22 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false }, { - "id": "qwen-flash", - "name": "Qwen Flash", - "display_name": "Qwen Flash", - "created": 1725840000, - "description": "qwen-flash provided by alibaba", - "family": "alibaba", + "id": "muse-spark-1.3", + "name": "Muse Spark 1.3", + "display_name": "Muse Spark 1.3", + "created": 1788307200, + "description": "Meta's agentic reasoning model for long-horizon coding, multi-agent workflows, and reliable instruction following.", + "family": "meta", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -21047,39 +28378,46 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-flash", + "providerId": "meta", + "externalId": "muse-spark-1.3", "pricing": { - "prompt": "0.05e-6", - "completion": "0.4e-6", + "prompt": "1.25e-6", + "completion": "4.25e-6", "image": "0", "request": "0", - "input_cache_read": "0.01e-6", - "input_cache_write": "0.0625e-6", + "input_cache_read": "0.15e-6", + "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1048576, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 32000 + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], + "max_output": 1048576, + "max_temperature": 1, + "stability": "beta" } ], "pricing": { - "prompt": "0.05e-6", - "completion": "0.4e-6", + "prompt": "1.25e-6", + "completion": "4.25e-6", "image": "0", "request": "0", - "input_cache_read": "0.01e-6", - "input_cache_write": "0.0625e-6", + "input_cache_read": "0.15e-6", + "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1000000, - "max_output": 32000, + "context_length": 1048576, + "max_output": 1048576, "supported_parameters": [ "temperature", "max_tokens", @@ -21088,22 +28426,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], "json_output": true, - "structured_outputs": false, + "structured_outputs": true, "free": false }, { - "id": "qwen-image-2.1-pro", - "name": "Qwen Image 2.1 Pro", - "display_name": "Qwen Image 2.1 Pro", - "created": 1789862400, - "description": "qwen-image-2.1-pro provided by alibaba", - "family": "alibaba", + "id": "muse-spark-1.3-contributor", + "name": "Muse Spark 1.3 Contributor", + "display_name": "Muse Spark 1.3 Contributor", + "created": 1788307200, + "description": "A discounted, training-eligible Muse Spark 1.3 variant for prototyping and large-scale experiments.", + "family": "meta", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -21111,45 +28450,46 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-image-2.1-pro", + "providerId": "meta-contributor", + "externalId": "muse-spark-1.3-contributor", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.10e-6", + "completion": "0.20e-6", "image": "0", - "per_image": { - "default": "0.04" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.002e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 1048576, + "streaming": true, "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 4096 + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], + "max_output": 1048576, + "max_temperature": 1, + "stability": "beta" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.10e-6", + "completion": "0.20e-6", "image": "0", - "per_image": { - "default": "0.04" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.002e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 4500, - "max_output": 4096, + "context_length": 1048576, + "max_output": 1048576, "supported_parameters": [ "temperature", "max_tokens", @@ -21158,22 +28498,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false }, { - "id": "qwen-image-2.1-turbo", - "name": "Qwen Image 2.1 Turbo", - "display_name": "Qwen Image 2.1 Turbo", - "created": 1791504000, - "description": "qwen-image-2.1-turbo provided by alibaba", - "family": "alibaba", + "id": "muse-wonder-1.0", + "name": "Muse Wonder 1.0", + "display_name": "Muse Wonder 1.0", + "created": 1791763200, + "description": "Meta's frontier model for coding, long-running agents, and advanced computer use. Plans long tasks, delegates to sub-agents, and recovers from errors.", + "family": "meta", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -21181,45 +28522,46 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-image-2.1-turbo", + "providerId": "meta", + "externalId": "muse-wonder-1.0", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "4e-6", + "completion": "20e-6", "image": "0", - "per_image": { - "default": "0.016" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 1048576, + "streaming": true, "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false, - "max_output": 4096 + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": ["minimal", "low", "medium", "high", "xhigh"], + "max_output": 1048576, + "max_temperature": 1, + "stability": "beta" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "4e-6", + "completion": "20e-6", "image": "0", - "per_image": { - "default": "0.016" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.2e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 4500, - "max_output": 4096, + "context_length": 1048576, + "max_output": 1048576, "supported_parameters": [ "temperature", "max_tokens", @@ -21228,22 +28570,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false - }, - { - "id": "qwen-image-3.0", - "name": "Qwen Image 3.0", - "display_name": "Qwen Image 3.0", - "created": 1785888000, - "description": "qwen-image-3.0 provided by alibaba", - "family": "alibaba", + }, + { + "id": "nemotron-3-ultra-550b", + "name": "Nemotron 3 Ultra 550B", + "display_name": "Nemotron 3 Ultra 550B", + "created": 1780272000, + "description": "NVIDIA's most capable model with 550B parameters for complex reasoning, coding, and multimodal tasks.", + "family": "nvidia", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -21251,45 +28594,63 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-image-3.0", + "providerId": "deepinfra", + "externalId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.5e-6", + "completion": "2.2e-6", "image": "0", - "per_image": { - "default": "0.03" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.1e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 262144, + "streaming": true, "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 4096 + "quantization": "fp4" + }, + { + "providerId": "nebius", + "externalId": "nvidia/Nemotron-3-Ultra-550b-a55b", + "pricing": { + "prompt": "1.0e-6", + "completion": "3.0e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1048576, + "streaming": true, + "vision": false, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "reasoning": true, + "quantization": "fp4", + "deactivated_at": "2026-08-31T00:00:00.000Z" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "0.5e-6", + "completion": "2.2e-6", "image": "0", - "per_image": { - "default": "0.03" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.1e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 4500, - "max_output": 4096, + "context_length": 1048576, "supported_parameters": [ "temperature", "max_tokens", @@ -21298,22 +28659,23 @@ "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, + "json_output": true, "structured_outputs": false, "free": false }, { - "id": "qwen-image-3.0-pro", - "name": "Qwen Image 3.0 Pro", - "display_name": "Qwen Image 3.0 Pro", - "created": 1785888000, - "description": "qwen-image-3.0-pro provided by alibaba", - "family": "alibaba", + "id": "o3", + "name": "o3", + "display_name": "o3", + "created": 1748736000, + "description": "Next-generation reasoning model with enhanced problem-solving capabilities.", + "family": "openai", "architecture": { "input_modalities": ["text", "image"], - "output_modalities": ["text", "image"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -21321,73 +28683,81 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-image-3.0-pro", + "providerId": "openai", + "externalId": "o3", "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "2e-6", + "completion": "8e-6", "image": "0", - "per_image": { - "1K": "0.04", - "2K": "0.075", - "default": "0.075" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.5e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 200000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": false, - "max_output": 4096 + "supported_parameters": ["reasoning_effort", "response_format"], + "deactivated_at": "2026-12-10T00:00:00.000Z" + }, + { + "providerId": "azure", + "externalId": "o3", + "pricing": { + "prompt": "2e-6", + "completion": "8e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 200000, + "streaming": false, + "vision": true, + "cancellation": true, + "tools": false, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "reasoning": false, + "deactivated_at": "2026-09-29T00:00:00.000Z" } ], "pricing": { - "prompt": "0", - "completion": "0", + "prompt": "2e-6", + "completion": "8e-6", "image": "0", - "per_image": { - "1K": "0.04", - "2K": "0.075", - "default": "0.075" - }, "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.5e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 4500, - "max_output": 4096, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", - "tools", - "tool_choice" - ], - "json_output": false, - "structured_outputs": false, - "free": false + "context_length": 200000, + "supported_parameters": ["reasoning_effort", "response_format"], + "json_output": true, + "structured_outputs": true, + "free": false, + "deactivated_at": "2026-12-10T00:00:00.000Z" }, { - "id": "qwen-max", - "name": "Qwen Max", - "display_name": "Qwen Max", - "created": 1757030400, - "description": "qwen-max provided by alibaba", - "family": "alibaba", + "id": "perplexity-search", + "name": "Perplexity Search", + "display_name": "Perplexity Search", + "created": 1758758400, + "description": "Perplexity's standalone Search API. Returns ranked web results with extracted page snippets instead of generated text. Served via the /v1/search endpoint.", + "family": "perplexity", "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], + "input_modalities": ["text"], + "output_modalities": ["search"], "tokenizer": "GPT" }, "top_provider": { @@ -21395,39 +28765,39 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-max", + "providerId": "perplexity", + "externalId": "web", "pricing": { - "prompt": "1.6e-6", - "completion": "6.4e-6", + "prompt": "0", + "completion": "0", "image": "0", - "request": "0", + "request": "0.005", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": true, + "context_length": 0, + "streaming": false, + "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192 + "json_output": false, + "reasoning": false } ], "pricing": { - "prompt": "1.6e-6", - "completion": "6.4e-6", + "prompt": "0", + "completion": "0", "image": "0", - "request": "0", + "request": "0.005", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 32768, - "max_output": 8192, + "context_length": 0, "supported_parameters": [ "temperature", "max_tokens", @@ -21438,20 +28808,20 @@ "tools", "tool_choice" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, { - "id": "qwen-plus", - "name": "Qwen Plus", - "display_name": "Qwen Plus", - "created": 1737763200, - "description": "qwen-plus provided by alibaba", - "family": "alibaba", + "id": "perplexity-search-fast", + "name": "Perplexity Search Fast", + "display_name": "Perplexity Search Fast", + "created": 1790208000, + "description": "Lower-latency, lower-cost variant of Perplexity's Search API. Returns ranked web results with extracted page snippets instead of generated text. Served via the /v1/search endpoint.", + "family": "perplexity", "architecture": { "input_modalities": ["text"], - "output_modalities": ["text"], + "output_modalities": ["search"], "tokenizer": "GPT" }, "top_provider": { @@ -21459,39 +28829,39 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen-plus", + "providerId": "perplexity", + "externalId": "fast", "pricing": { - "prompt": "0.4e-6", - "completion": "1.2e-6", + "prompt": "0", + "completion": "0", "image": "0", - "request": "0", - "input_cache_read": "0.08e-6", - "input_cache_write": "0.5e-6", + "request": "0.001", + "input_cache_read": "0", + "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "context_length": 0, + "streaming": false, "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": false, - "max_output": 32000 + "json_output": false, + "reasoning": false } ], "pricing": { - "prompt": "0.4e-6", - "completion": "1.2e-6", + "prompt": "0", + "completion": "0", "image": "0", - "request": "0", - "input_cache_read": "0.08e-6", - "input_cache_write": "0.5e-6", + "request": "0.001", + "input_cache_read": "0", + "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 131072, - "max_output": 32000, + "context_length": 0, "supported_parameters": [ "temperature", "max_tokens", @@ -21502,20 +28872,20 @@ "tools", "tool_choice" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, { - "id": "qwen-plus-latest", - "name": "Qwen Plus Latest", - "display_name": "Qwen Plus Latest", - "created": 1725840000, - "description": "qwen-plus-latest provided by alibaba", + "id": "qwen-audio-3.0-tts-flash", + "name": "Qwen-Audio-3.0-TTS Flash", + "display_name": "Qwen-Audio-3.0-TTS Flash", + "created": 1784505600, + "description": "Alibaba's low-latency Qwen-Audio-3.0 text-to-speech model optimized for real-time interaction across 16 languages. Generates speech via the /v1/audio/speech endpoint.", "family": "alibaba", "architecture": { "input_modalities": ["text"], - "output_modalities": ["text"], + "output_modalities": ["audio"], "tokenizer": "GPT" }, "top_provider": { @@ -21524,38 +28894,46 @@ "providers": [ { "providerId": "alibaba", - "externalId": "qwen-plus-latest", + "externalId": "qwen-audio-3.0-tts-flash", "pricing": { - "prompt": "0.4e-6", - "completion": "1.2e-6", + "prompt": "0", + "completion": "0", "image": "0", + "input_character": "15e-6", "request": "0", - "input_cache_read": "0.08e-6", - "input_cache_write": "0.5e-6", + "input_cache_read": "0", + "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "context_length": 20000, + "streaming": false, "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 32000 + "supported_voices": [ + "longanhuan_v3.6", + "longjielidou_v3.6", + "loongeva_v3.6", + "loongjohn" + ] } ], "pricing": { - "prompt": "0.4e-6", - "completion": "1.2e-6", + "prompt": "0", + "completion": "0", "image": "0", + "input_character": "15e-6", "request": "0", - "input_cache_read": "0.08e-6", - "input_cache_write": "0.5e-6", + "input_cache_read": "0", + "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1000000, - "max_output": 32000, + "context_length": 20000, "supported_parameters": [ "temperature", "max_tokens", @@ -21566,20 +28944,20 @@ "tools", "tool_choice" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, { - "id": "qwen3-14b", - "name": "Qwen3 14B", - "display_name": "Qwen3 14B", - "created": 1745798400, - "description": "qwen3-14b provided by nebius, greenference", + "id": "qwen-audio-3.0-tts-plus", + "name": "Qwen-Audio-3.0-TTS Plus", + "display_name": "Qwen-Audio-3.0-TTS Plus", + "created": 1784505600, + "description": "Alibaba's high-quality Qwen-Audio-3.0 text-to-speech model with natural prosody and contextually appropriate intonation across 16 languages. Generates speech via the /v1/audio/speech endpoint.", "family": "alibaba", "architecture": { "input_modalities": ["text"], - "output_modalities": ["text"], + "output_modalities": ["audio"], "tokenizer": "GPT" }, "top_provider": { @@ -21587,51 +28965,34 @@ }, "providers": [ { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-14B", + "providerId": "alibaba", + "externalId": "qwen-audio-3.0-tts-plus", "pricing": { - "prompt": "0.08e-6", - "completion": "0.24e-6", + "prompt": "0", + "completion": "0", "image": "0", + "input_character": "20e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "context_length": 20000, + "streaming": false, "vision": false, "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192 - }, - { - "providerId": "greenference", - "externalId": "greenference/qwen3-14b", - "pricing": { - "prompt": "0.000000076", - "completion": "0.000000228", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": false, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 8192, - "stability": "stable" + "supported_voices": ["longanlingxin", "longanlufeng"] } ], "pricing": { - "prompt": "0.000000076", - "completion": "0.000000228", + "prompt": "0", + "completion": "0", "image": "0", + "input_character": "20e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -21639,8 +29000,7 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 32768, - "max_output": 8192, + "context_length": 20000, "supported_parameters": [ "temperature", "max_tokens", @@ -21651,16 +29011,16 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, + "json_output": false, + "structured_outputs": false, "free": false }, { - "id": "qwen3-235b-a22b-fp8", - "name": "Qwen3 235B A22B FP8", - "display_name": "Qwen3 235B A22B FP8", - "created": 1745798400, - "description": "qwen3-235b-a22b-fp8 provided by novita", + "id": "qwen-flash", + "name": "Qwen Flash", + "display_name": "Qwen Flash", + "created": 1725840000, + "description": "Fast, cost-effective Qwen for high-volume tasks.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -21672,40 +29032,198 @@ }, "providers": [ { - "providerId": "novita", - "externalId": "qwen/qwen3-235b-a22b-fp8", + "providerId": "alibaba", + "externalId": "qwen-flash", "pricing": { - "prompt": "0.2e-6", - "completion": "0.8e-6", + "prompt": "0.05e-6", + "completion": "0.4e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.05e-6", + "completion": "0.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.05e-6", + "completion": "0.4e-6", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.25e-6", + "completion": "2.0e-6", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 32000, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.05e-6", + "completion": "0.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.05e-6", + "completion": "0.4e-6", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.25e-6", + "completion": "2.0e-6", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 32000, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.05e-6", + "completion": "0.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.05e-6", + "completion": "0.4e-6", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.25e-6", + "completion": "2.0e-6", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 32000, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.022e-6", + "completion": "0.216e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0044e-6", + "input_cache_read_explicit": "0.0022e-6", + "input_cache_write": "0.0275e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "0.022e-6", + "completion": "0.216e-6", + "input_cache_read": "0.0044e-6", + "input_cache_read_explicit": "0.0022e-6", + "input_cache_write": "0.0275e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.087e-6", + "completion": "0.861e-6", + "input_cache_read": "0.017e-6", + "input_cache_read_explicit": "0.0087e-6", + "input_cache_write": "0.10875e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.173e-6", + "completion": "1.721e-6", + "input_cache_read": "0.035e-6", + "input_cache_read_explicit": "0.0173e-6", + "input_cache_write": "0.21625e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 32000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 20000, - "stability": "unstable" + "max_output": 32000 } ], "pricing": { - "prompt": "0.2e-6", - "completion": "0.8e-6", + "prompt": "0.05e-6", + "completion": "0.4e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", + "input_cache_read": "0.01e-6", + "input_cache_read_explicit": "0.005e-6", + "input_cache_write": "0.0625e-6", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 40960, - "max_output": 20000, + "context_length": 1000000, + "max_output": 32000, "supported_parameters": [ "temperature", "max_tokens", @@ -21721,15 +29239,15 @@ "free": false }, { - "id": "qwen3-235b-a22b-instruct-2507", - "name": "Qwen3 235B A22B Instruct 2507", - "display_name": "Qwen3 235B A22B Instruct 2507", - "created": 1753056000, - "description": "qwen3-235b-a22b-instruct-2507 provided by nebius, cerebras, novita, vertex-openai", + "id": "qwen-image-2.1-pro", + "name": "Qwen Image 2.1 Pro", + "display_name": "Qwen Image 2.1 Pro", + "created": 1789862400, + "description": "Alibaba's Qwen Image 2.1 Pro model for text-to-image generation and multi-image editing with native transparent output.", "family": "alibaba", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], + "input_modalities": ["text", "image"], + "output_modalities": ["text", "image"], "tokenizer": "GPT" }, "top_provider": { @@ -21737,91 +29255,38 @@ }, "providers": [ { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-235B-A22B-Instruct-2507", - "pricing": { - "prompt": "0.2e-6", - "completion": "0.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192, - "stability": "unstable" - }, - { - "providerId": "cerebras", - "externalId": "qwen-3-235b-a22b-instruct-2507", - "pricing": { - "prompt": "0.6e-6", - "completion": "1.2e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192 - }, - { - "providerId": "novita", - "externalId": "qwen/qwen3-235b-a22b-instruct-2507", - "pricing": { - "prompt": "0.09e-6", - "completion": "0.58e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 16384 - }, - { - "providerId": "vertex-openai", - "externalId": "qwen/qwen3-235b-a22b-instruct-2507-maas", + "providerId": "alibaba", + "externalId": "qwen-image-2.1-pro", "pricing": { - "prompt": "0.22e-6", - "completion": "0.88e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "default": "0.04" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": false, + "context_length": 4500, + "streaming": false, + "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 32768 + "max_output": 4096 } ], "pricing": { - "prompt": "0.09e-6", - "completion": "0.58e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "default": "0.04" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -21829,30 +29294,32 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 262144, - "max_output": 8192, + "context_length": 4500, + "max_output": 4096, "supported_parameters": [ "temperature", "max_tokens", "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", "tool_choice" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, { - "id": "qwen3-235b-a22b-thinking-2507", - "name": "Qwen3 235B A22B Thinking 2507", - "display_name": "Qwen3 235B A22B Thinking 2507", - "created": 1753401600, - "description": "qwen3-235b-a22b-thinking-2507 provided by nebius, novita", + "id": "qwen-image-2.1-turbo", + "name": "Qwen Image 2.1 Turbo", + "display_name": "Qwen Image 2.1 Turbo", + "created": 1791504000, + "description": "Alibaba's cost-effective Qwen Image 2.1 Turbo model for fast text-to-image generation and multi-image editing with native transparent output.", "family": "alibaba", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], + "input_modalities": ["text", "image"], + "output_modalities": ["text", "image"], "tokenizer": "GPT" }, "top_provider": { @@ -21860,51 +29327,38 @@ }, "providers": [ { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-235B-A22B-Thinking-2507", - "pricing": { - "prompt": "0.2e-6", - "completion": "0.6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 8192, - "stability": "unstable" - }, - { - "providerId": "novita", - "externalId": "qwen/qwen3-235b-a22b-thinking-2507", + "providerId": "alibaba", + "externalId": "qwen-image-2.1-turbo", "pricing": { - "prompt": "0.3e-6", - "completion": "3e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "default": "0.016" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": false, + "context_length": 4500, + "streaming": false, + "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 32768 + "max_output": 4096 } ], "pricing": { - "prompt": "0.3e-6", - "completion": "3e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "default": "0.016" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -21912,34 +29366,32 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 262000, - "max_output": 32768, + "context_length": 4500, + "max_output": 4096, "supported_parameters": [ "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty", - "stop", - "stream", "response_format", "tools", - "reasoning" + "tool_choice" ], "json_output": false, "structured_outputs": false, "free": false }, { - "id": "qwen3-30b-a3b", - "name": "Qwen3 30B A3B", - "display_name": "Qwen3 30B A3B", - "created": 1745798400, - "description": "qwen3-30b-a3b provided by nebius, greenference", + "id": "qwen-image-3.0", + "name": "Qwen Image 3.0", + "display_name": "Qwen Image 3.0", + "created": 1785888000, + "description": "Alibaba's third-generation Qwen image model for text-to-image generation and image editing with strong text rendering.", "family": "alibaba", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], + "input_modalities": ["text", "image"], + "output_modalities": ["text", "image"], "tokenizer": "GPT" }, "top_provider": { @@ -21947,51 +29399,38 @@ }, "providers": [ { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-30B-A3B", + "providerId": "alibaba", + "externalId": "qwen-image-3.0", "pricing": { - "prompt": "0.1e-6", - "completion": "0.3e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "default": "0.03" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": false, + "context_length": 4500, + "streaming": false, + "vision": true, "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192 - }, - { - "providerId": "greenference", - "externalId": "greenference/qwen3-30b-a3b", - "pricing": { - "prompt": "0.000000095", - "completion": "0.000000285", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": false, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 4096, - "stability": "stable" + "max_output": 4096 } ], "pricing": { - "prompt": "0.000000095", - "completion": "0.000000285", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "default": "0.03" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -21999,7 +29438,7 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 32768, + "context_length": 4500, "max_output": 4096, "supported_parameters": [ "temperature", @@ -22011,20 +29450,20 @@ "tools", "tool_choice" ], - "json_output": true, - "structured_outputs": true, + "json_output": false, + "structured_outputs": false, "free": false }, { - "id": "qwen3-32b", - "name": "Qwen3 32B", - "display_name": "Qwen3 32B", - "created": 1745798400, - "description": "qwen3-32b provided by nebius, cerebras, scx-ai", + "id": "qwen-image-3.0-pro", + "name": "Qwen Image 3.0 Pro", + "display_name": "Qwen Image 3.0 Pro", + "created": 1785888000, + "description": "Alibaba's flagship third-generation Qwen image model for highest quality text-to-image generation and image editing.", "family": "alibaba", "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], + "input_modalities": ["text", "image"], + "output_modalities": ["text", "image"], "tokenizer": "GPT" }, "top_provider": { @@ -22032,71 +29471,42 @@ }, "providers": [ { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-32B", - "pricing": { - "prompt": "0.1e-6", - "completion": "0.3e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192 - }, - { - "providerId": "cerebras", - "externalId": "qwen-3-32b", + "providerId": "alibaba", + "externalId": "qwen-image-3.0-pro", "pricing": { - "prompt": "0.4e-6", - "completion": "0.8e-6", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "1K": "0.04", + "2K": "0.075", + "default": "0.075" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, - "vision": false, + "context_length": 4500, + "streaming": false, + "vision": true, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 8192 - }, - { - "providerId": "scx-ai", - "externalId": "Qwen3-32B", - "pricing": { - "prompt": "0.00000036", - "completion": "0.00000087", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 8192, - "stability": "stable" + "max_output": 4096 } ], "pricing": { - "prompt": "0.00000036", - "completion": "0.00000087", + "prompt": "0", + "completion": "0", "image": "0", + "per_image": { + "1K": "0.04", + "2K": "0.075", + "default": "0.075" + }, "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -22104,30 +29514,31 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 40960, - "max_output": 8192, + "context_length": 4500, + "max_output": 4096, "supported_parameters": [ "temperature", "max_tokens", "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], - "json_output": true, + "json_output": false, "structured_outputs": false, "free": false }, { - "id": "qwen3-coder-30b-a3b-instruct", - "name": "Qwen3 Coder 30B A3B Instruct", - "display_name": "Qwen3 Coder 30B A3B Instruct", - "created": 1753920000, - "description": "qwen3-coder-30b-a3b-instruct provided by nebius, novita", + "id": "qwen-max", + "name": "Qwen Max", + "display_name": "Qwen Max", + "created": 1757030400, + "description": "Alibaba's flagship Qwen model with vision and tool support.", "family": "alibaba", "architecture": { - "input_modalities": ["text"], + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -22136,49 +29547,63 @@ }, "providers": [ { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-Coder-30B-A3B-Instruct", + "providerId": "alibaba", + "externalId": "qwen-max", "pricing": { - "prompt": "0.1e-6", - "completion": "0.3e-6", + "prompt": "1.6e-6", + "completion": "6.4e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "1.6e-6", + "completion": "6.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 32768, + "max_output": 8192, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.345e-6", + "completion": "1.377e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 32768, + "max_output": 8192, + "streaming": true + } + ], + "context_length": 32768, "streaming": true, - "vision": false, + "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 8192 - }, - { - "providerId": "novita", - "externalId": "qwen/qwen3-coder-30b-a3b-instruct", - "pricing": { - "prompt": "0.07e-6", - "completion": "0.27e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 } ], "pricing": { - "prompt": "0.07e-6", - "completion": "0.27e-6", + "prompt": "1.6e-6", + "completion": "6.4e-6", "image": "0", "request": "0", "input_cache_read": "0", @@ -22187,8 +29612,8 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 262000, - "max_output": 32768, + "context_length": 32768, + "max_output": 8192, "supported_parameters": [ "temperature", "max_tokens", @@ -22203,119 +29628,275 @@ "structured_outputs": false, "free": false }, - { - "id": "qwen3-coder-480b-a35b-instruct", - "name": "Qwen3 Coder 480B A35B Instruct", - "display_name": "Qwen3 Coder 480B A35B Instruct", - "created": 1738281600, - "description": "qwen3-coder-480b-a35b-instruct provided by nebius, novita, vertex-openai", - "family": "alibaba", - "architecture": { - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ - { - "providerId": "nebius", - "externalId": "Qwen/Qwen3-Coder-480B-A35B-Instruct", - "pricing": { - "prompt": "0.4e-6", - "completion": "1.8e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 8192, - "stability": "unstable" - }, - { - "providerId": "novita", - "externalId": "qwen/qwen3-coder-480b-a35b-instruct", - "pricing": { - "prompt": "0.38e-6", - "completion": "1.55e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": false, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 65536, - "stability": "unstable" - }, + { + "id": "qwen-plus", + "name": "Qwen Plus", + "display_name": "Qwen Plus", + "created": 1737763200, + "description": "Mid-tier Qwen model balancing speed and capability.", + "family": "alibaba", + "architecture": { + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ { - "providerId": "vertex-openai", - "externalId": "qwen/qwen3-coder-480b-a35b-instruct-maas", + "providerId": "alibaba", + "externalId": "qwen-plus", "pricing": { - "prompt": "0.22e-6", - "completion": "1.8e-6", + "prompt": "0.4e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.022e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.4e-6", + "completion": "1.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "context_length": 131072, + "max_output": 32000, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.4e-6", + "completion": "1.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "context_length": 131072, + "max_output": 32000, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.115e-6", + "completion": "0.287e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.023e-6", + "input_cache_read_explicit": "0.0115e-6", + "input_cache_write": "0.14375e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.115e-6", + "completion": "0.287e-6", + "input_cache_read": "0.023e-6", + "input_cache_read_explicit": "0.0115e-6", + "input_cache_write": "0.14375e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.345e-6", + "completion": "0.861e-6", + "input_cache_read": "0.069e-6", + "input_cache_read_explicit": "0.0345e-6", + "input_cache_write": "0.43125e-6" + } + ] + }, + "context_length": 131072, + "max_output": 32000, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.115e-6", + "completion": "0.287e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.023e-6", + "input_cache_read_explicit": "0.0115e-6", + "input_cache_write": "0.14375e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "0.115e-6", + "completion": "0.287e-6", + "input_cache_read": "0.023e-6", + "input_cache_read_explicit": "0.0115e-6", + "input_cache_write": "0.14375e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.345e-6", + "completion": "2.868e-6", + "input_cache_read": "0.069e-6", + "input_cache_read_explicit": "0.0345e-6", + "input_cache_write": "0.43125e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.689e-6", + "completion": "6.881e-6", + "input_cache_read": "0.138e-6", + "input_cache_read_explicit": "0.0689e-6", + "input_cache_write": "0.86125e-6" + } + ] + }, + "context_length": 131072, + "max_output": 32000, + "streaming": true + } + ], + "context_length": 131072, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 65536 + "max_output": 32000 } ], "pricing": { - "prompt": "0.38e-6", - "completion": "1.55e-6", + "prompt": "0.4e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ], "internal_reasoning": "0" }, - "context_length": 262144, - "max_output": 65536, + "context_length": 131072, + "max_output": 32000, "supported_parameters": [ "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty", - "stop", - "stream", "response_format", - "tools" + "tools", + "tool_choice" ], "json_output": true, "structured_outputs": false, "free": false }, { - "id": "qwen3-coder-flash", - "name": "Qwen3 Coder Flash", - "display_name": "Qwen3 Coder Flash", - "created": 1753142400, - "description": "qwen3-coder-flash provided by alibaba", + "id": "qwen-plus-latest", + "name": "Qwen Plus Latest", + "display_name": "Qwen Plus Latest", + "created": 1725840000, + "description": "Updated Qwen Plus with extended context support.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -22328,38 +29909,165 @@ "providers": [ { "providerId": "alibaba", - "externalId": "qwen3-coder-flash", + "externalId": "qwen-plus-latest", "pricing": { - "prompt": "0.3e-6", - "completion": "1.5e-6", + "prompt": "0.4e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.06e-6", - "input_cache_write": "0.375e-6", - "input_cache_write_1h": "0" - }, + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.4e-6", + "completion": "1.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 32000, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.115e-6", + "completion": "0.287e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.023e-6", + "input_cache_read_explicit": "0.0115e-6", + "input_cache_write": "0.14375e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "0.115e-6", + "completion": "0.287e-6", + "input_cache_read": "0.023e-6", + "input_cache_read_explicit": "0.0115e-6", + "input_cache_write": "0.14375e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.345e-6", + "completion": "2.868e-6", + "input_cache_read": "0.069e-6", + "input_cache_read_explicit": "0.0345e-6", + "input_cache_write": "0.43125e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.689e-6", + "completion": "6.881e-6", + "input_cache_read": "0.138e-6", + "input_cache_read_explicit": "0.0689e-6", + "input_cache_write": "0.86125e-6" + } + ] + }, + "context_length": 1000000, + "max_output": 32000, + "streaming": true + } + ], + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 65536 + "max_output": 32000 } ], "pricing": { - "prompt": "0.3e-6", - "completion": "1.5e-6", + "prompt": "0.4e-6", + "completion": "1.2e-6", "image": "0", "request": "0", - "input_cache_read": "0.06e-6", - "input_cache_write": "0.375e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.2e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "3.6e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ], "internal_reasoning": "0" }, - "context_length": 997952, - "max_output": 65536, + "context_length": 1000000, + "max_output": 32000, "supported_parameters": [ "temperature", "max_tokens", @@ -22375,11 +30083,11 @@ "free": false }, { - "id": "qwen3-coder-next", - "name": "Qwen3 Coder Next", - "display_name": "Qwen3 Coder Next", - "created": 1770163200, - "description": "qwen3-coder-next provided by embercloud", + "id": "qwen3-14b", + "name": "Qwen3 14B", + "display_name": "Qwen3 14B", + "created": 1745798400, + "description": "Mid-size Qwen 3 model.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -22391,70 +30099,96 @@ }, "providers": [ { - "providerId": "embercloud", - "externalId": "qwen3-coder-next", + "providerId": "nebius", + "externalId": "Qwen/Qwen3-14B", "pricing": { - "prompt": "0.108e-6", - "completion": "0.675e-6", + "prompt": "0.08e-6", + "completion": "0.24e-6", "image": "0", "request": "0", - "input_cache_read": "0.06e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, - "max_output": 262144 + "max_output": 8192, + "deactivated_at": "2025-11-03T00:00:00.000Z" + }, + { + "providerId": "greenference", + "externalId": "greenference/qwen3-14b", + "pricing": { + "prompt": "0.000000076", + "completion": "0.000000228", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.2" + }, + "context_length": 16384, + "streaming": true, + "vision": false, + "audio": false, + "cancellation": false, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": false, + "reasoning_max_tokens": false, + "max_output": 8192, + "quantization": "fp8", + "stability": "stable" } ], "pricing": { - "prompt": "0.108e-6", - "completion": "0.675e-6", + "prompt": "0.000000076", + "completion": "0.000000228", "image": "0", "request": "0", - "input_cache_read": "0.06e-6", + "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "discount": "0.2", "internal_reasoning": "0" }, - "context_length": 262144, - "max_output": 262144, + "context_length": 32768, + "max_output": 8192, "supported_parameters": [ - "messages", - "model", - "stream", - "stream_options", "temperature", - "top_p", "max_tokens", - "max_completion_tokens", - "seed", - "stop", + "top_p", + "frequency_penalty", + "presence_penalty", "response_format", "tools", - "parallel_tool_calls" + "tool_choice" ], - "json_output": false, - "structured_outputs": false, - "free": false, - "deprecated_at": "2026-10-21T00:00:00.000Z", - "deactivated_at": "2026-10-28T00:00:00.000Z" + "json_output": true, + "structured_outputs": true, + "free": false }, { - "id": "qwen3-embedding-0.6b", - "name": "Qwen3 Embedding 0.6B", - "display_name": "Qwen3 Embedding 0.6B", - "created": 1749081600, - "description": "qwen3-embedding-0.6b provided by deepinfra", + "id": "qwen3-30b-a3b", + "name": "Qwen3 30B A3B", + "display_name": "Qwen3 30B A3B", + "created": 1745798400, + "description": "Mid-size Qwen 3 MoE model.", "family": "alibaba", "architecture": { "input_modalities": ["text"], - "output_modalities": ["embedding"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -22462,37 +30196,72 @@ }, "providers": [ { - "providerId": "deepinfra", - "externalId": "Qwen/Qwen3-Embedding-0.6B", + "providerId": "nebius", + "externalId": "Qwen/Qwen3-30B-A3B", "pricing": { - "prompt": "0.01e-6", - "completion": "0", + "prompt": "0.1e-6", + "completion": "0.3e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 32768, + "streaming": true, "vision": false, "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "reasoning": false, + "max_output": 8192, + "deactivated_at": "2025-11-03T00:00:00.000Z" + }, + { + "providerId": "greenference", + "externalId": "greenference/qwen3-30b-a3b", + "pricing": { + "prompt": "0.000000095", + "completion": "0.000000285", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "discount": "0.2" + }, + "context_length": 8192, + "streaming": true, + "vision": false, + "audio": false, + "cancellation": false, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "structured_outputs": true, + "web_search": false, + "reasoning": false, + "reasoning_max_tokens": false, + "max_output": 4096, + "quantization": "fp8", + "stability": "stable" } ], "pricing": { - "prompt": "0.01e-6", - "completion": "0", + "prompt": "0.000000095", + "completion": "0.000000285", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "discount": "0.2", "internal_reasoning": "0" }, "context_length": 32768, + "max_output": 4096, "supported_parameters": [ "temperature", "max_tokens", @@ -22503,20 +30272,20 @@ "tools", "tool_choice" ], - "json_output": false, - "structured_outputs": false, + "json_output": true, + "structured_outputs": true, "free": false }, { - "id": "qwen3-embedding-8b", - "name": "Qwen3 Embedding 8B", - "display_name": "Qwen3 Embedding 8B", - "created": 1749081600, - "description": "qwen3-embedding-8b provided by nebius, deepinfra", + "id": "qwen3-32b", + "name": "Qwen3 32B", + "display_name": "Qwen3 32B", + "created": 1745798400, + "description": "Mid-size Qwen 3 model.", "family": "alibaba", "architecture": { "input_modalities": ["text"], - "output_modalities": ["embedding"], + "output_modalities": ["text"], "tokenizer": "GPT" }, "top_provider": { @@ -22525,46 +30294,91 @@ "providers": [ { "providerId": "nebius", - "externalId": "Qwen/Qwen3-Embedding-8B", + "externalId": "Qwen/Qwen3-32B", "pricing": { - "prompt": "0.01e-6", - "completion": "0", + "prompt": "0.1e-6", + "completion": "0.3e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 40960, + "streaming": true, "vision": false, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "max_output": 8192, + "quantization": "fp8", + "deactivated_at": "2026-08-31T00:00:00.000Z" + }, + { + "providerId": "cerebras", + "externalId": "qwen-3-32b", + "pricing": { + "prompt": "0.4e-6", + "completion": "0.8e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 32768, + "streaming": true, + "vision": false, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "reasoning": false, + "max_output": 8192, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "response_format", + "tools", + "tool_choice" + ], + "deactivated_at": "2026-02-16T00:00:00.000Z" }, { - "providerId": "deepinfra", - "externalId": "Qwen/Qwen3-Embedding-8B", + "providerId": "scx-ai", + "externalId": "Qwen3-32B", "pricing": { - "prompt": "0.01e-6", - "completion": "0", + "prompt": "0.00000036", + "completion": "0.00000087", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": false, + "context_length": 32768, + "streaming": true, "vision": false, - "cancellation": true, - "tools": false, + "audio": false, + "cancellation": false, + "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "structured_outputs": false, + "web_search": false, + "reasoning": true, + "reasoning_max_tokens": false, + "max_output": 8192, + "quantization": "bf16", + "stability": "stable" } ], "pricing": { - "prompt": "0.01e-6", - "completion": "0", + "prompt": "0.00000036", + "completion": "0.00000087", "image": "0", "request": "0", "input_cache_read": "0", @@ -22574,29 +30388,29 @@ "internal_reasoning": "0" }, "context_length": 40960, + "max_output": 8192, "supported_parameters": [ "temperature", "max_tokens", "top_p", - "frequency_penalty", - "presence_penalty", "response_format", "tools", - "tool_choice" + "tool_choice", + "reasoning" ], - "json_output": false, + "json_output": true, "structured_outputs": false, "free": false }, { - "id": "qwen3-max", - "name": "Qwen3 Max", - "display_name": "Qwen3 Max", - "created": 1758672000, - "description": "qwen3-max provided by alibaba, novita", + "id": "qwen3-coder-flash", + "name": "Qwen3 Coder Flash", + "display_name": "Qwen3 Coder Flash", + "created": 1753142400, + "description": "Fast, cost-effective Qwen 3 model for code generation.", "family": "alibaba", "architecture": { - "input_modalities": ["text", "image"], + "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "GPT" }, @@ -22606,57 +30420,259 @@ "providers": [ { "providerId": "alibaba", - "externalId": "qwen3-max-preview", - "pricing": { - "prompt": "1.2e-6", - "completion": "6e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.24e-6", - "input_cache_write": "1.5e-6", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": true, - "max_output": 32800 - }, - { - "providerId": "novita", - "externalId": "qwen/qwen3-max", + "externalId": "qwen3-coder-flash", "pricing": { - "prompt": "0.845e-6", - "completion": "3.38e-6", + "prompt": "0.3e-6", + "completion": "1.5e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.3e-6", + "completion": "1.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.3e-6", + "completion": "1.5e-6", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.5e-6", + "completion": "2.5e-6", + "input_cache_read": "0.1e-6", + "input_cache_read_explicit": "0.05e-6", + "input_cache_write": "0.625e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.8e-6", + "completion": "4.0e-6", + "input_cache_read": "0.16e-6", + "input_cache_read_explicit": "0.08e-6", + "input_cache_write": "1.0e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.6e-6", + "completion": "9.6e-6", + "input_cache_read": "0.32e-6", + "input_cache_read_explicit": "0.16e-6", + "input_cache_write": "2.0e-6" + } + ] + }, + "context_length": 997952, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.3e-6", + "completion": "1.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.3e-6", + "completion": "1.5e-6", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.5e-6", + "completion": "2.5e-6", + "input_cache_read": "0.1e-6", + "input_cache_read_explicit": "0.05e-6", + "input_cache_write": "0.625e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.8e-6", + "completion": "4.0e-6", + "input_cache_read": "0.16e-6", + "input_cache_read_explicit": "0.08e-6", + "input_cache_write": "1.0e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.6e-6", + "completion": "9.6e-6", + "input_cache_read": "0.32e-6", + "input_cache_read_explicit": "0.16e-6", + "input_cache_write": "2.0e-6" + } + ] + }, + "context_length": 997952, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.144e-6", + "completion": "0.574e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0144e-6", + "input_cache_write": "0.18e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.144e-6", + "completion": "0.574e-6", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0144e-6", + "input_cache_write": "0.18e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.24e-6", + "completion": "0.957e-6", + "input_cache_read": "0.048e-6", + "input_cache_read_explicit": "0.024e-6", + "input_cache_write": "0.3e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.384e-6", + "completion": "1.53e-6", + "input_cache_read": "0.077e-6", + "input_cache_read_explicit": "0.0384e-6", + "input_cache_write": "0.48e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.768e-6", + "completion": "3.67e-6", + "input_cache_read": "0.154e-6", + "input_cache_read_explicit": "0.0768e-6", + "input_cache_write": "0.96e-6" + } + ] + }, + "context_length": 997952, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.144e-6", + "completion": "0.574e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0144e-6", + "input_cache_write": "0.18e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.144e-6", + "completion": "0.574e-6", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0144e-6", + "input_cache_write": "0.18e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.216e-6", + "completion": "0.861e-6", + "input_cache_read": "0.043e-6", + "input_cache_read_explicit": "0.0216e-6", + "input_cache_write": "0.27e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.359e-6", + "completion": "1.434e-6", + "input_cache_read": "0.072e-6", + "input_cache_read_explicit": "0.0359e-6", + "input_cache_write": "0.44875e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.717e-6", + "completion": "3.584e-6", + "input_cache_read": "0.143e-6", + "input_cache_read_explicit": "0.0717e-6", + "input_cache_write": "0.89625e-6" + } + ] + }, + "context_length": 997952, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 997952, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 65536 } ], "pricing": { - "prompt": "0.845e-6", - "completion": "3.38e-6", + "prompt": "0.3e-6", + "completion": "1.5e-6", "image": "0", "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 262144, + "context_length": 997952, "max_output": 65536, "supported_parameters": [ "temperature", @@ -22666,23 +30682,22 @@ "presence_penalty", "response_format", "tools", - "tool_choice", - "reasoning" + "tool_choice" ], "json_output": true, "structured_outputs": false, "free": false }, { - "id": "qwen3-next-80b-a3b-instruct", - "name": "Qwen3 Next 80B A3B Instruct", - "display_name": "Qwen3 Next 80B A3B Instruct", - "created": 1757462400, - "description": "qwen3-next-80b-a3b-instruct provided by alibaba, novita, vertex-openai", + "id": "qwen3-embedding-0.6b", + "name": "Qwen3 Embedding 0.6B", + "display_name": "Qwen3 Embedding 0.6B", + "created": 1749081600, + "description": "Compact Qwen3 embedding model with 32K context and configurable output dimensions (32–1024) via Matryoshka representation learning, supporting 100+ languages.", "family": "alibaba", "architecture": { "input_modalities": ["text"], - "output_modalities": ["text"], + "output_modalities": ["embedding"], "tokenizer": "GPT" }, "top_provider": { @@ -22690,69 +30705,116 @@ }, "providers": [ { - "providerId": "alibaba", - "externalId": "qwen3-next-80b-a3b-instruct", + "providerId": "deepinfra", + "externalId": "Qwen/Qwen3-Embedding-0.6B", "pricing": { - "prompt": "0.5e-6", - "completion": "2e-6", + "prompt": "0.01e-6", + "completion": "0", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "context_length": 32768, + "streaming": false, "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - }, + "json_output": false, + "reasoning": false + } + ], + "pricing": { + "prompt": "0.01e-6", + "completion": "0", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 32768, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false + }, + { + "id": "qwen3-embedding-8b", + "name": "Qwen3 Embedding 8B", + "display_name": "Qwen3 Embedding 8B", + "created": 1749081600, + "description": "Qwen3 embedding model with 32K context and configurable output dimensions (32–4096) via Matryoshka representation learning. No. 1 on the MTEB multilingual leaderboard as of June 2025 (score 70.58), supporting 100+ languages.", + "family": "alibaba", + "architecture": { + "input_modalities": ["text"], + "output_modalities": ["embedding"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ { - "providerId": "novita", - "externalId": "qwen/qwen3-next-80b-a3b-instruct", + "providerId": "nebius", + "externalId": "Qwen/Qwen3-Embedding-8B", "pricing": { - "prompt": "0.15e-6", - "completion": "1.5e-6", + "prompt": "0.01e-6", + "completion": "0", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "context_length": 40960, + "streaming": false, "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 32768 + "deactivated_at": "2026-08-31T00:00:00.000Z" }, { - "providerId": "vertex-openai", - "externalId": "qwen/qwen3-next-80b-a3b-instruct-maas", + "providerId": "deepinfra", + "externalId": "Qwen/Qwen3-Embedding-8B", "pricing": { - "prompt": "0.15e-6", - "completion": "1.2e-6", + "prompt": "0.01e-6", + "completion": "0", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, - "streaming": true, + "context_length": 32768, + "streaming": false, "vision": false, "cancellation": true, - "tools": true, + "tools": false, "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 + "json_output": false, + "reasoning": false } ], "pricing": { - "prompt": "0.15e-6", - "completion": "1.5e-6", + "prompt": "0.01e-6", + "completion": "0", "image": "0", "request": "0", "input_cache_read": "0", @@ -22761,8 +30823,7 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 131072, - "max_output": 32768, + "context_length": 40960, "supported_parameters": [ "temperature", "max_tokens", @@ -22782,7 +30843,7 @@ "name": "Qwen3 Reranker 0.6B", "display_name": "Qwen3 Reranker 0.6B", "created": 1749168000, - "description": "qwen3-reranker-0.6b provided by deepinfra", + "description": "Lightweight Qwen3 cross-encoder reranker with 32K context for latency-sensitive search and RAG applications. Fast scoring at minimal cost. 0.6B size.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -22805,11 +30866,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -22844,7 +30907,7 @@ "name": "Qwen3 Reranker 4B", "display_name": "Qwen3 Reranker 4B", "created": 1749168000, - "description": "qwen3-reranker-4b provided by deepinfra", + "description": "Mid-size Qwen3 cross-encoder reranker with 32K context, balancing speed and accuracy for document relevance scoring in search and RAG workloads. 4B size.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -22867,11 +30930,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "stability": "unstable" } @@ -22907,7 +30972,7 @@ "name": "Qwen3 Reranker 8B", "display_name": "Qwen3 Reranker 8B", "created": 1749168000, - "description": "qwen3-reranker-8b provided by deepinfra", + "description": "Qwen3 cross-encoder reranker with 32K context for search and RAG pipelines. Delivers accurate relevance scoring by jointly encoding query-document pairs. 8B size.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -22930,11 +30995,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -22969,7 +31036,7 @@ "name": "Qwen3 VL 235B A22B Instruct", "display_name": "Qwen3 VL 235B A22B Instruct", "created": 1758585600, - "description": "qwen3-vl-235b-a22b-instruct provided by alibaba, novita, deepinfra", + "description": "Large Qwen 3 MoE vision-language instruction model.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -22992,162 +31059,94 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - }, - { - "providerId": "novita", - "externalId": "qwen/qwen3-vl-235b-a22b-instruct", - "pricing": { - "prompt": "0.3e-6", - "completion": "1.5e-6", - "image": "0", - "request": "0", - "input_cache_read": "0", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - }, - { - "providerId": "deepinfra", - "externalId": "Qwen/Qwen3-VL-235B-A22B-Instruct", - "pricing": { - "prompt": "0.20e-6", - "completion": "0.88e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.11e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0" - }, - "streaming": true, - "vision": true, - "cancellation": true, - "tools": true, - "parallelToolCalls": false, - "reasoning": false, - "max_output": 32768 - } - ], - "pricing": { - "prompt": "0.20e-6", - "completion": "0.88e-6", - "image": "0", - "request": "0", - "input_cache_read": "0.11e-6", - "input_cache_write": "0", - "input_cache_write_1h": "0", - "web_search": "0", - "internal_reasoning": "0" - }, - "context_length": 262144, - "max_output": 32768, - "supported_parameters": [ - "temperature", - "max_tokens", - "top_p", - "stream", - "tools", - "response_format" - ], - "json_output": true, - "structured_outputs": false, - "free": false - }, - { - "id": "qwen3-vl-235b-a22b-thinking", - "name": "Qwen3 VL 235B A22B Thinking", - "display_name": "Qwen3 VL 235B A22B Thinking", - "created": 1758585600, - "description": "qwen3-vl-235b-a22b-thinking provided by alibaba, novita", - "family": "alibaba", - "architecture": { - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT" - }, - "top_provider": { - "is_moderated": true - }, - "providers": [ + "tools": true, + "parallelToolCalls": false, + "json_output": true, + "reasoning": false, + "max_output": 32768, + "deactivated_at": "2026-07-08T00:00:00.000Z" + }, { - "providerId": "alibaba", - "externalId": "qwen3-vl-235b-a22b-thinking", + "providerId": "novita", + "externalId": "qwen/qwen3-vl-235b-a22b-instruct", "pricing": { - "prompt": "0.5e-6", - "completion": "2.0e-6", + "prompt": "0.3e-6", + "completion": "1.5e-6", "image": "0", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": true, - "max_output": 32768 + "json_output": true, + "reasoning": false, + "max_output": 32768, + "deactivated_at": "2026-10-27T00:00:00.000Z" }, { - "providerId": "novita", - "externalId": "qwen/qwen3-vl-235b-a22b-thinking", + "providerId": "deepinfra", + "externalId": "Qwen/Qwen3-VL-235B-A22B-Instruct", "pricing": { - "prompt": "0.98e-6", - "completion": "3.95e-6", + "prompt": "0.20e-6", + "completion": "0.88e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.11e-6", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, - "tools": false, + "tools": true, "parallelToolCalls": false, - "reasoning": true, - "max_output": 32768 + "json_output": true, + "reasoning": false, + "max_output": 32768, + "quantization": "fp8", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "stream", + "tools", + "response_format" + ] } ], "pricing": { - "prompt": "0.98e-6", - "completion": "3.95e-6", + "prompt": "0.20e-6", + "completion": "0.88e-6", "image": "0", "request": "0", - "input_cache_read": "0", + "input_cache_read": "0.11e-6", "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", "internal_reasoning": "0" }, - "context_length": 131072, + "context_length": 262144, "max_output": 32768, "supported_parameters": [ "temperature", "max_tokens", "top_p", - "frequency_penalty", - "presence_penalty", - "response_format", + "stream", "tools", - "tool_choice", - "reasoning" + "response_format" ], - "json_output": false, + "json_output": true, "structured_outputs": false, "free": false }, @@ -23156,7 +31155,7 @@ "name": "Qwen3 VL 30B A3B Instruct", "display_name": "Qwen3 VL 30B A3B Instruct", "created": 1759622400, - "description": "qwen3-vl-30b-a3b-instruct provided by novita, deepinfra", + "description": "Vision-language Qwen 3 MoE model, 30B size.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23179,13 +31178,25 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 131072, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": false, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "quantization": "bf16", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "response_format", + "tools", + "tool_choice" + ] }, { "providerId": "deepinfra", @@ -23199,13 +31210,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "function"], + "json_output": true, "reasoning": false, - "max_output": 32768 + "max_output": 32768, + "quantization": "fp8", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "response_format", + "tools", + "tool_choice" + ] } ], "pricing": { @@ -23239,7 +31263,7 @@ "name": "Qwen3 VL Plus", "display_name": "Qwen3 VL Plus", "created": 1758585600, - "description": "qwen3-vl-plus provided by alibaba", + "description": "Qwen 3 vision-language model with balanced performance.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23259,14 +31283,199 @@ "image": "0", "request": "0", "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", "input_cache_write": "0.25e-6", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.2e-6", + "completion": "1.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.2e-6", + "completion": "1.6e-6", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.3e-6", + "completion": "2.4e-6", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.6e-6", + "completion": "4.8e-6", + "input_cache_read": "0.12e-6", + "input_cache_read_explicit": "0.06e-6", + "input_cache_write": "0.75e-6" + } + ] + }, + "context_length": 262144, + "max_output": 32768, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.2e-6", + "completion": "1.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.2e-6", + "completion": "1.6e-6", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.3e-6", + "completion": "2.4e-6", + "input_cache_read": "0.06e-6", + "input_cache_read_explicit": "0.03e-6", + "input_cache_write": "0.375e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.6e-6", + "completion": "4.8e-6", + "input_cache_read": "0.12e-6", + "input_cache_read_explicit": "0.06e-6", + "input_cache_write": "0.75e-6" + } + ] + }, + "context_length": 262144, + "max_output": 32768, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.143e-6", + "completion": "1.434e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0143e-6", + "input_cache_write": "0.17875e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.143e-6", + "completion": "1.434e-6", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0143e-6", + "input_cache_write": "0.17875e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.215e-6", + "completion": "2.151e-6", + "input_cache_read": "0.043e-6", + "input_cache_read_explicit": "0.0215e-6", + "input_cache_write": "0.26875e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "0.429e-6", + "completion": "4.302e-6", + "input_cache_read": "0.086e-6", + "input_cache_read_explicit": "0.0429e-6", + "input_cache_write": "0.53625e-6" + } + ] + }, + "context_length": 262144, + "max_output": 32768, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.143e-6", + "completion": "1.434e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0143e-6", + "input_cache_write": "0.17875e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.143e-6", + "completion": "1.434e-6", + "input_cache_read": "0.029e-6", + "input_cache_read_explicit": "0.0143e-6", + "input_cache_write": "0.17875e-6" + }, + { + "name": "32K-128K", + "up_to_tokens": 128000, + "prompt": "0.215e-6", + "completion": "2.15e-6", + "input_cache_read": "0.043e-6", + "input_cache_read_explicit": "0.0215e-6", + "input_cache_write": "0.26875e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.43e-6", + "completion": "4.301e-6", + "input_cache_read": "0.086e-6", + "input_cache_read_explicit": "0.043e-6", + "input_cache_write": "0.5375e-6" + } + ] + }, + "context_length": 262144, + "max_output": 32768, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": true, "reasoning": false, "max_output": 32768 } @@ -23277,6 +31486,7 @@ "image": "0", "request": "0", "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", "input_cache_write": "0.25e-6", "input_cache_write_1h": "0", "web_search": "0", @@ -23303,7 +31513,7 @@ "name": "Qwen3.5 122B A10B", "display_name": "Qwen3.5 122B A10B", "created": 1772064000, - "description": "qwen3.5-122b-a10b provided by alibaba, novita", + "description": "Open-weight Qwen3.5 native vision-language MoE model (122B total, 10B active) with hybrid linear attention.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23326,11 +31536,30 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.4e-6", + "completion": "3.2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23341,7 +31570,21 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -23355,13 +31598,28 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 65536 + "max_output": 65536, + "max_temperature": 1, + "quantization": "bf16", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools" + ] } ], "pricing": { @@ -23399,7 +31657,7 @@ "name": "Qwen3.5 27B", "display_name": "Qwen3.5 27B", "created": 1772064000, - "description": "qwen3.5-27b provided by alibaba", + "description": "Open-weight dense Qwen3.5 native vision-language model with linear attention for fast responses.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23422,11 +31680,30 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.3e-6", + "completion": "2.4e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23437,7 +31714,21 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] } ], "pricing": { @@ -23475,7 +31766,7 @@ "name": "Qwen3.5 35B A3B", "display_name": "Qwen3.5 35B A3B", "created": 1772064000, - "description": "qwen3.5-35b-a3b provided by alibaba", + "description": "Open-weight Qwen3.5 native vision-language MoE model (35B total, 3B active) with hybrid linear attention.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23498,11 +31789,30 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.25e-6", + "completion": "2e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23513,7 +31823,21 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "max_temperature": 1, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] } ], "pricing": { @@ -23551,7 +31875,7 @@ "name": "Qwen3.5 9B", "display_name": "Qwen3.5 9B", "created": 1780272000, - "description": "qwen3.5-9b provided by deepinfra", + "description": "Compact natively multimodal Qwen3.5 hybrid-reasoning model with vision, tool calling and a 262K context window.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23574,13 +31898,17 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "max_output": 32768, + "quantization": "bf16", "stability": "unstable" } ], @@ -23618,7 +31946,7 @@ "display_name": "Qwen3.6 27B", "aliases": [], "created": 1792570254, - "description": "qwen3.6-27b provided by greenference", + "description": "Qwen3.6 27B dense model from Alibaba's Qwen team. Solid general-purpose chat, coding and tool calling at low cost.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -23639,15 +31967,23 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "discount": "0.2" }, + "context_length": 16384, "streaming": true, "vision": false, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, + "web_search": false, "reasoning": false, + "reasoning_max_tokens": false, "max_output": 8192, + "quantization": "fp8", "stability": "stable" } ], @@ -23660,6 +31996,7 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "discount": "0.2", "internal_reasoning": "0" }, "context_length": 16384, @@ -23677,6 +32014,7 @@ "json_output": true, "structured_outputs": true, "free": false, + "image_input_required": false, "stability": "stable" }, { @@ -23684,7 +32022,7 @@ "name": "Qwen3.6 35B A3B", "display_name": "Qwen3.6 35B A3B", "created": 1777420800, - "description": "qwen3.6-35b-a3b provided by alibaba, novita", + "description": "Native vision-language MoE model with hybrid linear attention and sparse mixture-of-experts, improved agentic coding, math/code reasoning, and spatial intelligence.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23705,13 +32043,83 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.375e-6", + "completion": "2.25e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.248e-6", + "completion": "1.485e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.248e-6", + "completion": "1.485e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.248e-6", + "completion": "1.485e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23722,7 +32130,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -23736,13 +32157,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 64000 + "max_output": 64000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools" + ] } ], "pricing": { @@ -23780,7 +32214,7 @@ "name": "Qwen3.6 Flash", "display_name": "Qwen3.6 Flash", "created": 1777420800, - "description": "qwen3.6-flash provided by alibaba", + "description": "Fast, cost-effective Qwen3.6 model with native vision-language capabilities, hybrid reasoning, tool calling, and a 1M context window for high-volume tasks.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23800,14 +32234,183 @@ "image": "0", "request": "0", "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", "input_cache_write": "0.3125e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.25e-6", + "completion": "1.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.0e-6", + "completion": "4e-6", + "input_cache_read": "0.2e-6", + "input_cache_read_explicit": "0.1e-6", + "input_cache_write": "1.25e-6" + } + ] + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.25e-6", + "completion": "1.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.25e-6", + "completion": "1.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.0e-6", + "completion": "4e-6", + "input_cache_read": "0.2e-6", + "input_cache_read_explicit": "0.1e-6", + "input_cache_write": "1.25e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.165e-6", + "completion": "0.99e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.165e-6", + "completion": "0.99e-6", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.66e-6", + "completion": "3.961e-6", + "input_cache_read": "0.132e-6", + "input_cache_read_explicit": "0.066e-6", + "input_cache_write": "0.825e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.165e-6", + "completion": "0.99e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.165e-6", + "completion": "0.99e-6", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.66e-6", + "completion": "3.961e-6", + "input_cache_read": "0.132e-6", + "input_cache_read_explicit": "0.066e-6", + "input_cache_write": "0.825e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.165e-6", + "completion": "0.99e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.165e-6", + "completion": "0.99e-6", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.66e-6", + "completion": "3.961e-6", + "input_cache_read": "0.132e-6", + "input_cache_read_explicit": "0.066e-6", + "input_cache_write": "0.825e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23818,7 +32421,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] } ], "pricing": { @@ -23827,9 +32443,30 @@ "image": "0", "request": "0", "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", "input_cache_write": "0.3125e-6", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.25e-6", + "completion": "1.5e-6", + "input_cache_read": "0.05e-6", + "input_cache_read_explicit": "0.025e-6", + "input_cache_write": "0.3125e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.0e-6", + "completion": "4e-6", + "input_cache_read": "0.2e-6", + "input_cache_read_explicit": "0.1e-6", + "input_cache_write": "1.25e-6" + } + ], "internal_reasoning": "0" }, "context_length": 983616, @@ -23856,7 +32493,7 @@ "name": "Qwen3.6 Plus", "display_name": "Qwen3.6 Plus", "created": 1777420800, - "description": "qwen3.6-plus provided by alibaba", + "description": "Native vision-language Plus model with significantly improved agentic coding, front-end programming, vibe coding, multi-modal recognition, OCR, and object localization over the 3.5 series.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23877,13 +32514,173 @@ "request": "0", "input_cache_read": "0.05e-6", "input_cache_write": "0.625e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "2e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + } + ] + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.5e-6", + "completion": "3e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "2e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.276e-6", + "completion": "1.651e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0276e-6", + "input_cache_write": "0.345e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.276e-6", + "completion": "1.651e-6", + "input_cache_read": "0.0276e-6", + "input_cache_write": "0.345e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.101e-6", + "completion": "6.602e-6", + "input_cache_read": "0.1101e-6", + "input_cache_write": "1.37625e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.276e-6", + "completion": "1.651e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0276e-6", + "input_cache_write": "0.345e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.276e-6", + "completion": "1.651e-6", + "input_cache_read": "0.0276e-6", + "input_cache_write": "0.345e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.101e-6", + "completion": "6.602e-6", + "input_cache_read": "0.1101e-6", + "input_cache_write": "1.37625e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.276e-6", + "completion": "1.651e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0276e-6", + "input_cache_write": "0.345e-6", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.276e-6", + "completion": "1.651e-6", + "input_cache_read": "0.0276e-6", + "input_cache_write": "0.345e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.101e-6", + "completion": "6.602e-6", + "input_cache_read": "0.1101e-6", + "input_cache_write": "1.37625e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23894,7 +32691,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] } ], "pricing": { @@ -23905,7 +32715,25 @@ "input_cache_read": "0.05e-6", "input_cache_write": "0.625e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.05e-6", + "input_cache_write": "0.625e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "2e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6", + "input_cache_write": "2.5e-6" + } + ], "internal_reasoning": "0" }, "context_length": 983616, @@ -23932,7 +32760,7 @@ "name": "Qwen3.7 Flash", "display_name": "Qwen3.7 Flash", "created": 1785110400, - "description": "qwen3.7-flash provided by alibaba", + "description": "Fast, cost-effective Qwen3.7 model with hybrid reasoning and tool calling for high-volume tasks.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -23952,14 +32780,228 @@ "image": "0", "request": "0", "input_cache_read": "0.006e-6", + "input_cache_read_explicit": "0.003e-6", "input_cache_write": "0.0375e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.03e-6", + "completion": "0.13e-6", + "input_cache_read": "0.006e-6", + "input_cache_read_explicit": "0.003e-6", + "input_cache_write": "0.0375e-6" + }, + { + "name": "32K-256K", + "up_to_tokens": 256000, + "prompt": "0.10e-6", + "completion": "0.40e-6", + "input_cache_read": "0.02e-6", + "input_cache_read_explicit": "0.01e-6", + "input_cache_write": "0.125e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.20e-6", + "completion": "0.80e-6", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6" + } + ] + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.03e-6", + "completion": "0.13e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.006e-6", + "input_cache_read_explicit": "0.003e-6", + "input_cache_write": "0.0375e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.03e-6", + "completion": "0.13e-6", + "input_cache_read": "0.006e-6", + "input_cache_read_explicit": "0.003e-6", + "input_cache_write": "0.0375e-6" + }, + { + "name": "32K-256K", + "up_to_tokens": 256000, + "prompt": "0.10e-6", + "completion": "0.40e-6", + "input_cache_read": "0.02e-6", + "input_cache_read_explicit": "0.01e-6", + "input_cache_write": "0.125e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.20e-6", + "completion": "0.80e-6", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.028e-6", + "completion": "0.110e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0056e-6", + "input_cache_read_explicit": "0.0028e-6", + "input_cache_write": "0.035e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.028e-6", + "completion": "0.110e-6", + "input_cache_read": "0.0056e-6", + "input_cache_read_explicit": "0.0028e-6", + "input_cache_write": "0.035e-6" + }, + { + "name": "32K-256K", + "up_to_tokens": 256000, + "prompt": "0.083e-6", + "completion": "0.330e-6", + "input_cache_read": "0.0166e-6", + "input_cache_read_explicit": "0.0083e-6", + "input_cache_write": "0.10375e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.165e-6", + "completion": "0.660e-6", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.028e-6", + "completion": "0.110e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0056e-6", + "input_cache_read_explicit": "0.0028e-6", + "input_cache_write": "0.035e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.028e-6", + "completion": "0.110e-6", + "input_cache_read": "0.0056e-6", + "input_cache_read_explicit": "0.0028e-6", + "input_cache_write": "0.035e-6" + }, + { + "name": "32K-256K", + "up_to_tokens": 256000, + "prompt": "0.083e-6", + "completion": "0.330e-6", + "input_cache_read": "0.0166e-6", + "input_cache_read_explicit": "0.0083e-6", + "input_cache_write": "0.10375e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.165e-6", + "completion": "0.660e-6", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.028e-6", + "completion": "0.110e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0056e-6", + "input_cache_read_explicit": "0.0028e-6", + "input_cache_write": "0.035e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.028e-6", + "completion": "0.110e-6", + "input_cache_read": "0.0056e-6", + "input_cache_read_explicit": "0.0028e-6", + "input_cache_write": "0.035e-6" + }, + { + "name": "32K-256K", + "up_to_tokens": 256000, + "prompt": "0.083e-6", + "completion": "0.330e-6", + "input_cache_read": "0.0166e-6", + "input_cache_read_explicit": "0.0083e-6", + "input_cache_write": "0.10375e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.165e-6", + "completion": "0.660e-6", + "input_cache_read": "0.033e-6", + "input_cache_read_explicit": "0.0165e-6", + "input_cache_write": "0.20625e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -23970,7 +33012,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "response_format", + "reasoning_effort" + ] } ], "pricing": { @@ -23979,9 +33034,39 @@ "image": "0", "request": "0", "input_cache_read": "0.006e-6", + "input_cache_read_explicit": "0.003e-6", "input_cache_write": "0.0375e-6", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 32K", + "up_to_tokens": 32000, + "prompt": "0.03e-6", + "completion": "0.13e-6", + "input_cache_read": "0.006e-6", + "input_cache_read_explicit": "0.003e-6", + "input_cache_write": "0.0375e-6" + }, + { + "name": "32K-256K", + "up_to_tokens": 256000, + "prompt": "0.10e-6", + "completion": "0.40e-6", + "input_cache_read": "0.02e-6", + "input_cache_read_explicit": "0.01e-6", + "input_cache_write": "0.125e-6" + }, + { + "name": "256K-1M", + "up_to_tokens": 1000000, + "prompt": "0.20e-6", + "completion": "0.80e-6", + "input_cache_read": "0.04e-6", + "input_cache_read_explicit": "0.02e-6", + "input_cache_write": "0.25e-6" + } + ], "internal_reasoning": "0" }, "context_length": 983616, @@ -24008,7 +33093,7 @@ "name": "Qwen3.7 Max", "display_name": "Qwen3.7 Max", "created": 1779235200, - "description": "qwen3.7-max provided by alibaba, novita", + "description": "Largest and most capable model in the Qwen3.7 series, a next-generation agent-centric flagship excelling at programming and long-horizon autonomous execution.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -24028,14 +33113,89 @@ "image": "0", "request": "0", "input_cache_read": "0.5e-6", + "input_cache_read_explicit": "0.25e-6", "input_cache_write": "3.125e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "2.5e-6", + "completion": "7.5e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.5e-6", + "input_cache_read_explicit": "0.25e-6", + "input_cache_write": "3.125e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "1.65e-6", + "completion": "4.951e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_read_explicit": "0.165e-6", + "input_cache_write": "2.0625e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "1.65e-6", + "completion": "4.951e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_read_explicit": "0.165e-6", + "input_cache_write": "2.0625e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "1.65e-6", + "completion": "4.951e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.33e-6", + "input_cache_read_explicit": "0.165e-6", + "input_cache_write": "2.0625e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -24046,7 +33206,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "response_format", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -24060,13 +33233,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 65536 + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "response_format" + ] } ], "pricing": { @@ -24104,7 +33290,7 @@ "name": "Qwen3.7 Plus", "display_name": "Qwen3.7 Plus", "created": 1779235200, - "description": "qwen3.7-plus provided by alibaba", + "description": "Mid-tier model in the Qwen3.7 series balancing speed, cost, and capability with strong coding and agentic performance.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -24124,14 +33310,183 @@ "image": "0", "request": "0", "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", "input_cache_write": "0.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.6e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "4.8e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.4e-6", + "completion": "1.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.6e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "4.8e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.276e-6", + "completion": "1.101e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0552e-6", + "input_cache_read_explicit": "0.0276e-6", + "input_cache_write": "0.345e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.276e-6", + "completion": "1.101e-6", + "input_cache_read": "0.0552e-6", + "input_cache_read_explicit": "0.0276e-6", + "input_cache_write": "0.345e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.826e-6", + "completion": "3.301e-6", + "input_cache_read": "0.1652e-6", + "input_cache_read_explicit": "0.0826e-6", + "input_cache_write": "1.0325e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.276e-6", + "completion": "1.101e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0552e-6", + "input_cache_read_explicit": "0.0276e-6", + "input_cache_write": "0.345e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.276e-6", + "completion": "1.101e-6", + "input_cache_read": "0.0552e-6", + "input_cache_read_explicit": "0.0276e-6", + "input_cache_write": "0.345e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.826e-6", + "completion": "3.301e-6", + "input_cache_read": "0.1652e-6", + "input_cache_read_explicit": "0.0826e-6", + "input_cache_write": "1.0325e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.276e-6", + "completion": "1.101e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.0552e-6", + "input_cache_read_explicit": "0.0276e-6", + "input_cache_write": "0.345e-6", + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.276e-6", + "completion": "1.101e-6", + "input_cache_read": "0.0552e-6", + "input_cache_read_explicit": "0.0276e-6", + "input_cache_write": "0.345e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "0.826e-6", + "completion": "3.301e-6", + "input_cache_read": "0.1652e-6", + "input_cache_read_explicit": "0.0826e-6", + "input_cache_write": "1.0325e-6" + } + ] + }, + "context_length": 983616, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -24142,7 +33497,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "response_format", + "reasoning_effort" + ] } ], "pricing": { @@ -24151,9 +33519,30 @@ "image": "0", "request": "0", "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", "input_cache_write": "0.5e-6", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 256K", + "up_to_tokens": 256000, + "prompt": "0.4e-6", + "completion": "1.6e-6", + "input_cache_read": "0.08e-6", + "input_cache_read_explicit": "0.04e-6", + "input_cache_write": "0.5e-6" + }, + { + "name": "Over 256K", + "up_to_tokens": null, + "prompt": "1.2e-6", + "completion": "4.8e-6", + "input_cache_read": "0.24e-6", + "input_cache_read_explicit": "0.12e-6", + "input_cache_write": "1.5e-6" + } + ], "internal_reasoning": "0" }, "context_length": 983616, @@ -24180,7 +33569,7 @@ "name": "Qwen3.8 2.4T A95B", "display_name": "Qwen3.8 2.4T A95B", "created": 1786492800, - "description": "qwen3.8-2.4t-a95b provided by together-ai, deepinfra, novita", + "description": "Open-weight sparse MoE variant of Qwen3.8 Max with 95B active out of 2.4T total parameters.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -24203,14 +33592,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1010000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "xhigh"], - "max_output": 909000 + "max_output": 909000, + "max_temperature": 1, + "deactivated_at": "2026-11-04T00:00:00.000Z" }, { "providerId": "deepinfra", @@ -24224,11 +33618,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": [ "minimal", @@ -24239,7 +33636,10 @@ "max" ], "min_cacheable_tokens": 4096, - "max_output": 131072 + "max_output": 131072, + "max_temperature": 1, + "quantization": "fp4", + "deactivated_at": "2026-10-12T00:00:00.000Z" }, { "providerId": "novita", @@ -24253,11 +33653,15 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, "max_output": 131072 } @@ -24295,7 +33699,7 @@ "name": "Qwen3.8 27B", "display_name": "Qwen3.8 27B", "created": 1786665600, - "description": "qwen3.8-27b provided by novita, deepinfra", + "description": "Dense 27-billion-parameter Qwen3.8 model for coding, professional work, research, and long-horizon agentic tasks.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -24318,13 +33722,28 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "function"], + "json_output": true, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice", + "response_format" + ] }, { "providerId": "deepinfra", @@ -24338,14 +33757,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["none", "low", "medium", "high"], - "max_output": 235929 + "max_output": 235929, + "max_temperature": 1, + "quantization": "bf16", + "deactivated_at": "2026-09-23T00:00:00.000Z" } ], "pricing": { @@ -24384,7 +33809,7 @@ "display_name": "Qwen3.8 27B", "aliases": [], "created": 1788377194, - "description": "Qwen3.8-27B provided by consensusprotocol", + "description": "", "family": "Qwen3.8 27B", "architecture": { "input_modalities": ["text", "image"], @@ -24407,13 +33832,19 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262000, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, + "web_search": false, "reasoning": true, "reasoning_efforts": ["xhigh", "medium", "low"], + "reasoning_max_tokens": false, "stability": "stable" } ], @@ -24443,6 +33874,7 @@ "json_output": false, "structured_outputs": false, "free": false, + "image_input_required": false, "stability": "stable" }, { @@ -24450,7 +33882,7 @@ "name": "Qwen3.8 Flash", "display_name": "Qwen3.8 Flash", "created": 1787702400, - "description": "qwen3.8-flash provided by alibaba, novita", + "description": "Fast, cost-effective Qwen3.8 model with hybrid reasoning, visual understanding and a 1M context for high-volume tasks.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -24470,14 +33902,40 @@ "image": "0", "request": "0", "input_cache_read": "0.016e-6", + "input_cache_read_explicit": "0.016e-6", "input_cache_write": "0.2e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.47e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.016e-6", + "input_cache_read_explicit": "0.016e-6", + "input_cache_write": "0.2e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, + "web_search": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -24488,7 +33946,21 @@ "xhigh", "max" ], - "max_output": 131072 + "reasoning_max_tokens": true, + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice", + "response_format", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -24502,13 +33974,29 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": false, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice", + "response_format" + ] } ], "pricing": { @@ -24517,9 +34005,10 @@ "image": "0", "request": "0", "input_cache_read": "0.016e-6", + "input_cache_read_explicit": "0.016e-6", "input_cache_write": "0.2e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 1000000, @@ -24547,7 +34036,7 @@ "name": "Qwen3.8 Max", "display_name": "Qwen3.8 Max", "created": 1785628800, - "description": "qwen3.8-max provided by alibaba, novita, scx-ai-gp", + "description": "Flagship 2.4-trillion-parameter MoE model in the Qwen3.8 series with native visual understanding, excelling at coding, professional work, and long-horizon autonomous agent tasks.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -24567,16 +34056,104 @@ "image": "0", "request": "0", "input_cache_read": "0.25e-6", + "input_cache_read_explicit": "0.17e-6", "input_cache_write": "2.5e-6", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "2e-6", + "completion": "6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_read_explicit": "0.17e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "2e-6", + "completion": "6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_read_explicit": "0.17e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "2e-6", + "completion": "6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_read_explicit": "0.17e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "2e-6", + "completion": "6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.25e-6", + "input_cache_read_explicit": "0.17e-6", + "input_cache_write": "2.5e-6", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + } + ], + "context_length": 983616, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, - "max_output": 131072 + "reasoning_max_tokens": true, + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "response_format", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -24590,13 +34167,29 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": true, + "structured_outputs": true, "reasoning": true, - "max_output": 131072 + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice", + "response_format" + ] }, { "providerId": "scx-ai-gp", @@ -24610,12 +34203,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 1000000, "streaming": true, "vision": true, - "cancellation": true, + "audio": false, + "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": false, + "web_search": true, "reasoning": true, + "reasoning_max_tokens": true, "max_output": 131072, "stability": "stable" } @@ -24631,7 +34230,148 @@ "web_search": "0", "internal_reasoning": "0" }, - "context_length": 1000000, + "context_length": 1000000, + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "response_format", + "reasoning_effort", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, + { + "id": "qwen3.8-omni-flash", + "name": "Qwen3.8 Omni Flash", + "display_name": "Qwen3.8 Omni Flash", + "created": 1789689600, + "description": "Omni-modal Qwen3.8 Flash model that understands text, images and audio, with adjustable reasoning, tool use and a 1M context.", + "family": "alibaba", + "architecture": { + "input_modalities": ["text", "image", "audio"], + "output_modalities": ["text"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "alibaba", + "externalId": "qwen3.8-omni-flash", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.47e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.016e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.15e-6", + "completion": "0.47e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.016e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + }, + { + "id": "eu-frankfurt", + "pricing": { + "prompt": "0.113e-6", + "completion": "0.382e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.014e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.113e-6", + "completion": "0.382e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.014e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 983616, + "max_output": 131072, + "streaming": true + } + ], + "context_length": 983616, + "streaming": true, + "vision": true, + "audio": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "function"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "reasoning_efforts": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "max_output": 131072, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "tools", + "tool_choice", + "response_format", + "reasoning_effort" + ] + } + ], + "pricing": { + "prompt": "0.15e-6", + "completion": "0.47e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.016e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 983616, "max_output": 131072, "supported_parameters": [ "temperature", @@ -24642,6 +34382,7 @@ "stop", "stream", "tools", + "tool_choice", "response_format", "reasoning_effort", "reasoning" @@ -24655,7 +34396,7 @@ "name": "Qwen3.5 397B A17B", "display_name": "Qwen3.5 397B A17B", "created": 1771200000, - "description": "qwen35-397b-a17b provided by alibaba, novita, nebius", + "description": "Native multimodal MoE model with 397B total / 17B active parameters, reasoning, and agent capabilities.", "family": "alibaba", "architecture": { "input_modalities": ["text", "image"], @@ -24676,13 +34417,81 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0", - "input_cache_write_1h": "0" - }, + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "regions": [ + { + "id": "singapore", + "pricing": { + "prompt": "0.6e-6", + "completion": "3.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + }, + { + "id": "us-virginia", + "pricing": { + "prompt": "0.6e-6", + "completion": "3.6e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01" + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + }, + { + "id": "cn-beijing", + "pricing": { + "prompt": "0.172e-6", + "completion": "1.032e-6", + "image": "0", + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0.01", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 128000, + "prompt": "0.172e-6", + "completion": "1.032e-6" + }, + { + "name": "128K-256K", + "up_to_tokens": 256000, + "prompt": "0.43e-6", + "completion": "2.58e-6" + } + ] + }, + "context_length": 262144, + "max_output": 65536, + "streaming": true + } + ], + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "web_search": true, "reasoning": true, "reasoning_efforts": [ "none", @@ -24693,7 +34502,20 @@ "xhigh", "max" ], - "max_output": 65536 + "reasoning_max_tokens": true, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools", + "reasoning_effort" + ] }, { "providerId": "novita", @@ -24707,13 +34529,26 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 64000 + "max_output": 64000, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools" + ] }, { "providerId": "nebius", @@ -24727,13 +34562,28 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, - "max_output": 32768 + "max_output": 32768, + "quantization": "fp4", + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "stop", + "stream", + "response_format", + "tools" + ], + "deactivated_at": "2026-07-14T00:00:00.000Z" } ], "pricing": { @@ -24744,7 +34594,7 @@ "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.01", "internal_reasoning": "0" }, "context_length": 262144, @@ -24772,7 +34622,7 @@ "display_name": "Reka Edge 2603", "aliases": [], "created": 1791576159, - "description": "reka-edge-2603 provided by reka-ai", + "description": "Reka Edge 2603 provides frontier-level intelligence for physical AI. It excels at visual understanding (videos, images), object detection, and tool use, and with its CONVNEXT vision encoder, it processes images with 3x fewer tokens, leading to significant gains in latency.", "family": "reka", "architecture": { "input_modalities": ["text", "image"], @@ -24795,13 +34645,20 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 16384, "streaming": true, "vision": true, + "audio": false, "cancellation": false, "tools": true, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": true, + "web_search": false, "reasoning": false, + "reasoning_max_tokens": false, "max_output": 16384, + "quantization": "bf16", "stability": "stable" } ], @@ -24831,6 +34688,7 @@ "json_output": false, "structured_outputs": true, "free": false, + "image_input_required": false, "stability": "stable" }, { @@ -24838,7 +34696,7 @@ "name": "Seed 1.6 (250615)", "display_name": "Seed 1.6 (250615)", "created": 1750809600, - "description": "seed-1-6-250615 provided by bytedance", + "description": "ByteDance Seed 1.6 vision model with thinking/non-thinking modes, multimodal inputs, and 256K context window", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -24861,11 +34719,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"] } @@ -24902,7 +34762,7 @@ "name": "Seed 1.6 (250915)", "display_name": "Seed 1.6 (250915)", "created": 1757894400, - "description": "seed-1-6-250915 provided by bytedance", + "description": "ByteDance Seed 1.6 vision model released September 15, 2025 with thinking/non-thinking modes and multimodal inputs", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -24925,11 +34785,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"] } @@ -24966,7 +34828,7 @@ "name": "Seed 1.6 Flash (250715)", "display_name": "Seed 1.6 Flash (250715)", "created": 1753488000, - "description": "seed-1-6-flash-250715 provided by bytedance", + "description": "ByteDance Seed 1.6 Flash - faster, cost-effective vision model released July 15, 2025", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -24989,11 +34851,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"] } @@ -25030,7 +34894,7 @@ "name": "Seed 1.8 (251228)", "display_name": "Seed 1.8 (251228)", "created": 1766016000, - "description": "seed-1-8-251228 provided by bytedance", + "description": "ByteDance Seed 1.8 advanced vision model released December 28, 2025 with enhanced capabilities", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -25053,11 +34917,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 256000, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"] } @@ -25094,7 +34960,7 @@ "name": "Seed 2.0 Code Preview (260328)", "display_name": "Seed 2.0 Code Preview (260328)", "created": 1774656000, - "description": "seed-2-0-code-preview-260328 provided by bytedance", + "description": "ByteDance Seed 2.0 model optimized for agentic coding, frontend development, and multilingual programming.", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -25115,13 +34981,32 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.1e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "1e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6" + } + ] }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none"], + "json_output": false, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], "min_cacheable_tokens": 2048, @@ -25137,6 +35022,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.1e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "1e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6" + } + ], "internal_reasoning": "0" }, "context_length": 262144, @@ -25161,7 +35062,7 @@ "name": "Seed 2.0 Lite (260428)", "display_name": "Seed 2.0 Lite (260428)", "created": 1777334400, - "description": "seed-2-0-lite-260428 provided by bytedance", + "description": "Cost-efficient ByteDance Seed 2.0 workhorse with strong multimodal and agent capabilities at lower latency.", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -25182,13 +35083,32 @@ "request": "0", "input_cache_read": "0.05e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.25e-6", + "completion": "2e-6", + "input_cache_read": "0.05e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "0.5e-6", + "completion": "4e-6", + "input_cache_read": "0.1e-6" + } + ] }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], "min_cacheable_tokens": 2048, @@ -25204,6 +35124,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.25e-6", + "completion": "2e-6", + "input_cache_read": "0.05e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "0.5e-6", + "completion": "4e-6", + "input_cache_read": "0.1e-6" + } + ], "internal_reasoning": "0" }, "context_length": 262144, @@ -25228,7 +35164,7 @@ "name": "Seed 2.0 Mini (260428)", "display_name": "Seed 2.0 Mini (260428)", "created": 1777334400, - "description": "seed-2-0-mini-260428 provided by bytedance", + "description": "ByteDance Seed 2.0 model for latency-sensitive, high-concurrency, cost-sensitive workloads.", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -25249,13 +35185,32 @@ "request": "0", "input_cache_read": "0.02e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.1e-6", + "completion": "0.4e-6", + "input_cache_read": "0.02e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0.8e-6", + "input_cache_read": "0.04e-6" + } + ] }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], "min_cacheable_tokens": 2048, @@ -25271,6 +35226,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.1e-6", + "completion": "0.4e-6", + "input_cache_read": "0.02e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "0.2e-6", + "completion": "0.8e-6", + "input_cache_read": "0.04e-6" + } + ], "internal_reasoning": "0" }, "context_length": 262144, @@ -25295,7 +35266,7 @@ "name": "Seed 2.0 Pro (260328)", "display_name": "Seed 2.0 Pro (260328)", "created": 1774656000, - "description": "seed-2-0-pro-260328 provided by bytedance", + "description": "ByteDance Seed 2.0 flagship multimodal reasoning model for complex agentic and enterprise tasks.", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -25316,13 +35287,32 @@ "request": "0", "input_cache_read": "0.1e-6", "input_cache_write": "0", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.1e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "1e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6" + } + ] }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "json_output": true, + "structured_outputs": true, "reasoning": true, "reasoning_efforts": ["minimal", "low", "medium", "high"], "min_cacheable_tokens": 2048, @@ -25338,6 +35328,22 @@ "input_cache_write": "0", "input_cache_write_1h": "0", "web_search": "0", + "tiers": [ + { + "name": "Up to 128K", + "up_to_tokens": 131072, + "prompt": "0.5e-6", + "completion": "3e-6", + "input_cache_read": "0.1e-6" + }, + { + "name": "Over 128K", + "up_to_tokens": null, + "prompt": "1e-6", + "completion": "6e-6", + "input_cache_read": "0.2e-6" + } + ], "internal_reasoning": "0" }, "context_length": 262144, @@ -25362,7 +35368,7 @@ "name": "Seedance 1.5 Pro", "display_name": "Seedance 1.5 Pro", "created": 1774224000, - "description": "seedance-1-5-pro provided by bytedance", + "description": "ByteDance Seedance 1.5 Pro - professional video generation model with complex instruction following and native audio", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25384,6 +35390,7 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [5, 10], "pricing": { "prompt": "0", "completion": "0", @@ -25399,11 +35406,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -25446,7 +35455,7 @@ "name": "Seedance 2.0", "display_name": "Seedance 2.0", "created": 1776124800, - "description": "seedance-2-0 provided by bytedance", + "description": "ByteDance Seedance 2.0 high-quality video generation model with text-to-video and image-to-video support", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25468,6 +35477,9 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [ + 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 + ], "pricing": { "prompt": "0", "completion": "0", @@ -25483,11 +35495,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -25530,7 +35544,7 @@ "name": "Seedance 2.0 Fast", "display_name": "Seedance 2.0 Fast", "created": 1776124800, - "description": "seedance-2-0-fast provided by bytedance", + "description": "ByteDance Seedance 2.0 Fast - accelerated video generation model for quicker outputs", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25547,6 +35561,9 @@ "supportedVideoSizes": ["1280x720", "720x1280"], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [ + 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 + ], "pricing": { "prompt": "0", "completion": "0", @@ -25562,11 +35579,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -25609,7 +35628,7 @@ "name": "Seedance 2.0 Mini", "display_name": "Seedance 2.0 Mini", "created": 1781481600, - "description": "seedance-2-0-mini provided by bytedance", + "description": "ByteDance Seedance 2.0 Mini - lightweight and highly efficient video generation model designed for rapid iteration", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25632,6 +35651,9 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [ + 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 + ], "pricing": { "prompt": "0", "completion": "0", @@ -25647,11 +35669,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -25694,7 +35718,7 @@ "name": "Seedance 2.5", "display_name": "Seedance 2.5", "created": 1786147200, - "description": "seedance-2-5 provided by bytedance", + "description": "ByteDance Seedance 2.5 video generation model with single-shot clips up to 30 seconds and omni-reference image/video/audio conditioning", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25719,6 +35743,10 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [ + 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 + ], "pricing": { "prompt": "0", "completion": "0", @@ -25736,11 +35764,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } @@ -25788,7 +35818,7 @@ "name": "Seedream 4.0", "display_name": "Seedream 4.0", "created": 1757980800, - "description": "seedream-4-0 provided by bytedance", + "description": "ByteDance Seedream 4.0 text-to-image generation model with high-quality visual output", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25811,11 +35841,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -25852,7 +35884,7 @@ "name": "Seedream 4.5", "display_name": "Seedream 4.5", "created": 1764720000, - "description": "seedream-4-5 provided by bytedance", + "description": "ByteDance Seedream 4.5 advanced text-to-image generation model with enhanced quality and consistency", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -25875,11 +35907,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -25916,7 +35950,7 @@ "name": "Seedream 5.0 Flash", "display_name": "Seedream 5.0 Flash", "created": 1789430400, - "description": "seedream-5-0-flash provided by bytedance", + "description": "ByteDance Seedream 5.0 Flash fast, cost-efficient image generation and editing model for high-volume and interactive workflows, with up to 2K output", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -25939,11 +35973,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -25980,7 +36016,7 @@ "name": "Seedream 5.0 Lite", "display_name": "Seedream 5.0 Lite", "created": 1769558400, - "description": "seedream-5-0-lite provided by bytedance", + "description": "ByteDance Seedream 5.0 Lite (Dola Seedream 5.0) text-to-image generation model with strong prompt understanding and up to 4K output", "family": "bytedance", "architecture": { "input_modalities": ["text"], @@ -26003,11 +36039,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -26044,7 +36082,7 @@ "name": "Seedream 5.0 Pro", "display_name": "Seedream 5.0 Pro", "created": 1782604800, - "description": "seedream-5-0-pro provided by bytedance", + "description": "ByteDance Seedream 5.0 Pro flagship image generation and editing model with precise layout control, multilingual text rendering, and up to 2K output", "family": "bytedance", "architecture": { "input_modalities": ["text", "image"], @@ -26067,11 +36105,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": true, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 4096 } @@ -26108,7 +36148,7 @@ "name": "Smart Route", "display_name": "Smart Route", "created": 1790294400, - "description": "smart provided by llmgateway", + "description": "Routes to one of the models your organization configured, chosen by a classifier that rates each request.", "family": "llmgateway", "architecture": { "input_modalities": ["text", "image"], @@ -26127,7 +36167,15 @@ "cancellation": true, "tools": true, "parallelToolCalls": false, - "reasoning": false + "json_output": true, + "reasoning": false, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty" + ] } ], "pricing": { @@ -26158,7 +36206,7 @@ "name": "Sonar", "display_name": "Sonar", "created": 1735689600, - "description": "sonar provided by perplexity", + "description": "Standard Sonar model for search-augmented generation.", "family": "perplexity", "architecture": { "input_modalities": ["text"], @@ -26179,13 +36227,18 @@ "request": "0", "input_cache_read": "0", "input_cache_write": "0.25e-6", - "input_cache_write_1h": "0" + "input_cache_write_1h": "0", + "web_search": "0.0025" }, + "context_length": 130000, "streaming": true, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": true, + "web_search": true, "reasoning": false } ], @@ -26197,7 +36250,7 @@ "input_cache_read": "0", "input_cache_write": "0.25e-6", "input_cache_write_1h": "0", - "web_search": "0", + "web_search": "0.0025", "internal_reasoning": "0" }, "context_length": 130000, @@ -26220,7 +36273,7 @@ "name": "Step 3.7 Flash", "display_name": "Step 3.7 Flash", "created": 1779926400, - "description": "step-3.7-flash provided by novita, deepinfra", + "description": "StepFun's high-efficiency multimodal MoE model (196B language backbone, ~11B active) with native image and video understanding.", "family": "stepfun", "architecture": { "input_modalities": ["text", "image"], @@ -26243,13 +36296,18 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "required", "function"], + "json_output": false, "reasoning": true, - "max_output": 256000 + "max_output": 256000, + "max_temperature": 1, + "quantization": "fp8" }, { "providerId": "deepinfra", @@ -26263,11 +36321,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 262144, "streaming": true, "vision": true, "cancellation": true, "tools": true, "parallelToolCalls": false, + "supported_tool_choices": ["auto", "none", "function"], + "json_output": false, "reasoning": true, "reasoning_efforts": [ "minimal", @@ -26277,7 +36338,9 @@ "xhigh", "max" ], - "max_output": 32768 + "max_output": 32768, + "max_temperature": 1, + "deactivated_at": "2026-10-01T00:00:00.000Z" } ], "pricing": { @@ -26308,12 +36371,81 @@ "structured_outputs": false, "free": false }, + { + "id": "step-5-preview", + "name": "Step 5 Preview", + "display_name": "Step 5 Preview", + "created": 1790121600, + "description": "StepFun's multimodal reasoning preview model with a 1M-token context window, structured output, and function calling.", + "family": "stepfun", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "tencent", + "externalId": "step-5-preview", + "pricing": { + "prompt": "1e-6", + "completion": "2.7e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.1e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 1000000, + "streaming": true, + "vision": true, + "cancellation": true, + "tools": true, + "parallelToolCalls": false, + "supported_tool_choices": ["auto"], + "json_output": true, + "structured_outputs": true, + "reasoning": true, + "max_output": 65536 + } + ], + "pricing": { + "prompt": "1e-6", + "completion": "2.7e-6", + "image": "0", + "request": "0", + "input_cache_read": "0.1e-6", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 1000000, + "max_output": 65536, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice", + "reasoning" + ], + "json_output": true, + "structured_outputs": true, + "free": false + }, { "id": "text-embedding-004", "name": "Text Embedding 004", "display_name": "Text Embedding 004", "created": 1715644800, - "description": "text-embedding-004 provided by google-vertex", + "description": "Vertex AI text embedding model. Returns 768-dimensional vectors; supports the `dimensions` parameter (1–768) and native batching (up to 250 inputs per request).", "family": "google", "architecture": { "input_modalities": ["text"], @@ -26336,11 +36468,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2048, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -26375,7 +36509,7 @@ "name": "Text Embedding 005", "display_name": "Text Embedding 005", "created": 1731888000, - "description": "text-embedding-005 provided by google-vertex", + "description": "Vertex AI text embedding model optimized for English. Returns 768-dimensional vectors; supports the `dimensions` parameter (1–768) and native batching (up to 250 inputs per request).", "family": "google", "architecture": { "input_modalities": ["text"], @@ -26398,11 +36532,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2048, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -26437,7 +36573,7 @@ "name": "Text Embedding 3 Large", "display_name": "Text Embedding 3 Large", "created": 1706140800, - "description": "text-embedding-3-large provided by openai", + "description": "Highest-quality OpenAI embedding model. Default output dimension 3072; supports the `dimensions` parameter to shorten output (OpenAI examples: 256, 1024).", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -26460,11 +36596,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8192, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -26499,7 +36637,7 @@ "name": "Text Embedding 3 Small", "display_name": "Text Embedding 3 Small", "created": 1706140800, - "description": "text-embedding-3-small provided by openai", + "description": "Small, efficient embedding model. Default output dimension 1536; supports the `dimensions` parameter to shorten output.", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -26522,11 +36660,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8192, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -26561,7 +36701,7 @@ "name": "Text Embedding Ada 002", "display_name": "Text Embedding Ada 002", "created": 1671062400, - "description": "text-embedding-ada-002 provided by openai", + "description": "Legacy OpenAI embedding model with a fixed 1536-dimensional output. Does not support the `dimensions` parameter.", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -26584,11 +36724,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 8192, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -26623,7 +36765,7 @@ "name": "Text Multilingual Embedding 002", "display_name": "Text Multilingual Embedding 002", "created": 1715644800, - "description": "text-multilingual-embedding-002 provided by google-vertex", + "description": "Vertex AI multilingual text embedding model covering 100+ languages. Returns 768-dimensional vectors; supports the `dimensions` parameter (1–768) and native batching (up to 250 inputs per request).", "family": "google", "architecture": { "input_modalities": ["text"], @@ -26646,11 +36788,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2048, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false } ], @@ -26685,7 +36829,7 @@ "name": "TTS-1", "display_name": "TTS-1", "created": 1699228800, - "description": "tts-1 provided by openai", + "description": "OpenAI text-to-speech model optimized for real-time use. Generates speech via the /v1/audio/speech endpoint.", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -26703,23 +36847,39 @@ "prompt": "0", "completion": "0", "image": "0", + "input_character": "15e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 4096, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "supported_voices": [ + "alloy", + "ash", + "coral", + "echo", + "fable", + "nova", + "onyx", + "sage", + "shimmer" + ], + "deactivated_at": "2027-01-06T00:00:00.000Z" } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", + "input_character": "15e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -26748,7 +36908,7 @@ "name": "TTS-1 HD", "display_name": "TTS-1 HD", "created": 1699228800, - "description": "tts-1-hd provided by openai", + "description": "OpenAI text-to-speech model optimized for quality. Generates speech via the /v1/audio/speech endpoint.", "family": "openai", "architecture": { "input_modalities": ["text"], @@ -26766,23 +36926,39 @@ "prompt": "0", "completion": "0", "image": "0", + "input_character": "30e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 4096, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, - "reasoning": false + "json_output": false, + "reasoning": false, + "supported_voices": [ + "alloy", + "ash", + "coral", + "echo", + "fable", + "nova", + "onyx", + "sage", + "shimmer" + ], + "deactivated_at": "2027-01-06T00:00:00.000Z" } ], "pricing": { "prompt": "0", "completion": "0", "image": "0", + "input_character": "30e-6", "request": "0", "input_cache_read": "0", "input_cache_write": "0", @@ -26806,12 +36982,176 @@ "free": false, "deactivated_at": "2027-01-06T00:00:00.000Z" }, + { + "id": "veed-fabric-1-0", + "name": "VEED Fabric 1.0", + "display_name": "VEED Fabric 1.0", + "created": 1757894400, + "description": "VEED Fabric 1.0 talking-video generation. Animates one image with a face into a lip-synced video driven by one speech audio track; the output is as long as the audio.", + "family": "atlascloud", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["video"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "atlascloud", + "externalId": "veed/fabric-1.0", + "supportedVideoSizes": ["854x480", "480x854", "1280x720", "720x1280"], + "supportsVideoAudio": true, + "supportsVideoWithoutAudio": false, + "pricing": { + "prompt": "0", + "completion": "0", + "image": "0", + "per_second": { + "480p": "0.088", + "720p": "0.165" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 2000, + "streaming": false, + "vision": true, + "cancellation": false, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false, + "max_output": 1, + "stability": "beta" + } + ], + "pricing": { + "prompt": "0", + "completion": "0", + "image": "0", + "per_second": { + "480p": "0.088", + "720p": "0.165" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 2000, + "max_output": 1, + "per_request_limits": { + "max_video_duration_seconds": "300" + }, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false, + "stability": "beta" + }, + { + "id": "veed-fabric-1-0-fast", + "name": "VEED Fabric 1.0 Fast", + "display_name": "VEED Fabric 1.0 Fast", + "created": 1757894400, + "description": "VEED Fabric 1.0 Fast talking-video generation. Animates one image with a face into a lip-synced video driven by one speech audio track; the output is as long as the audio.", + "family": "atlascloud", + "architecture": { + "input_modalities": ["text", "image"], + "output_modalities": ["video"], + "tokenizer": "GPT" + }, + "top_provider": { + "is_moderated": true + }, + "providers": [ + { + "providerId": "atlascloud", + "externalId": "veed/fabric-1.0/fast", + "supportedVideoSizes": ["854x480", "480x854", "1280x720", "720x1280"], + "supportsVideoAudio": true, + "supportsVideoWithoutAudio": false, + "pricing": { + "prompt": "0", + "completion": "0", + "image": "0", + "per_second": { + "480p": "0.11", + "720p": "0.22" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0" + }, + "context_length": 2000, + "streaming": false, + "vision": true, + "cancellation": false, + "tools": false, + "parallelToolCalls": false, + "json_output": false, + "reasoning": false, + "max_output": 1, + "stability": "beta" + } + ], + "pricing": { + "prompt": "0", + "completion": "0", + "image": "0", + "per_second": { + "480p": "0.11", + "720p": "0.22" + }, + "request": "0", + "input_cache_read": "0", + "input_cache_write": "0", + "input_cache_write_1h": "0", + "web_search": "0", + "internal_reasoning": "0" + }, + "context_length": 2000, + "max_output": 1, + "per_request_limits": { + "max_video_duration_seconds": "300" + }, + "supported_parameters": [ + "temperature", + "max_tokens", + "top_p", + "frequency_penalty", + "presence_penalty", + "response_format", + "tools", + "tool_choice" + ], + "json_output": false, + "structured_outputs": false, + "free": false, + "stability": "beta" + }, { "id": "veo-3.1-fast-generate-preview", "name": "Veo 3.1 Fast", "display_name": "Veo 3.1 Fast", "created": 1773446400, - "description": "veo-3.1-fast-generate-preview provided by google-vertex", + "description": "Google Veo 3.1 Fast video generation with audio.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -26835,6 +37175,8 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [4, 6, 8, 10], + "supported_video_durations_seconds_image_to_video": [4, 6, 8], "pricing": { "prompt": "0", "completion": "0", @@ -26850,11 +37192,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 1, "stability": "beta" @@ -26902,7 +37247,7 @@ "name": "Veo 3.1", "display_name": "Veo 3.1", "created": 1773446400, - "description": "veo-3.1-generate-preview provided by google-vertex", + "description": "Google Veo 3.1 video generation with audio.", "family": "google", "architecture": { "input_modalities": ["text"], @@ -26926,6 +37271,8 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": true, + "supported_video_durations_seconds": [4, 6, 8, 10], + "supported_video_durations_seconds_image_to_video": [4, 6, 8], "pricing": { "prompt": "0", "completion": "0", @@ -26941,11 +37288,14 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 32768, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, + "structured_outputs": false, "reasoning": false, "max_output": 1, "stability": "beta" @@ -26993,7 +37343,7 @@ "name": "Wan 2.6 Text-to-Video", "display_name": "Wan 2.6 Text-to-Video", "created": 1768435200, - "description": "wan-2-6-t2v provided by alibaba", + "description": "Alibaba's Wan 2.6 text-to-video model generating short clips with synchronized audio from a text prompt.", "family": "alibaba", "architecture": { "input_modalities": ["text"], @@ -27015,6 +37365,9 @@ ], "supportsVideoAudio": true, "supportsVideoWithoutAudio": false, + "supported_video_durations_seconds": [ + 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 + ], "pricing": { "prompt": "0", "completion": "0", @@ -27029,11 +37382,13 @@ "input_cache_write": "0", "input_cache_write_1h": "0" }, + "context_length": 2000, "streaming": false, "vision": false, "cancellation": true, "tools": false, "parallelToolCalls": false, + "json_output": false, "reasoning": false, "max_output": 1 } diff --git a/scripts/lovable-gateway.models.json b/scripts/lovable-gateway.models.json index e6aa71be12..2ae1137174 100644 --- a/scripts/lovable-gateway.models.json +++ b/scripts/lovable-gateway.models.json @@ -27,6 +27,7 @@ "messages" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -34,14 +35,14 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ] @@ -49,7 +50,7 @@ "cache_write": { "tiers": [ { - "cost": "0.0000125", + "cost": "0.00005", "min": 0 } ] @@ -57,7 +58,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0 } ] @@ -68,7 +69,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -77,7 +78,7 @@ "text": { "tiers": [ { - "cost": "0.00005", + "cost": "0.0002", "min": 0 } ] @@ -92,14 +93,14 @@ "text": { "tiers": [ { - "cost": "0.000011", + "cost": "0.000044", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000275", + "cost": "0.0000011", "min": 0 } ] @@ -107,7 +108,7 @@ "cache_write": { "tiers": [ { - "cost": "0.00001375", + "cost": "0.000055", "min": 0 } ] @@ -115,7 +116,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000022", + "cost": "0.000088", "min": 0 } ] @@ -126,7 +127,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -135,7 +136,7 @@ "text": { "tiers": [ { - "cost": "0.000055", + "cost": "0.00022", "min": 0 } ] @@ -177,6 +178,7 @@ "messages" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -184,14 +186,14 @@ "text": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000001", + "cost": "0.0000004", "min": 0 } ] @@ -199,7 +201,7 @@ "cache_write": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0 } ] @@ -207,7 +209,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -218,7 +220,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -227,7 +229,7 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ] @@ -267,6 +269,7 @@ "messages" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -274,14 +277,14 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -289,7 +292,7 @@ "cache_write": { "tiers": [ { - "cost": "0.00000625", + "cost": "0.000025", "min": 0 } ] @@ -297,7 +300,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -308,7 +311,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -317,7 +320,7 @@ "text": { "tiers": [ { - "cost": "0.000025", + "cost": "0.0001", "min": 0 } ] @@ -332,14 +335,14 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0 } ] @@ -347,7 +350,7 @@ "cache_write": { "tiers": [ { - "cost": "0.0000125", + "cost": "0.00005", "min": 0 } ] @@ -355,7 +358,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0 } ] @@ -366,7 +369,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -375,7 +378,7 @@ "text": { "tiers": [ { - "cost": "0.00005", + "cost": "0.0002", "min": 0 } ] @@ -390,14 +393,14 @@ "text": { "tiers": [ { - "cost": "0.000011", + "cost": "0.000044", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000011", + "cost": "0.0000044", "min": 0 } ] @@ -405,7 +408,7 @@ "cache_write": { "tiers": [ { - "cost": "0.00001375", + "cost": "0.000055", "min": 0 } ] @@ -413,7 +416,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000022", + "cost": "0.000088", "min": 0 } ] @@ -424,7 +427,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -433,7 +436,7 @@ "text": { "tiers": [ { - "cost": "0.000055", + "cost": "0.00022", "min": 0 } ] @@ -448,14 +451,14 @@ "text": { "tiers": [ { - "cost": "0.0000055", + "cost": "0.000022", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000055", + "cost": "0.0000022", "min": 0 } ] @@ -463,7 +466,7 @@ "cache_write": { "tiers": [ { - "cost": "0.000006875", + "cost": "0.0000275", "min": 0 } ] @@ -471,7 +474,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000011", + "cost": "0.000044", "min": 0 } ] @@ -482,7 +485,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -491,7 +494,7 @@ "text": { "tiers": [ { - "cost": "0.0000275", + "cost": "0.00011", "min": 0 } ] @@ -533,6 +536,7 @@ "messages" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -540,14 +544,14 @@ "text": { "tiers": [ { - "cost": "0.000004", + "cost": "0.000016", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0 } ] @@ -555,7 +559,7 @@ "cache_write": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ] @@ -563,7 +567,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0 } ] @@ -574,7 +578,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -583,7 +587,7 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0 } ] @@ -598,14 +602,14 @@ "text": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0 } ] @@ -613,7 +617,7 @@ "cache_write": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -621,7 +625,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000016", + "cost": "0.000064", "min": 0 } ] @@ -632,7 +636,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -641,7 +645,7 @@ "text": { "tiers": [ { - "cost": "0.00004", + "cost": "0.00016", "min": 0 } ] @@ -656,14 +660,14 @@ "text": { "tiers": [ { - "cost": "0.0000088", + "cost": "0.0000352", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000044", + "cost": "0.00000176", "min": 0 } ] @@ -671,7 +675,7 @@ "cache_write": { "tiers": [ { - "cost": "0.000011", + "cost": "0.000044", "min": 0 } ] @@ -679,7 +683,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.0000176", + "cost": "0.0000704", "min": 0 } ] @@ -690,7 +694,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -699,7 +703,7 @@ "text": { "tiers": [ { - "cost": "0.000044", + "cost": "0.000176", "min": 0 } ] @@ -714,14 +718,14 @@ "text": { "tiers": [ { - "cost": "0.0000044", + "cost": "0.0000176", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000022", + "cost": "0.00000088", "min": 0 } ] @@ -729,7 +733,7 @@ "cache_write": { "tiers": [ { - "cost": "0.0000055", + "cost": "0.000022", "min": 0 } ] @@ -737,7 +741,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.0000088", + "cost": "0.0000352", "min": 0 } ] @@ -748,7 +752,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -757,7 +761,7 @@ "text": { "tiers": [ { - "cost": "0.000022", + "cost": "0.000088", "min": 0 } ] @@ -799,6 +803,7 @@ "messages" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -806,14 +811,14 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0 } ] @@ -821,7 +826,7 @@ "cache_write": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ] @@ -829,7 +834,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.000004", + "cost": "0.000016", "min": 0 } ] @@ -840,7 +845,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -849,7 +854,7 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -864,14 +869,14 @@ "text": { "tiers": [ { - "cost": "0.0000022", + "cost": "0.0000088", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000022", + "cost": "0.00000088", "min": 0 } ] @@ -879,7 +884,7 @@ "cache_write": { "tiers": [ { - "cost": "0.00000275", + "cost": "0.000011", "min": 0 } ] @@ -887,7 +892,7 @@ "cache_write_1h": { "tiers": [ { - "cost": "0.0000044", + "cost": "0.0000176", "min": 0 } ] @@ -898,7 +903,7 @@ "search": { "tiers": [ { - "cost": "0.01", + "cost": "0.04", "min": 0 } ], @@ -907,7 +912,7 @@ "text": { "tiers": [ { - "cost": "0.000011", + "cost": "0.000044", "min": 0 } ] @@ -950,11 +955,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0 } ] @@ -965,14 +971,14 @@ "text": { "tiers": [ { - "cost": "0.0000003", + "cost": "0.0000012", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000003", + "cost": "0.00000012", "min": 0 } ] @@ -981,7 +987,7 @@ "video": { "tiers": [ { - "cost": "0.0000003", + "cost": "0.0000012", "min": 0 } ] @@ -991,7 +997,7 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ] @@ -1003,7 +1009,7 @@ "audio": { "tiers": [ { - "cost": "0.0000018", + "cost": "0.0000072", "min": 0 } ] @@ -1014,14 +1020,14 @@ "text": { "tiers": [ { - "cost": "0.00000054", + "cost": "0.00000216", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000054", + "cost": "0.000000216", "min": 0 } ] @@ -1030,7 +1036,7 @@ "video": { "tiers": [ { - "cost": "0.00000054", + "cost": "0.00000216", "min": 0 } ] @@ -1040,7 +1046,7 @@ "text": { "tiers": [ { - "cost": "0.0000045", + "cost": "0.000018", "min": 0 } ] @@ -1084,6 +1090,7 @@ "image-generation" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -1091,7 +1098,7 @@ "text": { "tiers": [ { - "cost": "0.0000003", + "cost": "0.0000012", "min": 0 } ] @@ -1099,7 +1106,7 @@ "video": { "tiers": [ { - "cost": "0.0000003", + "cost": "0.0000012", "min": 0 } ] @@ -1109,7 +1116,7 @@ "image": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -1117,7 +1124,7 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ] @@ -1159,11 +1166,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.0000003", + "cost": "0.0000012", "min": 0 } ] @@ -1174,14 +1182,14 @@ "text": { "tiers": [ { - "cost": "0.0000001", + "cost": "0.0000004", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000001", + "cost": "0.00000004", "min": 0 } ] @@ -1190,7 +1198,7 @@ "video": { "tiers": [ { - "cost": "0.0000001", + "cost": "0.0000004", "min": 0 } ] @@ -1200,7 +1208,7 @@ "text": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0 } ] @@ -1212,7 +1220,7 @@ "audio": { "tiers": [ { - "cost": "0.00000054", + "cost": "0.00000216", "min": 0 } ] @@ -1223,14 +1231,14 @@ "text": { "tiers": [ { - "cost": "0.00000018", + "cost": "0.00000072", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000018", + "cost": "0.000000072", "min": 0 } ] @@ -1239,7 +1247,7 @@ "video": { "tiers": [ { - "cost": "0.00000018", + "cost": "0.00000072", "min": 0 } ] @@ -1249,7 +1257,7 @@ "text": { "tiers": [ { - "cost": "0.00000072", + "cost": "0.00000288", "min": 0 } ] @@ -1288,11 +1296,12 @@ "speech" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -1302,7 +1311,7 @@ "audio": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -1340,11 +1349,12 @@ "speech" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -1354,7 +1364,7 @@ "audio": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -1395,16 +1405,17 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0, "max": 200000 }, { - "cost": "0.0000025", + "cost": "0.00001", "min": 200000 } ] @@ -1415,24 +1426,24 @@ "text": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0, "max": 200000 }, { - "cost": "0.0000025", + "cost": "0.00001", "min": 200000 } ], "cache_read": { "tiers": [ { - "cost": "0.000000125", + "cost": "0.0000005", "min": 0, "max": 200000 }, { - "cost": "0.00000025", + "cost": "0.000001", "min": 200000 } ] @@ -1441,12 +1452,12 @@ "video": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0, "max": 200000 }, { - "cost": "0.0000025", + "cost": "0.00001", "min": 200000 } ] @@ -1456,12 +1467,12 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0, "max": 200000 }, { - "cost": "0.000015", + "cost": "0.00006", "min": 200000 } ] @@ -1473,12 +1484,12 @@ "audio": { "tiers": [ { - "cost": "0.00000225", + "cost": "0.000009", "min": 0, "max": 200000 }, { - "cost": "0.0000045", + "cost": "0.000018", "min": 200000 } ] @@ -1489,24 +1500,24 @@ "text": { "tiers": [ { - "cost": "0.00000225", + "cost": "0.000009", "min": 0, "max": 200000 }, { - "cost": "0.0000045", + "cost": "0.000018", "min": 200000 } ], "cache_read": { "tiers": [ { - "cost": "0.000000225", + "cost": "0.0000009", "min": 0, "max": 200000 }, { - "cost": "0.00000045", + "cost": "0.0000018", "min": 200000 } ] @@ -1515,12 +1526,12 @@ "video": { "tiers": [ { - "cost": "0.00000225", + "cost": "0.000009", "min": 0, "max": 200000 }, { - "cost": "0.0000045", + "cost": "0.000018", "min": 200000 } ] @@ -1530,12 +1541,12 @@ "text": { "tiers": [ { - "cost": "0.000018", + "cost": "0.000072", "min": 0, "max": 200000 }, { - "cost": "0.000027", + "cost": "0.000108", "min": 200000 } ] @@ -1577,11 +1588,12 @@ "speech" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0 } ] @@ -1591,7 +1603,7 @@ "audio": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0 } ] @@ -1632,11 +1644,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0 } ] @@ -1647,14 +1660,14 @@ "text": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000005", + "cost": "0.0000002", "min": 0 } ] @@ -1663,7 +1676,7 @@ "video": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -1673,7 +1686,7 @@ "text": { "tiers": [ { - "cost": "0.000003", + "cost": "0.000012", "min": 0 } ] @@ -1685,7 +1698,7 @@ "audio": { "tiers": [ { - "cost": "0.0000018", + "cost": "0.0000072", "min": 0 } ] @@ -1696,14 +1709,14 @@ "text": { "tiers": [ { - "cost": "0.0000009", + "cost": "0.0000036", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000009", + "cost": "0.00000036", "min": 0 } ] @@ -1712,7 +1725,7 @@ "video": { "tiers": [ { - "cost": "0.0000009", + "cost": "0.0000036", "min": 0 } ] @@ -1722,7 +1735,7 @@ "text": { "tiers": [ { - "cost": "0.0000054", + "cost": "0.0000216", "min": 0 } ] @@ -1769,6 +1782,7 @@ "image-generation" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -1776,14 +1790,14 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0 } ] @@ -1792,7 +1806,7 @@ "video": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -1802,7 +1816,7 @@ "image": { "tiers": [ { - "cost": "0.00012", + "cost": "0.00048", "min": 0 } ] @@ -1810,7 +1824,7 @@ "text": { "tiers": [ { - "cost": "0.000012", + "cost": "0.000048", "min": 0 } ] @@ -1853,6 +1867,7 @@ "image-generation" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -1860,14 +1875,14 @@ "text": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000005", + "cost": "0.0000002", "min": 0 } ] @@ -1876,7 +1891,7 @@ "video": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -1886,7 +1901,7 @@ "image": { "tiers": [ { - "cost": "0.00006", + "cost": "0.00024", "min": 0 } ] @@ -1894,7 +1909,7 @@ "text": { "tiers": [ { - "cost": "0.000003", + "cost": "0.000012", "min": 0 } ] @@ -1936,11 +1951,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -1951,14 +1967,14 @@ "text": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000025", + "cost": "0.0000001", "min": 0 } ] @@ -1967,7 +1983,7 @@ "video": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ] @@ -1977,7 +1993,7 @@ "text": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -1989,7 +2005,7 @@ "audio": { "tiers": [ { - "cost": "0.0000009", + "cost": "0.0000036", "min": 0 } ] @@ -2000,14 +2016,14 @@ "text": { "tiers": [ { - "cost": "0.00000045", + "cost": "0.0000018", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000045", + "cost": "0.00000018", "min": 0 } ] @@ -2016,7 +2032,7 @@ "video": { "tiers": [ { - "cost": "0.00000045", + "cost": "0.0000018", "min": 0 } ] @@ -2026,7 +2042,7 @@ "text": { "tiers": [ { - "cost": "0.0000027", + "cost": "0.0000108", "min": 0 } ] @@ -2069,6 +2085,7 @@ "image-generation" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -2076,14 +2093,14 @@ "text": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000025", + "cost": "0.0000001", "min": 0 } ] @@ -2092,7 +2109,7 @@ "video": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ] @@ -2102,7 +2119,7 @@ "image": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -2110,7 +2127,7 @@ "text": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -2150,11 +2167,12 @@ "speech" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0 } ] @@ -2164,7 +2182,7 @@ "audio": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0 } ] @@ -2205,16 +2223,17 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 200000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 200000 } ] @@ -2225,24 +2244,24 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 200000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 200000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0, "max": 200000 }, { - "cost": "0.0000004", + "cost": "0.0000016", "min": 200000 } ] @@ -2251,12 +2270,12 @@ "video": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 200000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 200000 } ] @@ -2266,12 +2285,12 @@ "text": { "tiers": [ { - "cost": "0.000012", + "cost": "0.000048", "min": 0, "max": 200000 }, { - "cost": "0.000018", + "cost": "0.000072", "min": 200000 } ] @@ -2283,12 +2302,12 @@ "audio": { "tiers": [ { - "cost": "0.0000036", + "cost": "0.0000144", "min": 0, "max": 200000 }, { - "cost": "0.0000072", + "cost": "0.0000288", "min": 200000 } ] @@ -2299,24 +2318,24 @@ "text": { "tiers": [ { - "cost": "0.0000036", + "cost": "0.0000144", "min": 0, "max": 200000 }, { - "cost": "0.0000072", + "cost": "0.0000288", "min": 200000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000036", + "cost": "0.00000144", "min": 0, "max": 200000 }, { - "cost": "0.00000072", + "cost": "0.00000288", "min": 200000 } ] @@ -2325,12 +2344,12 @@ "video": { "tiers": [ { - "cost": "0.0000036", + "cost": "0.0000144", "min": 0, "max": 200000 }, { - "cost": "0.0000072", + "cost": "0.0000288", "min": 200000 } ] @@ -2340,12 +2359,12 @@ "text": { "tiers": [ { - "cost": "0.0000216", + "cost": "0.0000864", "min": 0, "max": 200000 }, { - "cost": "0.0000324", + "cost": "0.0001296", "min": 200000 } ] @@ -2389,11 +2408,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -2404,14 +2424,14 @@ "text": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000015", + "cost": "0.0000006", "min": 0 } ] @@ -2420,7 +2440,7 @@ "video": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -2430,7 +2450,7 @@ "text": { "tiers": [ { - "cost": "0.000009", + "cost": "0.000036", "min": 0 } ] @@ -2442,7 +2462,7 @@ "audio": { "tiers": [ { - "cost": "0.0000027", + "cost": "0.0000108", "min": 0 } ] @@ -2453,14 +2473,14 @@ "text": { "tiers": [ { - "cost": "0.0000027", + "cost": "0.0000108", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000027", + "cost": "0.00000108", "min": 0 } ] @@ -2469,7 +2489,7 @@ "video": { "tiers": [ { - "cost": "0.0000027", + "cost": "0.0000108", "min": 0 } ] @@ -2479,7 +2499,7 @@ "text": { "tiers": [ { - "cost": "0.0000162", + "cost": "0.0000648", "min": 0 } ] @@ -2521,11 +2541,12 @@ "transcription" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -2533,7 +2554,7 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -2543,7 +2564,7 @@ "text": { "tiers": [ { - "cost": "0.000012", + "cost": "0.000048", "min": 0 } ] @@ -2584,11 +2605,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ] @@ -2599,14 +2621,14 @@ "text": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000075", + "cost": "0.0000003", "min": 0 } ] @@ -2615,7 +2637,7 @@ "video": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ] @@ -2625,7 +2647,7 @@ "text": { "tiers": [ { - "cost": "0.00000375", + "cost": "0.000015", "min": 0 } ] @@ -2637,7 +2659,7 @@ "audio": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ] @@ -2648,14 +2670,14 @@ "text": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000135", + "cost": "0.00000054", "min": 0 } ] @@ -2664,7 +2686,7 @@ "video": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ] @@ -2674,7 +2696,7 @@ "text": { "tiers": [ { - "cost": "0.00000675", + "cost": "0.000027", "min": 0 } ] @@ -2718,11 +2740,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ] @@ -2733,14 +2756,14 @@ "text": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000075", + "cost": "0.0000003", "min": 0 } ] @@ -2749,7 +2772,7 @@ "video": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ] @@ -2759,7 +2782,7 @@ "text": { "tiers": [ { - "cost": "0.00000375", + "cost": "0.000015", "min": 0 } ] @@ -2771,7 +2794,7 @@ "audio": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ] @@ -2782,14 +2805,14 @@ "text": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000135", + "cost": "0.00000054", "min": 0 } ] @@ -2798,7 +2821,7 @@ "video": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ] @@ -2808,7 +2831,7 @@ "text": { "tiers": [ { - "cost": "0.00000675", + "cost": "0.000027", "min": 0 } ] @@ -2851,11 +2874,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ] @@ -2866,14 +2890,14 @@ "text": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000075", + "cost": "0.0000003", "min": 0 } ] @@ -2882,7 +2906,7 @@ "video": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ] @@ -2892,7 +2916,7 @@ "text": { "tiers": [ { - "cost": "0.00000375", + "cost": "0.000015", "min": 0 } ] @@ -2904,7 +2928,7 @@ "audio": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ] @@ -2915,14 +2939,14 @@ "text": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000135", + "cost": "0.00000054", "min": 0 } ] @@ -2931,7 +2955,7 @@ "video": { "tiers": [ { - "cost": "0.00000135", + "cost": "0.0000054", "min": 0 } ] @@ -2941,7 +2965,7 @@ "text": { "tiers": [ { - "cost": "0.00000675", + "cost": "0.000027", "min": 0 } ] @@ -2984,11 +3008,12 @@ "chat-completions" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -2999,14 +3024,14 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000001", + "cost": "0.0000004", "min": 0 } ] @@ -3015,7 +3040,7 @@ "video": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -3025,7 +3050,7 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -3063,11 +3088,12 @@ "embeddings" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.00000015", + "cost": "0.0000006", "min": 0 } ] @@ -3110,11 +3136,12 @@ "embeddings" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.0000065", + "cost": "0.000026", "min": 0 } ] @@ -3122,7 +3149,7 @@ "image": { "tiers": [ { - "cost": "0.00000045", + "cost": "0.0000018", "min": 0 } ] @@ -3130,7 +3157,7 @@ "text": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0 } ] @@ -3138,7 +3165,7 @@ "video": { "tiers": [ { - "cost": "0.000012", + "cost": "0.000048", "min": 0 } ] @@ -3180,11 +3207,12 @@ "videos" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -3192,7 +3220,7 @@ "image": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -3200,7 +3228,7 @@ "text": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -3208,7 +3236,7 @@ "video": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ] @@ -3216,7 +3244,7 @@ }, "video_duration": { "720p": { - "cost_per_second": "0.0000175" + "cost_per_second": "0.00007" } } }, @@ -3251,11 +3279,12 @@ "music" ], "pricing": { + "cost_currency": "credits", "output": { "audio": { "tiers": [ { - "cost": "0.04", + "cost": "0.16", "min": 0 } ], @@ -3294,11 +3323,12 @@ "music" ], "pricing": { + "cost_currency": "credits", "output": { "audio": { "tiers": [ { - "cost": "0.08", + "cost": "0.32", "min": 0 } ], @@ -3339,15 +3369,16 @@ "videos" ], "pricing": { + "cost_currency": "credits", "video_duration": { "1080p": { - "cost_per_second": "0.4" + "cost_per_second": "1.6" }, "4k": { - "cost_per_second": "0.6" + "cost_per_second": "2.4" }, "720p": { - "cost_per_second": "0.4" + "cost_per_second": "1.6" } } }, @@ -3382,15 +3413,16 @@ "videos" ], "pricing": { + "cost_currency": "credits", "video_duration": { "1080p": { - "cost_per_second": "0.12" + "cost_per_second": "0.48" }, "4k": { - "cost_per_second": "0.3" + "cost_per_second": "1.2" }, "720p": { - "cost_per_second": "0.1" + "cost_per_second": "0.4" } } }, @@ -3425,12 +3457,13 @@ "videos" ], "pricing": { + "cost_currency": "credits", "video_duration": { "1080p": { - "cost_per_second": "0.08" + "cost_per_second": "0.32" }, "720p": { - "cost_per_second": "0.05" + "cost_per_second": "0.2" } } }, @@ -3466,6 +3499,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -3473,14 +3507,14 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -3491,7 +3525,7 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -3530,11 +3564,12 @@ "transcription" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0 } ] @@ -3542,7 +3577,7 @@ "text": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0 } ] @@ -3552,7 +3587,7 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ] @@ -3589,11 +3624,12 @@ "speech" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.0000006", + "cost": "0.0000024", "min": 0 } ] @@ -3603,7 +3639,7 @@ "audio": { "tiers": [ { - "cost": "0.000012", + "cost": "0.000048", "min": 0 } ] @@ -3643,11 +3679,12 @@ "transcription" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ] @@ -3655,7 +3692,7 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ] @@ -3665,7 +3702,7 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -3705,6 +3742,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -3712,14 +3750,14 @@ "text": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000125", + "cost": "0.0000005", "min": 0 } ] @@ -3730,7 +3768,7 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0 } ] @@ -3745,14 +3783,14 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ] @@ -3763,7 +3801,7 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0 } ] @@ -3806,6 +3844,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -3813,14 +3852,14 @@ "text": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000025", + "cost": "0.0000001", "min": 0 } ] @@ -3831,7 +3870,7 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -3846,14 +3885,14 @@ "text": { "tiers": [ { - "cost": "0.00000045", + "cost": "0.0000018", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000045", + "cost": "0.00000018", "min": 0 } ] @@ -3864,7 +3903,7 @@ "text": { "tiers": [ { - "cost": "0.0000036", + "cost": "0.0000144", "min": 0 } ] @@ -3907,6 +3946,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -3914,14 +3954,14 @@ "text": { "tiers": [ { - "cost": "0.00000005", + "cost": "0.0000002", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000005", + "cost": "0.00000002", "min": 0 } ] @@ -3932,7 +3972,7 @@ "text": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0 } ] @@ -3973,6 +4013,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -3980,14 +4021,14 @@ "text": { "tiers": [ { - "cost": "0.00000175", + "cost": "0.000007", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000175", + "cost": "0.0000007", "min": 0 } ] @@ -3998,7 +4039,7 @@ "text": { "tiers": [ { - "cost": "0.000014", + "cost": "0.000056", "min": 0 } ] @@ -4013,14 +4054,14 @@ "text": { "tiers": [ { - "cost": "0.0000035", + "cost": "0.000014", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000035", + "cost": "0.0000014", "min": 0 } ] @@ -4031,7 +4072,7 @@ "text": { "tiers": [ { - "cost": "0.000028", + "cost": "0.000112", "min": 0 } ] @@ -4074,6 +4115,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4081,24 +4123,24 @@ "text": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0, "max": 272000 }, { - "cost": "0.000005", + "cost": "0.00002", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000025", + "cost": "0.000001", "min": 0, "max": 272000 }, { - "cost": "0.0000005", + "cost": "0.000002", "min": 272000 } ] @@ -4109,12 +4151,12 @@ "text": { "tiers": [ { - "cost": "0.000015", + "cost": "0.00006", "min": 0, "max": 272000 }, { - "cost": "0.0000225", + "cost": "0.00009", "min": 272000 } ] @@ -4129,14 +4171,14 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0 } ] @@ -4147,7 +4189,7 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -4190,6 +4232,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4197,14 +4240,14 @@ "text": { "tiers": [ { - "cost": "0.00000075", + "cost": "0.000003", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.000000075", + "cost": "0.0000003", "min": 0 } ] @@ -4215,7 +4258,7 @@ "text": { "tiers": [ { - "cost": "0.0000045", + "cost": "0.000018", "min": 0 } ] @@ -4230,14 +4273,14 @@ "text": { "tiers": [ { - "cost": "0.0000015", + "cost": "0.000006", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000015", + "cost": "0.0000006", "min": 0 } ] @@ -4248,7 +4291,7 @@ "text": { "tiers": [ { - "cost": "0.000009", + "cost": "0.000036", "min": 0 } ] @@ -4291,6 +4334,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4298,14 +4342,14 @@ "text": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000002", + "cost": "0.00000008", "min": 0 } ] @@ -4316,7 +4360,7 @@ "text": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0 } ] @@ -4356,6 +4400,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4363,24 +4408,24 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0, "max": 272000 }, { - "cost": "0.00006", + "cost": "0.00024", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000003", + "cost": "0.000012", "min": 0, "max": 272000 }, { - "cost": "0.000006", + "cost": "0.000024", "min": 272000 } ] @@ -4391,12 +4436,12 @@ "text": { "tiers": [ { - "cost": "0.00018", + "cost": "0.00072", "min": 0, "max": 272000 }, { - "cost": "0.00027", + "cost": "0.00108", "min": 272000 } ] @@ -4438,6 +4483,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4445,24 +4491,24 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0, "max": 272000 }, { - "cost": "0.00001", + "cost": "0.00004", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0, "max": 272000 }, { - "cost": "0.000001", + "cost": "0.000004", "min": 272000 } ] @@ -4473,12 +4519,12 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0, "max": 272000 }, { - "cost": "0.000045", + "cost": "0.00018", "min": 272000 } ] @@ -4493,14 +4539,14 @@ "text": { "tiers": [ { - "cost": "0.0000125", + "cost": "0.00005", "min": 0 } ], "cache_read": { "tiers": [ { - "cost": "0.00000125", + "cost": "0.000005", "min": 0 } ] @@ -4511,7 +4557,7 @@ "text": { "tiers": [ { - "cost": "0.000075", + "cost": "0.0003", "min": 0 } ] @@ -4553,6 +4599,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4560,24 +4607,24 @@ "text": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0, "max": 272000 }, { - "cost": "0.00006", + "cost": "0.00024", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0, "max": 272000 }, { - "cost": "0.00006", + "cost": "0.00024", "min": 272000 } ] @@ -4588,12 +4635,12 @@ "text": { "tiers": [ { - "cost": "0.00018", + "cost": "0.00072", "min": 0, "max": 272000 }, { - "cost": "0.00027", + "cost": "0.00108", "min": 272000 } ] @@ -4633,6 +4680,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4640,24 +4688,24 @@ "text": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0, "max": 272000 }, { - "cost": "0.0000004", + "cost": "0.0000016", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000002", + "cost": "0.00000008", "min": 0, "max": 272000 }, { - "cost": "0.00000004", + "cost": "0.00000016", "min": 272000 } ] @@ -4668,12 +4716,12 @@ "text": { "tiers": [ { - "cost": "0.0000012", + "cost": "0.0000048", "min": 0, "max": 272000 }, { - "cost": "0.0000018", + "cost": "0.0000072", "min": 272000 } ] @@ -4688,24 +4736,24 @@ "text": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0, "max": 272000 }, { - "cost": "0.0000008", + "cost": "0.0000032", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000004", + "cost": "0.00000016", "min": 0, "max": 272000 }, { - "cost": "0.00000008", + "cost": "0.00000032", "min": 272000 } ] @@ -4716,12 +4764,12 @@ "text": { "tiers": [ { - "cost": "0.0000024", + "cost": "0.0000096", "min": 0, "max": 272000 }, { - "cost": "0.0000036", + "cost": "0.0000144", "min": 272000 } ] @@ -4766,6 +4814,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4773,24 +4822,24 @@ "text": { "tiers": [ { - "cost": "0.000004", + "cost": "0.000016", "min": 0, "max": 272000 }, { - "cost": "0.000008", + "cost": "0.000032", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0, "max": 272000 }, { - "cost": "0.0000008", + "cost": "0.0000032", "min": 272000 } ] @@ -4801,12 +4850,12 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0, "max": 272000 }, { - "cost": "0.00003", + "cost": "0.00012", "min": 272000 } ] @@ -4821,24 +4870,24 @@ "text": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0, "max": 272000 }, { - "cost": "0.000016", + "cost": "0.000064", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000008", + "cost": "0.0000032", "min": 0, "max": 272000 }, { - "cost": "0.0000016", + "cost": "0.0000064", "min": 272000 } ] @@ -4849,12 +4898,12 @@ "text": { "tiers": [ { - "cost": "0.00004", + "cost": "0.00016", "min": 0, "max": 272000 }, { - "cost": "0.00006", + "cost": "0.00024", "min": 272000 } ] @@ -4897,6 +4946,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -4904,24 +4954,24 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 272000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0, "max": 272000 }, { - "cost": "0.0000004", + "cost": "0.0000016", "min": 272000 } ] @@ -4932,12 +4982,12 @@ "text": { "tiers": [ { - "cost": "0.000012", + "cost": "0.000048", "min": 0, "max": 272000 }, { - "cost": "0.000018", + "cost": "0.000072", "min": 272000 } ] @@ -4952,24 +5002,24 @@ "text": { "tiers": [ { - "cost": "0.000004", + "cost": "0.000016", "min": 0, "max": 272000 }, { - "cost": "0.000008", + "cost": "0.000032", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0, "max": 272000 }, { - "cost": "0.0000008", + "cost": "0.0000032", "min": 272000 } ] @@ -4980,12 +5030,12 @@ "text": { "tiers": [ { - "cost": "0.000024", + "cost": "0.000096", "min": 0, "max": 272000 }, { - "cost": "0.000036", + "cost": "0.000144", "min": 272000 } ] @@ -5030,6 +5080,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -5037,24 +5088,24 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0, "max": 272000 }, { - "cost": "0.00002", + "cost": "0.00008", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0, "max": 272000 }, { - "cost": "0.000002", + "cost": "0.000008", "min": 272000 } ] @@ -5062,12 +5113,12 @@ "cache_write": { "tiers": [ { - "cost": "0.0000125", + "cost": "0.00005", "min": 0, "max": 272000 }, { - "cost": "0.000025", + "cost": "0.0001", "min": 272000 } ] @@ -5078,12 +5129,12 @@ "text": { "tiers": [ { - "cost": "0.00005", + "cost": "0.0002", "min": 0, "max": 272000 }, { - "cost": "0.000075", + "cost": "0.0003", "min": 272000 } ] @@ -5098,24 +5149,24 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0, "max": 272000 }, { - "cost": "0.00004", + "cost": "0.00016", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 272000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 272000 } ] @@ -5123,12 +5174,12 @@ "cache_write": { "tiers": [ { - "cost": "0.000025", + "cost": "0.0001", "min": 0, "max": 272000 }, { - "cost": "0.00005", + "cost": "0.0002", "min": 272000 } ] @@ -5139,12 +5190,12 @@ "text": { "tiers": [ { - "cost": "0.0001", + "cost": "0.0004", "min": 0, "max": 272000 }, { - "cost": "0.00015", + "cost": "0.0006", "min": 272000 } ] @@ -5187,6 +5238,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -5194,24 +5246,24 @@ "text": { "tiers": [ { - "cost": "0.0000001", + "cost": "0.0000004", "min": 0, "max": 272000 }, { - "cost": "0.0000002", + "cost": "0.0000008", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000001", + "cost": "0.00000004", "min": 0, "max": 272000 }, { - "cost": "0.00000002", + "cost": "0.00000008", "min": 272000 } ] @@ -5222,12 +5274,12 @@ "text": { "tiers": [ { - "cost": "0.0000005", + "cost": "0.000002", "min": 0, "max": 272000 }, { - "cost": "0.00000075", + "cost": "0.000003", "min": 272000 } ] @@ -5242,24 +5294,24 @@ "text": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0, "max": 272000 }, { - "cost": "0.0000004", + "cost": "0.0000016", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.00000002", + "cost": "0.00000008", "min": 0, "max": 272000 }, { - "cost": "0.00000004", + "cost": "0.00000016", "min": 272000 } ] @@ -5270,12 +5322,12 @@ "text": { "tiers": [ { - "cost": "0.000001", + "cost": "0.000004", "min": 0, "max": 272000 }, { - "cost": "0.0000015", + "cost": "0.000006", "min": 272000 } ] @@ -5318,6 +5370,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -5325,24 +5378,24 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 272000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0, "max": 272000 }, { - "cost": "0.0000004", + "cost": "0.0000016", "min": 272000 } ] @@ -5353,12 +5406,12 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0, "max": 272000 }, { - "cost": "0.000015", + "cost": "0.00006", "min": 272000 } ] @@ -5373,24 +5426,24 @@ "text": { "tiers": [ { - "cost": "0.000004", + "cost": "0.000016", "min": 0, "max": 272000 }, { - "cost": "0.000008", + "cost": "0.000032", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000004", + "cost": "0.0000016", "min": 0, "max": 272000 }, { - "cost": "0.0000008", + "cost": "0.0000032", "min": 272000 } ] @@ -5401,12 +5454,12 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0, "max": 272000 }, { - "cost": "0.00003", + "cost": "0.00012", "min": 272000 } ] @@ -5449,6 +5502,7 @@ "responses" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "billed_as": "text" @@ -5456,24 +5510,24 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0, "max": 272000 }, { - "cost": "0.000004", + "cost": "0.000016", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000001", + "cost": "0.0000004", "min": 0, "max": 272000 }, { - "cost": "0.0000002", + "cost": "0.0000008", "min": 272000 } ] @@ -5481,12 +5535,12 @@ "cache_write": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0, "max": 272000 }, { - "cost": "0.000005", + "cost": "0.00002", "min": 272000 } ] @@ -5497,12 +5551,12 @@ "text": { "tiers": [ { - "cost": "0.00001", + "cost": "0.00004", "min": 0, "max": 272000 }, { - "cost": "0.000015", + "cost": "0.00006", "min": 272000 } ] @@ -5517,24 +5571,24 @@ "text": { "tiers": [ { - "cost": "0.000004", + "cost": "0.000016", "min": 0, "max": 272000 }, { - "cost": "0.000008", + "cost": "0.000032", "min": 272000 } ], "cache_read": { "tiers": [ { - "cost": "0.0000002", + "cost": "0.0000008", "min": 0, "max": 272000 }, { - "cost": "0.0000004", + "cost": "0.0000016", "min": 272000 } ] @@ -5542,12 +5596,12 @@ "cache_write": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0, "max": 272000 }, { - "cost": "0.00001", + "cost": "0.00004", "min": 272000 } ] @@ -5558,12 +5612,12 @@ "text": { "tiers": [ { - "cost": "0.00002", + "cost": "0.00008", "min": 0, "max": 272000 }, { - "cost": "0.00003", + "cost": "0.00012", "min": 272000 } ] @@ -5605,11 +5659,12 @@ "image-edit" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "tiers": [ { - "cost": "0.0000025", + "cost": "0.00001", "min": 0 } ] @@ -5617,7 +5672,7 @@ "text": { "tiers": [ { - "cost": "0.000002", + "cost": "0.000008", "min": 0 } ] @@ -5627,7 +5682,7 @@ "image": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0 } ] @@ -5669,11 +5724,12 @@ "image-edit" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0 } ] @@ -5681,7 +5737,7 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ] @@ -5691,7 +5747,7 @@ "image": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -5731,11 +5787,12 @@ "image-edit" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0 } ] @@ -5743,7 +5800,7 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ] @@ -5753,7 +5810,7 @@ "image": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -5795,11 +5852,12 @@ "image-edit" ], "pricing": { + "cost_currency": "credits", "input": { "image": { "tiers": [ { - "cost": "0.000008", + "cost": "0.000032", "min": 0 } ] @@ -5807,7 +5865,7 @@ "text": { "tiers": [ { - "cost": "0.000005", + "cost": "0.00002", "min": 0 } ] @@ -5817,7 +5875,7 @@ "image": { "tiers": [ { - "cost": "0.00003", + "cost": "0.00012", "min": 0 } ] @@ -5858,11 +5916,12 @@ "live" ], "pricing": { + "cost_currency": "credits", "output": { "audio": { "tiers": [ { - "cost": "0.000833333", + "cost": "0.003333332", "min": 0 } ], @@ -5903,11 +5962,12 @@ "transcription" ], "pricing": { + "cost_currency": "credits", "input": { "audio": { "tiers": [ { - "cost": "0.000075", + "cost": "0.0003", "min": 0 } ], @@ -5947,11 +6007,12 @@ "embeddings" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.00000013", + "cost": "0.00000052", "min": 0 } ] @@ -5988,11 +6049,12 @@ "embeddings" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.00000002", + "cost": "0.00000008", "min": 0 } ] @@ -6029,11 +6091,12 @@ "systemone" ], "pricing": { + "cost_currency": "credits", "input": { "text": { "tiers": [ { - "cost": "0.000000042", + "cost": "0.000000168", "min": 0 } ] diff --git a/scripts/neon.models.json b/scripts/neon.models.json index 23d55bfe65..2de4c883bb 100644 --- a/scripts/neon.models.json +++ b/scripts/neon.models.json @@ -2,7 +2,8 @@ { "id": "bge-large-en", "name": "BGE Large (En)", - "provider": "baai", + "lab": "baai", + "provider": "databricks", "family": "text-embedding", "released": true, "type": "embedding", @@ -21,7 +22,8 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": true + "embeddings": true, + "decision": false }, "use_case": "chat", "unsupported": "bge-large-en does not serve chat completions. It is an embedding model — see the embeddings use case." @@ -29,7 +31,8 @@ { "id": "claude-fable-5", "name": "Claude Fable 5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-fable", "released": true, "attachment": true, @@ -70,14 +73,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-fable-5-1", "name": "Claude Fable 5.1", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-fable", "released": true, "attachment": true, @@ -118,14 +123,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-haiku-4-5", "name": "Claude Haiku 4.5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-haiku", "released": true, "attachment": true, @@ -170,14 +177,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-haiku-5-5", "name": "Claude Haiku 5.5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-haiku", "released": true, "attachment": true, @@ -241,14 +250,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-4-1", "name": "Claude Opus 4.1", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -293,14 +304,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-4-5", "name": "Claude Opus 4.5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -345,14 +358,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-4-6", "name": "Claude Opus 4.6", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -397,14 +412,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-4-7", "name": "Claude Opus 4.7", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -448,14 +465,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-4-8", "name": "Claude Opus 4.8", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -499,14 +518,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-5", "name": "Claude Opus 5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -550,14 +571,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-opus-5-5", "name": "Claude Opus 5.5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-opus", "released": true, "attachment": true, @@ -600,14 +623,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-sonnet-4-5", "name": "Claude Sonnet 4.5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-sonnet", "released": true, "attachment": true, @@ -652,14 +677,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-sonnet", "released": true, "attachment": true, @@ -704,14 +731,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-sonnet-5", "name": "Claude Sonnet 5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-sonnet", "released": true, "attachment": true, @@ -755,14 +784,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "claude-sonnet-5-5", "name": "Claude Sonnet 5.5", - "provider": "anthropic", + "lab": "anthropic", + "provider": "databricks", "family": "claude-sonnet", "released": true, "attachment": true, @@ -805,14 +836,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "deepseek-v4-1-flash", "name": "DeepSeek V4.1 Flash", - "provider": "deepseek", + "lab": "deepseek", + "provider": "databricks", "family": "deepseek-flash", "released": true, "attachment": true, @@ -845,14 +878,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-1-flash-lite", "name": "Gemini 3.1 Flash Lite", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash-lite", "released": true, "attachment": true, @@ -893,14 +928,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-1-pro", "name": "Gemini 3.1 Pro", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-pro", "released": true, "attachment": true, @@ -956,14 +993,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-5-flash", "name": "Gemini 3.5 Flash", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash", "released": true, "attachment": true, @@ -1004,14 +1043,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-5-flash-lite", "name": "Gemini 3.5 Flash Lite", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash-lite", "released": true, "attachment": true, @@ -1051,14 +1092,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-6-flash", "name": "Gemini 3.6 Flash", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash", "released": true, "attachment": true, @@ -1099,14 +1142,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-7-flash", "name": "Gemini 3.7 Flash", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash", "released": true, "attachment": true, @@ -1150,14 +1195,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-8-flash", "name": "Gemini 3.8 Flash", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash", "released": true, "attachment": true, @@ -1199,14 +1246,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemini-3-flash", "name": "Gemini 3 Flash", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemini-flash", "released": true, "attachment": true, @@ -1247,14 +1296,70 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false + }, + "use_case": "chat" + }, + { + "id": "gemini-4-argon", + "name": "Gemini 4 Argon", + "lab": "google", + "provider": "databricks", + "family": "gemini", + "released": true, + "attachment": true, + "reasoning": true, + "reasoning_options": [ + { + "type": "effort", + "values": ["low", "medium", "high"] + } + ], + "tool_call": true, + "temperature": false, + "structured_output": true, + "open_weights": false, + "knowledge": "2026-03", + "release_date": "2026-10-13", + "last_updated": "2026-10-13", + "modalities": { + "input": ["text", "image", "video", "audio", "pdf"], + "output": ["text"] + }, + "limit": { + "context": 1048576, + "output": 65536 + }, + "cost": { + "input": 4, + "output": 20, + "cache_read": 0.2 + }, + "blended_cost": 8, + "capabilities": { + "entitled": true, + "chat": "array-content", + "deviations": [ + "`id` is null; the spec requires a string", + "`content` is an array[1] of {text} with keys {text, thoughtSignature, type}; the spec requires a string", + "`usage.total_tokens` is 240, but prompt + completion is 46", + "`usage.reasoning_tokens` is top-level; the spec nests it under `completion_tokens_details`" + ], + "native_dialect": "gemini", + "responses": false, + "web_search": false, + "image_generation": false, + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gemma-3-12b", "name": "Gemma 3 12B", - "provider": "google", + "lab": "google", + "provider": "databricks", "family": "gemma", "released": true, "attachment": true, @@ -1287,14 +1392,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "glm-5-2", "name": "GLM 5.2", - "provider": "zhipuai", + "lab": "zhipuai", + "provider": "databricks", "family": "glm", "released": true, "attachment": false, @@ -1336,14 +1443,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "glm-5-3", "name": "GLM 5.3", - "provider": "zhipuai", + "lab": "zhipuai", + "provider": "databricks", "family": "glm", "released": true, "attachment": false, @@ -1382,14 +1491,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "glm-5-3-flash", "name": "GLM 5.3 Flash", - "provider": "zhipuai", + "lab": "zhipuai", + "provider": "databricks", "family": "glm-flash", "released": true, "attachment": true, @@ -1428,14 +1539,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5", "name": "GPT-5", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt", "released": true, "attachment": true, @@ -1476,14 +1589,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-1", "name": "GPT-5.1", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt", "released": true, "attachment": true, @@ -1524,14 +1639,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-2", "name": "GPT-5.2", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt", "released": true, "attachment": true, @@ -1572,14 +1689,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-3-codex", "name": "GPT-5.3 Codex", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-codex", "released": true, "attachment": true, @@ -1620,14 +1739,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-4", "name": "GPT-5.4", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt", "released": true, "attachment": true, @@ -1684,14 +1805,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-4-mini", "name": "GPT-5.4 Mini", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-mini", "released": true, "attachment": true, @@ -1732,14 +1855,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-4-nano", "name": "GPT-5.4 Nano", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-nano", "released": true, "attachment": true, @@ -1780,14 +1905,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-5", "name": "GPT-5.5", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt", "released": true, "attachment": true, @@ -1844,14 +1971,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-5-pro", "name": "GPT-5.5 Pro", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-pro", "released": true, "attachment": true, @@ -1905,14 +2034,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-6-luna", "name": "GPT-5.6 Luna", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-luna", "released": true, "attachment": true, @@ -1972,14 +2103,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-6-sol", "name": "GPT-5.6 Sol", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-sol", "released": true, "attachment": true, @@ -2039,14 +2172,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-6-terra", "name": "GPT-5.6 Terra", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-terra", "released": true, "attachment": true, @@ -2106,14 +2241,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-mini", "name": "GPT-5 Mini", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-mini", "released": true, "attachment": true, @@ -2154,14 +2291,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-5-nano", "name": "GPT-5 Nano", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-nano", "released": true, "attachment": true, @@ -2202,14 +2341,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-6-1-sol", "name": "GPT-6.1 Sol", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-sol", "released": true, "attachment": true, @@ -2268,14 +2409,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-6-astra", "name": "GPT-6 Astra", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-astra", "released": true, "attachment": true, @@ -2335,14 +2478,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-6-luna", "name": "GPT-6 Luna", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-luna", "released": true, "attachment": true, @@ -2401,14 +2546,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-6-sol", "name": "GPT-6 Sol", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-sol", "released": true, "attachment": true, @@ -2467,14 +2614,16 @@ "responses": true, "web_search": true, "image_generation": true, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-oss-120b", "name": "GPT OSS 120B", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-oss", "released": true, "attachment": false, @@ -2512,14 +2661,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gpt-oss-20b", "name": "GPT OSS 20B", - "provider": "openai", + "lab": "openai", + "provider": "databricks", "family": "gpt-oss", "released": true, "attachment": false, @@ -2557,14 +2708,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "grok-4-6", "name": "Grok 4.6", - "provider": "xai", + "lab": "xai", + "provider": "databricks", "family": "grok", "released": true, "attachment": true, @@ -2604,14 +2757,16 @@ "responses": true, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "grok-4-7", "name": "Grok 4.7", - "provider": "xai", + "lab": "xai", + "provider": "databricks", "family": "grok", "released": true, "attachment": false, @@ -2650,14 +2805,16 @@ "responses": true, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "gte-large-en", "name": "GTE Large (En)", - "provider": "alibaba", + "lab": "alibaba", + "provider": "databricks", "family": "text-embedding", "released": true, "type": "embedding", @@ -2676,7 +2833,8 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": true + "embeddings": true, + "decision": false }, "use_case": "chat", "unsupported": "gte-large-en does not serve chat completions. It is an embedding model — see the embeddings use case." @@ -2684,7 +2842,8 @@ { "id": "inkling", "name": "Inkling", - "provider": "thinkingmachines", + "lab": "thinkingmachines", + "provider": "databricks", "family": "ling", "released": true, "attachment": true, @@ -2726,14 +2885,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "kimi-k3", "name": "Kimi K3", - "provider": "moonshotai", + "lab": "moonshotai", + "provider": "databricks", "family": "kimi-k3", "released": true, "attachment": true, @@ -2775,14 +2936,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "llama-4-maverick", "name": "Llama 4 Maverick", - "provider": "meta", + "lab": "meta", + "provider": "databricks", "family": "llama", "released": true, "attachment": true, @@ -2815,14 +2978,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "meta-llama-3-1-8b-instruct", "name": "Meta Llama 3.1 8B Instruct", - "provider": "meta", + "lab": "meta", + "provider": "databricks", "family": "llama", "released": true, "attachment": false, @@ -2855,14 +3020,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "meta-llama-3-3-70b-instruct", "name": "Meta Llama 3.3 70B Instruct", - "provider": "meta", + "lab": "meta", + "provider": "databricks", "family": "llama", "released": true, "attachment": false, @@ -2895,14 +3062,47 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, + { + "id": "openjev-qwen35-4b", + "name": "OpenJev (Qwen 3.5 4B)", + "lab": "typesafe", + "provider": "databricks", + "family": "openjev", + "released": true, + "type": "decision", + "open_weights": true, + "release_date": "2026-10-01", + "last_updated": "2026-10-01", + "limit": { + "context": 131072 + }, + "cost": { + "input": 0.042 + }, + "capabilities": { + "entitled": true, + "chat": "not-served", + "deviations": [], + "native_dialect": "none", + "responses": false, + "web_search": false, + "image_generation": false, + "embeddings": false, + "decision": true + }, + "use_case": "chat", + "unsupported": "openjev-qwen35-4b is a System One decision model served only on /typesafe/v1/systemone — see the systemone use case." + }, { "id": "qwen3-embedding-0-6b", "name": "Qwen3 Embedding 0.6B", - "provider": "alibaba", + "lab": "alibaba", + "provider": "databricks", "family": "text-embedding", "released": true, "type": "embedding", @@ -2921,7 +3121,8 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": true + "embeddings": true, + "decision": false }, "use_case": "chat", "unsupported": "qwen3-embedding-0-6b does not serve chat completions. It is an embedding model — see the embeddings use case." @@ -2929,7 +3130,8 @@ { "id": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next Instruct", - "provider": "alibaba", + "lab": "alibaba", + "provider": "databricks", "family": "qwen", "released": true, "attachment": false, @@ -2962,14 +3164,16 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" }, { "id": "qwen35-122b-a10b", "name": "Qwen3.5 122B A10B", - "provider": "alibaba", + "lab": "alibaba", + "provider": "databricks", "family": "qwen", "released": true, "attachment": false, @@ -3007,8 +3211,40 @@ "responses": false, "web_search": false, "image_generation": false, - "embeddings": false + "embeddings": false, + "decision": false }, "use_case": "chat" + }, + { + "id": "typesafeai-jev-1-14-0", + "name": "Jev 1.14", + "lab": "typesafe", + "provider": "typesafe", + "family": "jev", + "released": true, + "type": "decision", + "open_weights": false, + "release_date": "2026-10-15", + "last_updated": "2026-10-15", + "limit": { + "context": 65536 + }, + "cost": { + "input": 0.042 + }, + "capabilities": { + "entitled": true, + "chat": "not-served", + "deviations": [], + "native_dialect": "none", + "responses": false, + "web_search": false, + "image_generation": false, + "embeddings": false, + "decision": true + }, + "use_case": "chat", + "unsupported": "typesafeai-jev-1-14-0 is a System One decision model served only on /typesafe/v1/systemone — see the systemone use case." } ] diff --git a/scripts/openrouter.models.json b/scripts/openrouter.models.json index 2b76e96661..92c192e351 100644 --- a/scripts/openrouter.models.json +++ b/scripts/openrouter.models.json @@ -52,6 +52,12 @@ "links": { "details": "/api/v1/models/~anthropic/claude-fable-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], @@ -121,6 +127,12 @@ "links": { "details": "/api/v1/models/~anthropic/claude-haiku-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], @@ -180,6 +192,12 @@ "links": { "details": "/api/v1/models/~anthropic/claude-opus-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], @@ -239,6 +257,12 @@ "links": { "details": "/api/v1/models/~anthropic/claude-sonnet-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], @@ -265,9 +289,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000007", + "prompt": "0.000000032", "completion": "0.0000005", - "input_cache_read": "0.000000008" + "input_cache_read": "0.000000005" }, "top_provider": { "context_length": 1048576, @@ -306,6 +330,12 @@ "links": { "details": "/api/v1/models/~deepseek/deepseek-flash-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -333,9 +363,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000002235", + "prompt": "0.0000001035", "completion": "0.000008", - "input_cache_read": "0.00000022" + "input_cache_read": "0.0000001" }, "top_provider": { "context_length": 1048576, @@ -375,6 +405,12 @@ "links": { "details": "/api/v1/models/~deepseek/deepseek-pro-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["max", "high", "low", "none"], @@ -401,9 +437,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000000475", - "completion": "0.0000001568", - "input_cache_read": "0.000000028" + "prompt": "0.000000059", + "completion": "0.0000003", + "input_cache_read": "0.000000035" }, "top_provider": { "context_length": 1048576, @@ -442,6 +478,12 @@ "links": { "details": "/api/v1/models/~deepseek/deepseek-v4-flash-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -506,6 +548,12 @@ "links": { "details": "/api/v1/models/~google/gemini-flash-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -577,6 +625,12 @@ "links": { "details": "/api/v1/models/~google/gemini-pro-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["high", "medium", "low"], @@ -603,9 +657,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000238", - "completion": "0.000016", - "input_cache_read": "0.000000228" + "prompt": "0.000000152", + "completion": "0.0000101583", + "input_cache_read": "0.00000015" }, "top_provider": { "context_length": 1048576, @@ -618,8 +672,10 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", @@ -649,6 +705,12 @@ "links": { "details": "/api/v1/models/~moonshotai/kimi-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -694,7 +756,7 @@ "top_provider": { "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -717,6 +779,12 @@ "links": { "details": "/api/v1/models/~openai/gpt-astra-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -792,6 +860,12 @@ "links": { "details": "/api/v1/models/~openai/gpt-luna-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -857,6 +931,12 @@ "links": { "details": "/api/v1/models/~openai/gpt-mini-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": false, @@ -902,7 +982,7 @@ "top_provider": { "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -925,6 +1005,12 @@ "links": { "details": "/api/v1/models/~openai/gpt-sol-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -936,8 +1022,8 @@ "id": "~openai/gpt-terra-latest", "canonical_slug": "~openai/gpt-terra-latest", "alias_target": { - "name": "OpenAI: GPT-5.6 Terra", - "slug": "openai/gpt-5.6-terra" + "name": "OpenAI: GPT-6.1 Terra", + "slug": "openai/gpt-6.1-terra" }, "hugging_face_id": null, "name": "OpenAI: GPT Terra Latest", @@ -952,18 +1038,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000012", + "prompt": "0.000001", + "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025", + "input_cache_read": "0.00000005", + "input_cache_write": "0.00000125", "overrides": [ { "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000018", - "input_cache_read": "0.0000004", - "input_cache_write": "0.000005" + "prompt": "0.000002", + "completion": "0.0000075", + "input_cache_read": "0.0000001", + "input_cache_write": "0.0000025" } ] }, @@ -986,20 +1072,19 @@ "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": "2026-02-16", + "knowledge_cutoff": null, "expiration_date": null, "links": { "details": "/api/v1/models/~openai/gpt-terra-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -1050,7 +1135,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/~unbiased/pareto-latest/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "~x-ai/grok-latest", @@ -1074,21 +1165,23 @@ "pricing": { "prompt": "0.000002", "completion": "0.000006", - "web_search": "0.005", + "web_search": "0.01", "input_cache_read": "0.0000005", + "input_cache_write": "0", "overrides": [ { "min_prompt_tokens": 200000, "prompt": "0.000004", "completion": "0.000012", - "input_cache_read": "0.000001" + "input_cache_read": "0.000001", + "input_cache_write": "0" } ] }, "top_provider": { "context_length": 500000, "max_completion_tokens": 450000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -1099,10 +1192,12 @@ "reasoning_effort", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], @@ -1116,6 +1211,12 @@ "links": { "details": "/api/v1/models/~x-ai/grok-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -1143,13 +1244,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000000052", - "completion": "0.0000001985", - "input_cache_read": "0.0000000052" + "prompt": "0.0000000269", + "completion": "0.0000000996", + "input_cache_read": "0.0000000269" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 943718, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -1186,6 +1287,12 @@ "links": { "details": "/api/v1/models/~z-ai/glm-flash-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -1213,9 +1320,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000079", + "prompt": "0.0000000699", "completion": "0.0000014", - "input_cache_read": "0.000000078" + "input_cache_read": "0.0000000689" }, "top_provider": { "context_length": 1048576, @@ -1256,6 +1363,12 @@ "links": { "details": "/api/v1/models/~z-ai/glm-latest/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -1310,6 +1423,12 @@ "links": { "details": "/api/v1/models/aion-labs/aion-2.0-20260223/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -1357,6 +1476,12 @@ "links": { "details": "/api/v1/models/aion-labs/aion-3.0-20260707/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -1404,6 +1529,12 @@ "links": { "details": "/api/v1/models/aion-labs/aion-3.0-mini-20260707/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -1452,6 +1583,12 @@ "links": { "details": "/api/v1/models/aion-labs/aion-3.5-20260923/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["max", "high", "low"], @@ -1502,6 +1639,12 @@ "links": { "details": "/api/v1/models/aion-labs/aion-3.5-mini-20260923/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["max", "high", "low"], @@ -1540,7 +1683,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/aion-labs/aion-rp-llama-3.1-8b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "amazon/nova-2-lite-v1", @@ -1589,10 +1738,16 @@ "links": { "details": "/api/v1/models/amazon/nova-2-lite-v1/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 13.4, + "intelligence_index": null, "coding_index": 23, "agentic_index": null } @@ -1641,14 +1796,12 @@ "links": { "details": "/api/v1/models/amazon/nova-lite-v1/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "amazon/nova-micro-v1", @@ -1690,14 +1843,12 @@ "links": { "details": "/api/v1/models/amazon/nova-micro-v1/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.9, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "amazon/nova-premier-v1", @@ -1744,6 +1895,12 @@ "links": { "details": "/api/v1/models/amazon/nova-premier-v1/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -1751,14 +1908,9 @@ "category": "website", "elo": 835, "win_rate": 26.2, - "rank": 143 + "rank": 145 } - ], - "artificial_analysis": { - "intelligence_index": 9.2, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -1801,21 +1953,22 @@ "links": { "details": "/api/v1/models/amazon/nova-pro-v1/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "website", - "elo": 796, + "elo": 794, "win_rate": 21.4, - "rank": 145 + "rank": 147 } - ], - "artificial_analysis": { - "intelligence_index": 7, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -1867,7 +2020,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/anthracite-org/magnum-v4-72b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "anthropic/claude-fable-5", @@ -1925,14 +2084,20 @@ "links": { "details": "/api/v1/models/anthropic/claude-5-fable-20260609/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1285, + "elo": 1231, "win_rate": 61.9, - "rank": 1 + "rank": 2 }, { "arena": "agents", @@ -1951,9 +2116,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1283, + "elo": 1282, "win_rate": 65.1, - "rank": 2 + "rank": 3 }, { "arena": "agents", @@ -1972,49 +2137,49 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1277, + "elo": 1173, "win_rate": 63.1, - "rank": 1 + "rank": 4 }, { "arena": "agents", "category": "mobileapps", - "elo": 1264, + "elo": 1262, "win_rate": 60.4, - "rank": 5 + "rank": 7 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1293, + "elo": 1250, "win_rate": 61.4, - "rank": 3 + "rank": 4 }, { "arena": "agents", "category": "webapps", - "elo": 1261, + "elo": 1247, "win_rate": 56.3, - "rank": 11 + "rank": 12 }, { "arena": "models", "category": "3d", - "elo": 1319, + "elo": 1316, "win_rate": 61.8, - "rank": 16 + "rank": 17 }, { "arena": "models", "category": "asciiart", - "elo": 1329, - "win_rate": 68.1, - "rank": 2 + "elo": 1324, + "win_rate": 67.9, + "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1310, + "elo": 1308, "win_rate": 57.6, "rank": 13 }, @@ -2023,39 +2188,39 @@ "category": "dataviz", "elo": 1304, "win_rate": 57.5, - "rank": 14 + "rank": 12 }, { "arena": "models", "category": "gamedev", - "elo": 1335, + "elo": 1334, "win_rate": 60.8, "rank": 11 }, { "arena": "models", "category": "svg", - "elo": 1303, + "elo": 1298, "win_rate": 62.6, - "rank": 4 + "rank": 8 }, { "arena": "models", "category": "uicomponent", - "elo": 1319, + "elo": 1313, "win_rate": 58.1, - "rank": 12 + "rank": 14 }, { "arena": "models", "category": "website", - "elo": 1296, + "elo": 1294, "win_rate": 56, - "rank": 17 + "rank": 18 } ], "artificial_analysis": { - "intelligence_index": 49.6, + "intelligence_index": null, "coding_index": 76.5, "agentic_index": 50.7 } @@ -2121,14 +2286,15 @@ "links": { "details": "/api/v1/models/anthropic/claude-5-fable-20260609/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1285, + "elo": 1231, "win_rate": 61.9, - "rank": 1 + "rank": 2 }, { "arena": "agents", @@ -2147,9 +2313,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1283, + "elo": 1282, "win_rate": 65.1, - "rank": 2 + "rank": 3 }, { "arena": "agents", @@ -2168,49 +2334,49 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1277, + "elo": 1173, "win_rate": 63.1, - "rank": 1 + "rank": 4 }, { "arena": "agents", "category": "mobileapps", - "elo": 1264, + "elo": 1262, "win_rate": 60.4, - "rank": 5 + "rank": 7 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1293, + "elo": 1250, "win_rate": 61.4, - "rank": 3 + "rank": 4 }, { "arena": "agents", "category": "webapps", - "elo": 1261, + "elo": 1247, "win_rate": 56.3, - "rank": 11 + "rank": 12 }, { "arena": "models", "category": "3d", - "elo": 1319, + "elo": 1316, "win_rate": 61.8, - "rank": 16 + "rank": 17 }, { "arena": "models", "category": "asciiart", - "elo": 1329, - "win_rate": 68.1, - "rank": 2 + "elo": 1324, + "win_rate": 67.9, + "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1310, + "elo": 1308, "win_rate": 57.6, "rank": 13 }, @@ -2219,39 +2385,39 @@ "category": "dataviz", "elo": 1304, "win_rate": 57.5, - "rank": 14 + "rank": 12 }, { "arena": "models", "category": "gamedev", - "elo": 1335, + "elo": 1334, "win_rate": 60.8, "rank": 11 }, { "arena": "models", "category": "svg", - "elo": 1303, + "elo": 1298, "win_rate": 62.6, - "rank": 4 + "rank": 8 }, { "arena": "models", "category": "uicomponent", - "elo": 1319, + "elo": 1313, "win_rate": 58.1, - "rank": 12 + "rank": 14 }, { "arena": "models", "category": "website", - "elo": 1296, + "elo": 1294, "win_rate": 56, - "rank": 17 + "rank": 18 } ], "artificial_analysis": { - "intelligence_index": 49.6, + "intelligence_index": null, "coding_index": 76.5, "agentic_index": 50.7 } @@ -2311,6 +2477,12 @@ "links": { "details": "/api/v1/models/anthropic/claude-fable-5.1-20260831/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -2327,54 +2499,61 @@ "win_rate": 60.7, "rank": 1 }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1394, + "win_rate": 56.5, + "rank": 1 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1267, + "elo": 1261, "win_rate": 56.3, - "rank": 4 + "rank": 8 }, { "arena": "agents", "category": "python-pptxslides", "elo": 1318, - "win_rate": 62.1, + "win_rate": 60.8, "rank": 1 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1356, + "elo": 1426, "win_rate": 70.4, "rank": 1 }, { "arena": "agents", "category": "webapps", - "elo": 1318, - "win_rate": 56.1, - "rank": 1 + "elo": 1296, + "win_rate": 54.9, + "rank": 3 }, { "arena": "models", "category": "3d", - "elo": 1393, - "win_rate": 67.7, - "rank": 6 + "elo": 1403, + "win_rate": 63.4, + "rank": 5 }, { "arena": "models", "category": "asciiart", - "elo": 1323, + "elo": 1321, "win_rate": 65, - "rank": 3 + "rank": 4 }, { "arena": "models", "category": "codecategories", - "elo": 1336, - "win_rate": 59.3, - "rank": 7 + "elo": 1333, + "win_rate": 57.4, + "rank": 8 }, { "arena": "models", @@ -2386,36 +2565,36 @@ { "arena": "models", "category": "gamedev", - "elo": 1381, - "win_rate": 65.6, - "rank": 4 + "elo": 1373, + "win_rate": 60.2, + "rank": 6 }, { "arena": "models", "category": "svg", - "elo": 1301, + "elo": 1296, "win_rate": 56.4, - "rank": 6 + "rank": 9 }, { "arena": "models", "category": "uicomponent", - "elo": 1339, + "elo": 1333, "win_rate": 59.6, - "rank": 9 + "rank": 11 }, { "arena": "models", "category": "website", - "elo": 1313, - "win_rate": 56.3, - "rank": 9 + "elo": 1308, + "win_rate": 55.1, + "rank": 10 } ], "artificial_analysis": { - "intelligence_index": 53.4, - "coding_index": 81.6, - "agentic_index": 57.9 + "intelligence_index": 50, + "coding_index": 80.7, + "agentic_index": 57.2 } }, "reasoning": { @@ -2472,6 +2651,7 @@ "links": { "details": "/api/v1/models/anthropic/claude-fable-5.1-20260831/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { @@ -2488,54 +2668,61 @@ "win_rate": 60.7, "rank": 1 }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1394, + "win_rate": 56.5, + "rank": 1 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1267, + "elo": 1261, "win_rate": 56.3, - "rank": 4 + "rank": 8 }, { "arena": "agents", "category": "python-pptxslides", "elo": 1318, - "win_rate": 62.1, + "win_rate": 60.8, "rank": 1 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1356, + "elo": 1426, "win_rate": 70.4, "rank": 1 }, { "arena": "agents", "category": "webapps", - "elo": 1318, - "win_rate": 56.1, - "rank": 1 + "elo": 1296, + "win_rate": 54.9, + "rank": 3 }, { "arena": "models", "category": "3d", - "elo": 1393, - "win_rate": 67.7, - "rank": 6 + "elo": 1403, + "win_rate": 63.4, + "rank": 5 }, { "arena": "models", "category": "asciiart", - "elo": 1323, + "elo": 1321, "win_rate": 65, - "rank": 3 + "rank": 4 }, { "arena": "models", "category": "codecategories", - "elo": 1336, - "win_rate": 59.3, - "rank": 7 + "elo": 1333, + "win_rate": 57.4, + "rank": 8 }, { "arena": "models", @@ -2547,36 +2734,36 @@ { "arena": "models", "category": "gamedev", - "elo": 1381, - "win_rate": 65.6, - "rank": 4 + "elo": 1373, + "win_rate": 60.2, + "rank": 6 }, { "arena": "models", "category": "svg", - "elo": 1301, + "elo": 1296, "win_rate": 56.4, - "rank": 6 + "rank": 9 }, { "arena": "models", "category": "uicomponent", - "elo": 1339, + "elo": 1333, "win_rate": 59.6, - "rank": 9 + "rank": 11 }, { "arena": "models", "category": "website", - "elo": 1313, - "win_rate": 56.3, - "rank": 9 + "elo": 1308, + "win_rate": 55.1, + "rank": 10 } ], "artificial_analysis": { - "intelligence_index": 53.4, - "coding_index": 81.6, - "agentic_index": 57.9 + "intelligence_index": 50, + "coding_index": 80.7, + "agentic_index": 57.2 } }, "reasoning": { @@ -2642,34 +2829,40 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1072, + "elo": 1069, "win_rate": 41.1, - "rank": 100 + "rank": 103 }, { "arena": "models", "category": "asciiart", - "elo": 1140, + "elo": 1137, "win_rate": 49.3, - "rank": 49 + "rank": 53 }, { "arena": "models", "category": "codecategories", - "elo": 1115, + "elo": 1113, "win_rate": 44.9, - "rank": 98 + "rank": 102 }, { "arena": "models", "category": "dataviz", - "elo": 1124, - "win_rate": 45.6, + "elo": 1125, + "win_rate": 45.7, "rank": 94 }, { @@ -2677,32 +2870,32 @@ "category": "gamedev", "elo": 1097, "win_rate": 44.7, - "rank": 97 + "rank": 98 }, { "arena": "models", "category": "svg", - "elo": 1026, + "elo": 1022, "win_rate": 39.1, - "rank": 80 + "rank": 86 }, { "arena": "models", "category": "uicomponent", - "elo": 1100, + "elo": 1095, "win_rate": 42.6, - "rank": 95 + "rank": 98 }, { "arena": "models", "category": "website", "elo": 1122, "win_rate": 45.1, - "rank": 101 + "rank": 103 } ], "artificial_analysis": { - "intelligence_index": 16.9, + "intelligence_index": null, "coding_index": 43.9, "agentic_index": 8 } @@ -2767,34 +2960,35 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1072, + "elo": 1069, "win_rate": 41.1, - "rank": 100 + "rank": 103 }, { "arena": "models", "category": "asciiart", - "elo": 1140, + "elo": 1137, "win_rate": 49.3, - "rank": 49 + "rank": 53 }, { "arena": "models", "category": "codecategories", - "elo": 1115, + "elo": 1113, "win_rate": 44.9, - "rank": 98 + "rank": 102 }, { "arena": "models", "category": "dataviz", - "elo": 1124, - "win_rate": 45.6, + "elo": 1125, + "win_rate": 45.7, "rank": 94 }, { @@ -2802,32 +2996,32 @@ "category": "gamedev", "elo": 1097, "win_rate": 44.7, - "rank": 97 + "rank": 98 }, { "arena": "models", "category": "svg", - "elo": 1026, + "elo": 1022, "win_rate": 39.1, - "rank": 80 + "rank": 86 }, { "arena": "models", "category": "uicomponent", - "elo": 1100, + "elo": 1095, "win_rate": 42.6, - "rank": 95 + "rank": 98 }, { "arena": "models", "category": "website", "elo": 1122, "win_rate": 45.1, - "rank": 101 + "rank": 103 } ], "artificial_analysis": { - "intelligence_index": 16.9, + "intelligence_index": null, "coding_index": 43.9, "agentic_index": 8 } @@ -2895,53 +3089,73 @@ "links": { "details": "/api/v1/models/anthropic/claude-haiku-5.5-20261007/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1343, - "win_rate": 58.3, - "rank": 10 + "elo": 1337, + "win_rate": 57.2, + "rank": 11 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1210, + "win_rate": 51, + "rank": 22 }, { "arena": "models", "category": "codecategories", - "elo": 1278, - "win_rate": 50.1, - "rank": 23 + "elo": 1281, + "win_rate": 50.5, + "rank": 24 }, { "arena": "models", "category": "dataviz", - "elo": 1295, - "win_rate": 54.8, - "rank": 15 + "elo": 1289, + "win_rate": 51.8, + "rank": 16 }, { "arena": "models", "category": "gamedev", - "elo": 1315, - "win_rate": 53.8, - "rank": 13 + "elo": 1319, + "win_rate": 53.3, + "rank": 12 + }, + { + "arena": "models", + "category": "svg", + "elo": 1202, + "win_rate": 44.1, + "rank": 28 }, { "arena": "models", "category": "uicomponent", - "elo": 1292, - "win_rate": 52.8, - "rank": 22 + "elo": 1276, + "win_rate": 50.6, + "rank": 27 }, { "arena": "models", "category": "website", - "elo": 1263, - "win_rate": 48.5, - "rank": 36 + "elo": 1261, + "win_rate": 48.7, + "rank": 37 } ], "artificial_analysis": { - "intelligence_index": 43.4, + "intelligence_index": 36.5, "coding_index": null, "agentic_index": null } @@ -3010,53 +3224,68 @@ "links": { "details": "/api/v1/models/anthropic/claude-haiku-5.5-20261007/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1343, - "win_rate": 58.3, - "rank": 10 + "elo": 1337, + "win_rate": 57.2, + "rank": 11 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1210, + "win_rate": 51, + "rank": 22 }, { "arena": "models", "category": "codecategories", - "elo": 1278, - "win_rate": 50.1, - "rank": 23 + "elo": 1281, + "win_rate": 50.5, + "rank": 24 }, { "arena": "models", "category": "dataviz", - "elo": 1295, - "win_rate": 54.8, - "rank": 15 + "elo": 1289, + "win_rate": 51.8, + "rank": 16 }, { "arena": "models", "category": "gamedev", - "elo": 1315, - "win_rate": 53.8, - "rank": 13 + "elo": 1319, + "win_rate": 53.3, + "rank": 12 + }, + { + "arena": "models", + "category": "svg", + "elo": 1202, + "win_rate": 44.1, + "rank": 28 }, { "arena": "models", "category": "uicomponent", - "elo": 1292, - "win_rate": 52.8, - "rank": 22 + "elo": 1276, + "win_rate": 50.6, + "rank": 27 }, { "arena": "models", "category": "website", - "elo": 1263, - "win_rate": 48.5, - "rank": 36 + "elo": 1261, + "win_rate": 48.7, + "rank": 37 } ], "artificial_analysis": { - "intelligence_index": 43.4, + "intelligence_index": 36.5, "coding_index": null, "agentic_index": null } @@ -3121,35 +3350,41 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1153, + "elo": 1150, "win_rate": 51.9, - "rank": 67 + "rank": 69 }, { "arena": "models", "category": "asciiart", - "elo": 1167, + "elo": 1164, "win_rate": 51.5, - "rank": 31 + "rank": 34 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1169, "win_rate": 55.8, - "rank": 71 + "rank": 75 }, { "arena": "models", "category": "dataviz", "elo": 1166, "win_rate": 56.4, - "rank": 74 + "rank": 75 }, { "arena": "models", @@ -3161,30 +3396,25 @@ { "arena": "models", "category": "svg", - "elo": 1153, + "elo": 1149, "win_rate": 60.8, - "rank": 42 + "rank": 48 }, { "arena": "models", "category": "uicomponent", - "elo": 1165, + "elo": 1159, "win_rate": 57.8, - "rank": 72 + "rank": 75 }, { "arena": "models", "category": "website", - "elo": 1177, + "elo": 1175, "win_rate": 55.3, - "rank": 77 + "rank": 79 } - ], - "artificial_analysis": { - "intelligence_index": 22.8, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -3244,35 +3474,36 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1153, + "elo": 1150, "win_rate": 51.9, - "rank": 67 + "rank": 69 }, { "arena": "models", "category": "asciiart", - "elo": 1167, + "elo": 1164, "win_rate": 51.5, - "rank": 31 + "rank": 34 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1169, "win_rate": 55.8, - "rank": 71 + "rank": 75 }, { "arena": "models", "category": "dataviz", "elo": 1166, "win_rate": 56.4, - "rank": 74 + "rank": 75 }, { "arena": "models", @@ -3284,30 +3515,25 @@ { "arena": "models", "category": "svg", - "elo": 1153, + "elo": 1149, "win_rate": 60.8, - "rank": 42 + "rank": 48 }, { "arena": "models", "category": "uicomponent", - "elo": 1165, + "elo": 1159, "win_rate": 57.8, - "rank": 72 + "rank": 75 }, { "arena": "models", "category": "website", - "elo": 1177, + "elo": 1175, "win_rate": 55.3, - "rank": 77 + "rank": 79 } - ], - "artificial_analysis": { - "intelligence_index": 22.8, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -3363,68 +3589,74 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1214, + "elo": 1211, "win_rate": 58.5, - "rank": 44 + "rank": 46 }, { "arena": "models", "category": "asciiart", - "elo": 1190, + "elo": 1187, "win_rate": 54.8, - "rank": 28 + "rank": 32 }, { "arena": "models", "category": "codecategories", - "elo": 1242, + "elo": 1240, "win_rate": 59.5, - "rank": 44 + "rank": 46 }, { "arena": "models", "category": "dataviz", "elo": 1243, "win_rate": 58.5, - "rank": 37 + "rank": 38 }, { "arena": "models", "category": "gamedev", "elo": 1229, "win_rate": 59.3, - "rank": 42 + "rank": 43 }, { "arena": "models", "category": "svg", - "elo": 1181, + "elo": 1177, "win_rate": 58.7, - "rank": 33 + "rank": 40 }, { "arena": "models", "category": "uicomponent", - "elo": 1238, + "elo": 1233, "win_rate": 58.1, - "rank": 45 + "rank": 46 }, { "arena": "models", "category": "website", - "elo": 1247, + "elo": 1245, "win_rate": 59.7, - "rank": 46 + "rank": 47 }, { "arena": "agents", "category": "androidnative", - "elo": 1175, + "elo": 1172, "win_rate": 65.5, "rank": 20 }, @@ -3438,23 +3670,18 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1189, + "elo": 1187, "win_rate": 60.7, - "rank": 21 + "rank": 23 }, { "arena": "agents", "category": "webapps", - "elo": 1159, + "elo": 1146, "win_rate": 55.1, - "rank": 30 + "rank": 31 } - ], - "artificial_analysis": { - "intelligence_index": 29.1, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -3508,68 +3735,69 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1214, + "elo": 1211, "win_rate": 58.5, - "rank": 44 + "rank": 46 }, { "arena": "models", "category": "asciiart", - "elo": 1190, + "elo": 1187, "win_rate": 54.8, - "rank": 28 + "rank": 32 }, { "arena": "models", "category": "codecategories", - "elo": 1242, + "elo": 1240, "win_rate": 59.5, - "rank": 44 + "rank": 46 }, { "arena": "models", "category": "dataviz", "elo": 1243, "win_rate": 58.5, - "rank": 37 + "rank": 38 }, { "arena": "models", "category": "gamedev", "elo": 1229, "win_rate": 59.3, - "rank": 42 + "rank": 43 }, { "arena": "models", "category": "svg", - "elo": 1181, + "elo": 1177, "win_rate": 58.7, - "rank": 33 + "rank": 40 }, { "arena": "models", "category": "uicomponent", - "elo": 1238, + "elo": 1233, "win_rate": 58.1, - "rank": 45 + "rank": 46 }, { "arena": "models", "category": "website", - "elo": 1247, + "elo": 1245, "win_rate": 59.7, - "rank": 46 + "rank": 47 }, { "arena": "agents", "category": "androidnative", - "elo": 1175, + "elo": 1172, "win_rate": 65.5, "rank": 20 }, @@ -3583,23 +3811,18 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1189, + "elo": 1187, "win_rate": 60.7, - "rank": 21 + "rank": 23 }, { "arena": "agents", "category": "webapps", - "elo": 1159, + "elo": 1146, "win_rate": 55.1, - "rank": 30 + "rank": 31 } - ], - "artificial_analysis": { - "intelligence_index": 29.1, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -3657,26 +3880,46 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1212, - "win_rate": 48.2, - "rank": 8 + "elo": 1143, + "win_rate": 45.3, + "rank": 11 }, { "arena": "agents", "category": "androidnative", - "elo": 1196, - "win_rate": 63, - "rank": 13 + "elo": 1190, + "win_rate": 61.8, + "rank": 15 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1008, + "win_rate": 37.2, + "rank": 20 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1155, + "win_rate": 46.5, + "rank": 8 }, { "arena": "agents", "category": "fullstack", - "elo": 1220, + "elo": 1222, "win_rate": 59.9, "rank": 13 }, @@ -3684,36 +3927,50 @@ "arena": "agents", "category": "mobileapps", "elo": 1207, - "win_rate": 58.5, - "rank": 17 + "win_rate": 57.9, + "rank": 19 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1266, + "win_rate": 59.3, + "rank": 6 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1234, + "win_rate": 65.4, + "rank": 9 }, { "arena": "agents", "category": "webapps", - "elo": 1206, - "win_rate": 56.3, - "rank": 22 + "elo": 1193, + "win_rate": 56.1, + "rank": 23 }, { "arena": "models", "category": "3d", - "elo": 1274, + "elo": 1271, "win_rate": 62.5, - "rank": 23 + "rank": 24 }, { "arena": "models", "category": "asciiart", - "elo": 1255, + "elo": 1252, "win_rate": 61.9, - "rank": 15 + "rank": 17 }, { "arena": "models", "category": "codecategories", - "elo": 1289, + "elo": 1287, "win_rate": 61.2, - "rank": 20 + "rank": 22 }, { "arena": "models", @@ -3725,37 +3982,32 @@ { "arena": "models", "category": "gamedev", - "elo": 1278, + "elo": 1276, "win_rate": 61, - "rank": 23 + "rank": 22 }, { "arena": "models", "category": "svg", - "elo": 1228, + "elo": 1224, "win_rate": 60.9, - "rank": 18 + "rank": 22 }, { "arena": "models", "category": "uicomponent", - "elo": 1284, + "elo": 1278, "win_rate": 59.8, - "rank": 25 + "rank": 26 }, { "arena": "models", "category": "website", - "elo": 1291, - "win_rate": 61.2, + "elo": 1290, + "win_rate": 61.1, "rank": 19 } - ], - "artificial_analysis": { - "intelligence_index": 31.9, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -3815,26 +4067,41 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1212, - "win_rate": 48.2, - "rank": 8 + "elo": 1143, + "win_rate": 45.3, + "rank": 11 }, { "arena": "agents", "category": "androidnative", - "elo": 1196, - "win_rate": 63, - "rank": 13 + "elo": 1190, + "win_rate": 61.8, + "rank": 15 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1008, + "win_rate": 37.2, + "rank": 20 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1155, + "win_rate": 46.5, + "rank": 8 }, { "arena": "agents", "category": "fullstack", - "elo": 1220, + "elo": 1222, "win_rate": 59.9, "rank": 13 }, @@ -3842,36 +4109,50 @@ "arena": "agents", "category": "mobileapps", "elo": 1207, - "win_rate": 58.5, - "rank": 17 + "win_rate": 57.9, + "rank": 19 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1266, + "win_rate": 59.3, + "rank": 6 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1234, + "win_rate": 65.4, + "rank": 9 }, { "arena": "agents", "category": "webapps", - "elo": 1206, - "win_rate": 56.3, - "rank": 22 + "elo": 1193, + "win_rate": 56.1, + "rank": 23 }, { "arena": "models", "category": "3d", - "elo": 1274, + "elo": 1271, "win_rate": 62.5, - "rank": 23 + "rank": 24 }, { "arena": "models", "category": "asciiart", - "elo": 1255, + "elo": 1252, "win_rate": 61.9, - "rank": 15 + "rank": 17 }, { "arena": "models", "category": "codecategories", - "elo": 1289, + "elo": 1287, "win_rate": 61.2, - "rank": 20 + "rank": 22 }, { "arena": "models", @@ -3883,37 +4164,32 @@ { "arena": "models", "category": "gamedev", - "elo": 1278, + "elo": 1276, "win_rate": 61, - "rank": 23 + "rank": 22 }, { "arena": "models", "category": "svg", - "elo": 1228, + "elo": 1224, "win_rate": 60.9, - "rank": 18 + "rank": 22 }, { "arena": "models", "category": "uicomponent", - "elo": 1284, + "elo": 1278, "win_rate": 59.8, - "rank": 25 + "rank": 26 }, { "arena": "models", "category": "website", - "elo": 1291, - "win_rate": 61.2, + "elo": 1290, + "win_rate": 61.1, "rank": 19 } - ], - "artificial_analysis": { - "intelligence_index": 31.9, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -3972,10 +4248,16 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 40.7, + "intelligence_index": null, "coding_index": 73.6, "agentic_index": 38.6 } @@ -4035,10 +4317,11 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 40.7, + "intelligence_index": null, "coding_index": 73.6, "agentic_index": 38.6 } @@ -4076,7 +4359,7 @@ "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": true + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -4099,14 +4382,20 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1239, - "win_rate": 55.7, - "rank": 4 + "elo": 1182, + "win_rate": 55.2, + "rank": 5 }, { "arena": "agents", @@ -4139,10 +4428,24 @@ { "arena": "agents", "category": "androidnative", - "elo": 1232, - "win_rate": 56.2, + "elo": 1233, + "win_rate": 56.3, "rank": 8 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1096, + "win_rate": 48.2, + "rank": 14 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1193, + "win_rate": 52.6, + "rank": 5 + }, { "arena": "agents", "category": "fullstack", @@ -4160,16 +4463,23 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1221, + "elo": 1117, "win_rate": 58, - "rank": 4 + "rank": 8 }, { "arena": "agents", "category": "mobileapps", - "elo": 1222, - "win_rate": 55, - "rank": 11 + "elo": 1216, + "win_rate": 54, + "rank": 15 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1155, + "win_rate": 47, + "rank": 18 }, { "arena": "agents", @@ -4188,63 +4498,63 @@ { "arena": "agents", "category": "spreadsheet", - "elo": 1296, - "win_rate": 75, - "rank": 4 + "elo": 1216, + "win_rate": 64.5, + "rank": 10 }, { "arena": "agents", "category": "webapps", - "elo": 1233, - "win_rate": 51.4, - "rank": 15 + "elo": 1219, + "win_rate": 51.3, + "rank": 16 }, { "arena": "models", "category": "3d", - "elo": 1223, - "win_rate": 51.6, - "rank": 42 + "elo": 1219, + "win_rate": 51.2, + "rank": 44 }, { "arena": "models", "category": "asciiart", - "elo": 1277, - "win_rate": 62.3, - "rank": 8 + "elo": 1274, + "win_rate": 62.1, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1255, - "win_rate": 52.5, - "rank": 39 + "elo": 1254, + "win_rate": 52.3, + "rank": 41 }, { "arena": "models", "category": "dataviz", - "elo": 1240, + "elo": 1241, "win_rate": 52.8, - "rank": 38 + "rank": 40 }, { "arena": "models", "category": "gamedev", - "elo": 1264, - "win_rate": 52.7, - "rank": 30 + "elo": 1263, + "win_rate": 52.4, + "rank": 31 }, { "arena": "models", "category": "svg", - "elo": 1195, - "win_rate": 51.4, - "rank": 27 + "elo": 1191, + "win_rate": 51.1, + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1257, + "elo": 1253, "win_rate": 53, "rank": 41 }, @@ -4252,12 +4562,12 @@ "arena": "models", "category": "website", "elo": 1258, - "win_rate": 52.9, - "rank": 38 + "win_rate": 52.7, + "rank": 39 } ], "artificial_analysis": { - "intelligence_index": 41.8, + "intelligence_index": null, "coding_index": 74.3, "agentic_index": 41.9 } @@ -4317,14 +4627,15 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1239, - "win_rate": 55.7, - "rank": 4 + "elo": 1182, + "win_rate": 55.2, + "rank": 5 }, { "arena": "agents", @@ -4357,10 +4668,24 @@ { "arena": "agents", "category": "androidnative", - "elo": 1232, - "win_rate": 56.2, + "elo": 1233, + "win_rate": 56.3, "rank": 8 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1096, + "win_rate": 48.2, + "rank": 14 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1193, + "win_rate": 52.6, + "rank": 5 + }, { "arena": "agents", "category": "fullstack", @@ -4378,16 +4703,23 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1221, + "elo": 1117, "win_rate": 58, - "rank": 4 + "rank": 8 }, { "arena": "agents", "category": "mobileapps", - "elo": 1222, - "win_rate": 55, - "rank": 11 + "elo": 1216, + "win_rate": 54, + "rank": 15 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1155, + "win_rate": 47, + "rank": 18 }, { "arena": "agents", @@ -4406,63 +4738,63 @@ { "arena": "agents", "category": "spreadsheet", - "elo": 1296, - "win_rate": 75, - "rank": 4 + "elo": 1216, + "win_rate": 64.5, + "rank": 10 }, { "arena": "agents", "category": "webapps", - "elo": 1233, - "win_rate": 51.4, - "rank": 15 + "elo": 1219, + "win_rate": 51.3, + "rank": 16 }, { "arena": "models", "category": "3d", - "elo": 1223, - "win_rate": 51.6, - "rank": 42 + "elo": 1219, + "win_rate": 51.2, + "rank": 44 }, { "arena": "models", "category": "asciiart", - "elo": 1277, - "win_rate": 62.3, - "rank": 8 + "elo": 1274, + "win_rate": 62.1, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1255, - "win_rate": 52.5, - "rank": 39 + "elo": 1254, + "win_rate": 52.3, + "rank": 41 }, { "arena": "models", "category": "dataviz", - "elo": 1240, + "elo": 1241, "win_rate": 52.8, - "rank": 38 + "rank": 40 }, { "arena": "models", "category": "gamedev", - "elo": 1264, - "win_rate": 52.7, - "rank": 30 + "elo": 1263, + "win_rate": 52.4, + "rank": 31 }, { "arena": "models", "category": "svg", - "elo": 1195, - "win_rate": 51.4, - "rank": 27 + "elo": 1191, + "win_rate": 51.1, + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1257, + "elo": 1253, "win_rate": 53, "rank": 41 }, @@ -4470,12 +4802,12 @@ "arena": "models", "category": "website", "elo": 1258, - "win_rate": 52.9, - "rank": 38 + "win_rate": 52.7, + "rank": 39 } ], "artificial_analysis": { - "intelligence_index": 41.8, + "intelligence_index": null, "coding_index": 74.3, "agentic_index": 41.9 } @@ -4536,21 +4868,41 @@ "links": { "details": "/api/v1/models/anthropic/claude-opus-5-20260723/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1261, - "win_rate": 53.9, - "rank": 2 + "elo": 1204, + "win_rate": 53.1, + "rank": 3 }, { "arena": "agents", "category": "androidnative", - "elo": 1257, - "win_rate": 56.1, - "rank": 4 + "elo": 1253, + "win_rate": 55.9, + "rank": 6 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1201, + "win_rate": 63.1, + "rank": 5 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1264, + "win_rate": 64.3, + "rank": 2 }, { "arena": "agents", @@ -4563,7 +4915,7 @@ "arena": "agents", "category": "godotgamedev", "elo": 1279, - "win_rate": 54.2, + "win_rate": 54.4, "rank": 3 }, { @@ -4573,79 +4925,93 @@ "win_rate": 67.1, "rank": 1 }, + { + "arena": "agents", + "category": "pdf", + "elo": 1232, + "win_rate": 56.6, + "rank": 10 + }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1261, - "win_rate": 54.2, - "rank": 5 + "elo": 1218, + "win_rate": 54.1, + "rank": 7 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1199, + "win_rate": 51.9, + "rank": 12 }, { "arena": "agents", "category": "webapps", - "elo": 1266, - "win_rate": 54.3, - "rank": 10 + "elo": 1255, + "win_rate": 54.6, + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1335, - "win_rate": 59.7, - "rank": 13 + "elo": 1333, + "win_rate": 59.8, + "rank": 14 }, { "arena": "models", "category": "asciiart", - "elo": 1352, - "win_rate": 67.4, + "elo": 1358, + "win_rate": 68.6, "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1324, - "win_rate": 57.3, + "elo": 1323, + "win_rate": 57.4, "rank": 10 }, { "arena": "models", "category": "dataviz", - "elo": 1329, - "win_rate": 58.2, - "rank": 10 + "elo": 1331, + "win_rate": 58.5, + "rank": 9 }, { "arena": "models", "category": "gamedev", - "elo": 1339, - "win_rate": 58.5, + "elo": 1340, + "win_rate": 58.6, "rank": 10 }, { "arena": "models", "category": "svg", - "elo": 1311, - "win_rate": 58.2, - "rank": 3 + "elo": 1308, + "win_rate": 58.4, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1348, - "win_rate": 60.7, - "rank": 5 + "elo": 1346, + "win_rate": 60.8, + "rank": 6 }, { "arena": "models", "category": "website", - "elo": 1309, + "elo": 1308, "win_rate": 55.9, - "rank": 12 + "rank": 11 } ], "artificial_analysis": { - "intelligence_index": 50.8, + "intelligence_index": null, "coding_index": 78, "agentic_index": 56.5 } @@ -4705,21 +5071,36 @@ "links": { "details": "/api/v1/models/anthropic/claude-opus-5-20260723/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1261, - "win_rate": 53.9, - "rank": 2 + "elo": 1204, + "win_rate": 53.1, + "rank": 3 }, { "arena": "agents", "category": "androidnative", - "elo": 1257, - "win_rate": 56.1, - "rank": 4 + "elo": 1253, + "win_rate": 55.9, + "rank": 6 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1201, + "win_rate": 63.1, + "rank": 5 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1264, + "win_rate": 64.3, + "rank": 2 }, { "arena": "agents", @@ -4732,7 +5113,7 @@ "arena": "agents", "category": "godotgamedev", "elo": 1279, - "win_rate": 54.2, + "win_rate": 54.4, "rank": 3 }, { @@ -4742,79 +5123,93 @@ "win_rate": 67.1, "rank": 1 }, + { + "arena": "agents", + "category": "pdf", + "elo": 1232, + "win_rate": 56.6, + "rank": 10 + }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1261, - "win_rate": 54.2, - "rank": 5 + "elo": 1218, + "win_rate": 54.1, + "rank": 7 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1199, + "win_rate": 51.9, + "rank": 12 }, { "arena": "agents", "category": "webapps", - "elo": 1266, - "win_rate": 54.3, - "rank": 10 + "elo": 1255, + "win_rate": 54.6, + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1335, - "win_rate": 59.7, - "rank": 13 + "elo": 1333, + "win_rate": 59.8, + "rank": 14 }, { "arena": "models", "category": "asciiart", - "elo": 1352, - "win_rate": 67.4, + "elo": 1358, + "win_rate": 68.6, "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1324, - "win_rate": 57.3, + "elo": 1323, + "win_rate": 57.4, "rank": 10 }, { "arena": "models", "category": "dataviz", - "elo": 1329, - "win_rate": 58.2, - "rank": 10 + "elo": 1331, + "win_rate": 58.5, + "rank": 9 }, { "arena": "models", "category": "gamedev", - "elo": 1339, - "win_rate": 58.5, + "elo": 1340, + "win_rate": 58.6, "rank": 10 }, { "arena": "models", "category": "svg", - "elo": 1311, - "win_rate": 58.2, - "rank": 3 + "elo": 1308, + "win_rate": 58.4, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1348, - "win_rate": 60.7, - "rank": 5 + "elo": 1346, + "win_rate": 60.8, + "rank": 6 }, { "arena": "models", "category": "website", - "elo": 1309, + "elo": 1308, "win_rate": 55.9, - "rank": 12 + "rank": 11 } ], "artificial_analysis": { - "intelligence_index": 50.8, + "intelligence_index": null, "coding_index": 78, "agentic_index": 56.5 } @@ -4875,81 +5270,115 @@ "links": { "details": "/api/v1/models/anthropic/claude-opus-5.5-20260921/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1274, + "win_rate": 64.5, + "rank": 3 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1348, + "win_rate": 73.2, + "rank": 1 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1308, - "win_rate": 62, + "elo": 1306, + "win_rate": 62.5, "rank": 2 }, + { + "arena": "agents", + "category": "pdf", + "elo": 1320, + "win_rate": 67.9, + "rank": 1 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1345, - "win_rate": 69.8, + "elo": 1400, + "win_rate": 68.7, "rank": 2 }, { "arena": "agents", "category": "webapps", - "elo": 1317, - "win_rate": 60.7, + "elo": 1309, + "win_rate": 60.9, "rank": 2 }, { "arena": "models", "category": "3d", - "elo": 1477, - "win_rate": 71.9, + "elo": 1471, + "win_rate": 64.7, "rank": 1 }, + { + "arena": "models", + "category": "asciiart", + "elo": 1354, + "win_rate": 64.2, + "rank": 2 + }, { "arena": "models", "category": "codecategories", - "elo": 1390, - "win_rate": 63.8, - "rank": 1 + "elo": 1384, + "win_rate": 60.6, + "rank": 2 }, { "arena": "models", "category": "dataviz", - "elo": 1397, - "win_rate": 64.7, + "elo": 1393, + "win_rate": 64.3, "rank": 1 }, { "arena": "models", "category": "gamedev", - "elo": 1458, - "win_rate": 71.8, - "rank": 2 + "elo": 1434, + "win_rate": 64.1, + "rank": 1 }, { "arena": "models", "category": "svg", - "elo": 1331, - "win_rate": 52, - "rank": 1 + "elo": 1323, + "win_rate": 52.7, + "rank": 3 }, { "arena": "models", "category": "uicomponent", - "elo": 1388, - "win_rate": 64.3, - "rank": 1 + "elo": 1375, + "win_rate": 62.9, + "rank": 4 }, { "arena": "models", "category": "website", - "elo": 1336, - "win_rate": 57.6, - "rank": 3 + "elo": 1325, + "win_rate": 55.2, + "rank": 5 } ], "artificial_analysis": { - "intelligence_index": 57.6, + "intelligence_index": 59.1, "coding_index": null, "agentic_index": null } @@ -5008,81 +5437,110 @@ "links": { "details": "/api/v1/models/anthropic/claude-opus-5.5-20260921/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1274, + "win_rate": 64.5, + "rank": 3 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1348, + "win_rate": 73.2, + "rank": 1 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1308, - "win_rate": 62, + "elo": 1306, + "win_rate": 62.5, "rank": 2 }, + { + "arena": "agents", + "category": "pdf", + "elo": 1320, + "win_rate": 67.9, + "rank": 1 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1345, - "win_rate": 69.8, + "elo": 1400, + "win_rate": 68.7, "rank": 2 }, { "arena": "agents", "category": "webapps", - "elo": 1317, - "win_rate": 60.7, + "elo": 1309, + "win_rate": 60.9, "rank": 2 }, { "arena": "models", "category": "3d", - "elo": 1477, - "win_rate": 71.9, + "elo": 1471, + "win_rate": 64.7, "rank": 1 }, + { + "arena": "models", + "category": "asciiart", + "elo": 1354, + "win_rate": 64.2, + "rank": 2 + }, { "arena": "models", "category": "codecategories", - "elo": 1390, - "win_rate": 63.8, - "rank": 1 + "elo": 1384, + "win_rate": 60.6, + "rank": 2 }, { "arena": "models", "category": "dataviz", - "elo": 1397, - "win_rate": 64.7, + "elo": 1393, + "win_rate": 64.3, "rank": 1 }, { "arena": "models", "category": "gamedev", - "elo": 1458, - "win_rate": 71.8, - "rank": 2 + "elo": 1434, + "win_rate": 64.1, + "rank": 1 }, { "arena": "models", "category": "svg", - "elo": 1331, - "win_rate": 52, - "rank": 1 + "elo": 1323, + "win_rate": 52.7, + "rank": 3 }, { "arena": "models", "category": "uicomponent", - "elo": 1388, - "win_rate": 64.3, - "rank": 1 + "elo": 1375, + "win_rate": 62.9, + "rank": 4 }, { "arena": "models", "category": "website", - "elo": 1336, - "win_rate": 57.6, - "rank": 3 + "elo": 1325, + "win_rate": 55.2, + "rank": 5 } ], "artificial_analysis": { - "intelligence_index": 57.6, + "intelligence_index": 59.1, "coding_index": null, "agentic_index": null } @@ -5160,63 +5618,69 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1158, + "elo": 1155, "win_rate": 51, - "rank": 66 + "rank": 67 }, { "arena": "models", "category": "asciiart", - "elo": 1205, + "elo": 1202, "win_rate": 56.1, - "rank": 23 + "rank": 27 }, { "arena": "models", "category": "codecategories", - "elo": 1183, + "elo": 1181, "win_rate": 51.5, - "rank": 64 + "rank": 67 }, { "arena": "models", "category": "dataviz", "elo": 1167, "win_rate": 47.4, - "rank": 73 + "rank": 74 }, { "arena": "models", "category": "gamedev", "elo": 1166, "win_rate": 51.1, - "rank": 69 + "rank": 70 }, { "arena": "models", "category": "svg", - "elo": 1115, + "elo": 1111, "win_rate": 52.2, - "rank": 56 + "rank": 62 }, { "arena": "models", "category": "uicomponent", - "elo": 1173, - "win_rate": 49.5, - "rank": 68 + "elo": 1167, + "win_rate": 49.4, + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1190, + "elo": 1188, "win_rate": 51.8, - "rank": 70 + "rank": 71 }, { "arena": "agents", @@ -5230,18 +5694,18 @@ "category": "mobileapps", "elo": 1137, "win_rate": 52.9, - "rank": 33 + "rank": 35 }, { "arena": "agents", "category": "webapps", - "elo": 1059, + "elo": 1046, "win_rate": 43.2, - "rank": 40 + "rank": 41 } ], "artificial_analysis": { - "intelligence_index": 20.7, + "intelligence_index": null, "coding_index": 52.1, "agentic_index": 15.8 } @@ -5316,63 +5780,64 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1158, + "elo": 1155, "win_rate": 51, - "rank": 66 + "rank": 67 }, { "arena": "models", "category": "asciiart", - "elo": 1205, + "elo": 1202, "win_rate": 56.1, - "rank": 23 + "rank": 27 }, { "arena": "models", "category": "codecategories", - "elo": 1183, + "elo": 1181, "win_rate": 51.5, - "rank": 64 + "rank": 67 }, { "arena": "models", "category": "dataviz", "elo": 1167, "win_rate": 47.4, - "rank": 73 + "rank": 74 }, { "arena": "models", "category": "gamedev", "elo": 1166, "win_rate": 51.1, - "rank": 69 + "rank": 70 }, { "arena": "models", "category": "svg", - "elo": 1115, + "elo": 1111, "win_rate": 52.2, - "rank": 56 + "rank": 62 }, { "arena": "models", "category": "uicomponent", - "elo": 1173, - "win_rate": 49.5, - "rank": 68 + "elo": 1167, + "win_rate": 49.4, + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1190, + "elo": 1188, "win_rate": 51.8, - "rank": 70 + "rank": 71 }, { "arena": "agents", @@ -5386,18 +5851,18 @@ "category": "mobileapps", "elo": 1137, "win_rate": 52.9, - "rank": 33 + "rank": 35 }, { "arena": "agents", "category": "webapps", - "elo": 1059, + "elo": 1046, "win_rate": 43.2, - "rank": 40 + "rank": 41 } ], "artificial_analysis": { - "intelligence_index": 20.7, + "intelligence_index": null, "coding_index": 52.1, "agentic_index": 15.8 } @@ -5458,19 +5923,25 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1177, + "elo": 1123, "win_rate": 52.2, - "rank": 16 + "rank": 17 }, { "arena": "agents", "category": "androidnative", - "elo": 1196, + "elo": 1193, "win_rate": 62.1, "rank": 14 }, @@ -5491,37 +5962,37 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1212, + "elo": 1210, "win_rate": 63.6, - "rank": 15 + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1190, + "elo": 1177, "win_rate": 57, - "rank": 27 + "rank": 28 }, { "arena": "models", "category": "3d", - "elo": 1234, - "win_rate": 57.6, - "rank": 39 + "elo": 1231, + "win_rate": 57.5, + "rank": 41 }, { "arena": "models", "category": "asciiart", - "elo": 1235, + "elo": 1233, "win_rate": 60.1, - "rank": 19 + "rank": 21 }, { "arena": "models", "category": "codecategories", - "elo": 1276, + "elo": 1274, "win_rate": 59.4, - "rank": 24 + "rank": 26 }, { "arena": "models", @@ -5535,32 +6006,32 @@ "category": "gamedev", "elo": 1259, "win_rate": 58.8, - "rank": 36 + "rank": 37 }, { "arena": "models", "category": "svg", - "elo": 1197, + "elo": 1193, "win_rate": 58.7, - "rank": 25 + "rank": 30 }, { "arena": "models", "category": "uicomponent", - "elo": 1272, + "elo": 1266, "win_rate": 58.3, - "rank": 32 + "rank": 34 }, { "arena": "models", "category": "website", - "elo": 1285, + "elo": 1283, "win_rate": 60, - "rank": 22 + "rank": 23 } ], "artificial_analysis": { - "intelligence_index": 30.1, + "intelligence_index": null, "coding_index": 63, "agentic_index": 31.8 } @@ -5621,19 +6092,20 @@ "links": { "details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1177, + "elo": 1123, "win_rate": 52.2, - "rank": 16 + "rank": 17 }, { "arena": "agents", "category": "androidnative", - "elo": 1196, + "elo": 1193, "win_rate": 62.1, "rank": 14 }, @@ -5654,37 +6126,37 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1212, + "elo": 1210, "win_rate": 63.6, - "rank": 15 + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1190, + "elo": 1177, "win_rate": 57, - "rank": 27 + "rank": 28 }, { "arena": "models", "category": "3d", - "elo": 1234, - "win_rate": 57.6, - "rank": 39 + "elo": 1231, + "win_rate": 57.5, + "rank": 41 }, { "arena": "models", "category": "asciiart", - "elo": 1235, + "elo": 1233, "win_rate": 60.1, - "rank": 19 + "rank": 21 }, { "arena": "models", "category": "codecategories", - "elo": 1276, + "elo": 1274, "win_rate": 59.4, - "rank": 24 + "rank": 26 }, { "arena": "models", @@ -5698,32 +6170,32 @@ "category": "gamedev", "elo": 1259, "win_rate": 58.8, - "rank": 36 + "rank": 37 }, { "arena": "models", "category": "svg", - "elo": 1197, + "elo": 1193, "win_rate": 58.7, - "rank": 25 + "rank": 30 }, { "arena": "models", "category": "uicomponent", - "elo": 1272, + "elo": 1266, "win_rate": 58.3, - "rank": 32 + "rank": 34 }, { "arena": "models", "category": "website", - "elo": 1285, + "elo": 1283, "win_rate": 60, - "rank": 22 + "rank": 23 } ], "artificial_analysis": { - "intelligence_index": 30.1, + "intelligence_index": null, "coding_index": 63, "agentic_index": 31.8 } @@ -5783,28 +6255,41 @@ "links": { "details": "/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1227, - "win_rate": 52.2, - "rank": 7 + "elo": 1172, + "win_rate": 51.7, + "rank": 8 }, { "arena": "agents", "category": "androidnative", - "elo": 1226, - "win_rate": 54.7, - "rank": 9 + "elo": 1220, + "win_rate": 53.8, + "rank": 11 }, { "arena": "agents", "category": "blender3d", - "elo": 1200, - "win_rate": 40.3, - "rank": 1 + "elo": 1004, + "win_rate": 35.6, + "rank": 21 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1126, + "win_rate": 41.9, + "rank": 10 }, { "arena": "agents", @@ -5816,104 +6301,111 @@ { "arena": "agents", "category": "godotgamedev", - "elo": 1225, - "win_rate": 54.4, + "elo": 1223, + "win_rate": 54.2, "rank": 13 }, { "arena": "agents", "category": "htmlslides", - "elo": 1218, + "elo": 1114, "win_rate": 53.7, - "rank": 5 + "rank": 9 }, { "arena": "agents", "category": "mobileapps", - "elo": 1215, - "win_rate": 51.2, - "rank": 14 + "elo": 1208, + "win_rate": 50.2, + "rank": 18 }, { "arena": "agents", - "category": "python-pptxslides", - "elo": 1214, - "win_rate": 50.2, + "category": "pdf", + "elo": 1216, + "win_rate": 52.8, "rank": 13 }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1170, + "win_rate": 49.9, + "rank": 14 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1042, - "win_rate": 44.8, - "rank": 17 + "elo": 1152, + "win_rate": 50.6, + "rank": 13 }, { "arena": "agents", "category": "webapps", - "elo": 1245, - "win_rate": 53.2, - "rank": 13 + "elo": 1229, + "win_rate": 52.5, + "rank": 14 }, { "arena": "models", "category": "3d", - "elo": 1261, + "elo": 1257, "win_rate": 53.9, - "rank": 28 + "rank": 30 }, { "arena": "models", "category": "asciiart", - "elo": 1207, - "win_rate": 51.3, - "rank": 22 + "elo": 1204, + "win_rate": 51, + "rank": 26 }, { "arena": "models", "category": "codecategories", - "elo": 1276, + "elo": 1274, "win_rate": 52.5, - "rank": 25 + "rank": 27 }, { "arena": "models", "category": "dataviz", "elo": 1251, "win_rate": 52.9, - "rank": 34 + "rank": 35 }, { "arena": "models", "category": "gamedev", - "elo": 1278, - "win_rate": 51.6, + "elo": 1275, + "win_rate": 51.2, "rank": 24 }, { "arena": "models", "category": "svg", - "elo": 1194, - "win_rate": 49.6, - "rank": 29 + "elo": 1190, + "win_rate": 49.3, + "rank": 34 }, { "arena": "models", "category": "uicomponent", - "elo": 1280, - "win_rate": 53.9, - "rank": 26 + "elo": 1274, + "win_rate": 53.6, + "rank": 30 }, { "arena": "models", "category": "website", - "elo": 1274, + "elo": 1273, "win_rate": 52.2, - "rank": 26 + "rank": 28 } ], "artificial_analysis": { - "intelligence_index": 38.2, + "intelligence_index": null, "coding_index": 71.5, "agentic_index": 43.6 } @@ -5973,28 +6465,36 @@ "links": { "details": "/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1227, - "win_rate": 52.2, - "rank": 7 + "elo": 1172, + "win_rate": 51.7, + "rank": 8 }, { "arena": "agents", "category": "androidnative", - "elo": 1226, - "win_rate": 54.7, - "rank": 9 + "elo": 1220, + "win_rate": 53.8, + "rank": 11 }, { "arena": "agents", "category": "blender3d", - "elo": 1200, - "win_rate": 40.3, - "rank": 1 + "elo": 1004, + "win_rate": 35.6, + "rank": 21 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1126, + "win_rate": 41.9, + "rank": 10 }, { "arena": "agents", @@ -6006,104 +6506,111 @@ { "arena": "agents", "category": "godotgamedev", - "elo": 1225, - "win_rate": 54.4, + "elo": 1223, + "win_rate": 54.2, "rank": 13 }, { "arena": "agents", "category": "htmlslides", - "elo": 1218, + "elo": 1114, "win_rate": 53.7, - "rank": 5 + "rank": 9 }, { "arena": "agents", "category": "mobileapps", - "elo": 1215, - "win_rate": 51.2, - "rank": 14 + "elo": 1208, + "win_rate": 50.2, + "rank": 18 }, { "arena": "agents", - "category": "python-pptxslides", - "elo": 1214, - "win_rate": 50.2, + "category": "pdf", + "elo": 1216, + "win_rate": 52.8, "rank": 13 }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1170, + "win_rate": 49.9, + "rank": 14 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1042, - "win_rate": 44.8, - "rank": 17 + "elo": 1152, + "win_rate": 50.6, + "rank": 13 }, { "arena": "agents", "category": "webapps", - "elo": 1245, - "win_rate": 53.2, - "rank": 13 + "elo": 1229, + "win_rate": 52.5, + "rank": 14 }, { "arena": "models", "category": "3d", - "elo": 1261, + "elo": 1257, "win_rate": 53.9, - "rank": 28 + "rank": 30 }, { "arena": "models", "category": "asciiart", - "elo": 1207, - "win_rate": 51.3, - "rank": 22 + "elo": 1204, + "win_rate": 51, + "rank": 26 }, { "arena": "models", "category": "codecategories", - "elo": 1276, + "elo": 1274, "win_rate": 52.5, - "rank": 25 + "rank": 27 }, { "arena": "models", "category": "dataviz", "elo": 1251, "win_rate": 52.9, - "rank": 34 + "rank": 35 }, { "arena": "models", "category": "gamedev", - "elo": 1278, - "win_rate": 51.6, + "elo": 1275, + "win_rate": 51.2, "rank": 24 }, { "arena": "models", "category": "svg", - "elo": 1194, - "win_rate": 49.6, - "rank": 29 + "elo": 1190, + "win_rate": 49.3, + "rank": 34 }, { "arena": "models", "category": "uicomponent", - "elo": 1280, - "win_rate": 53.9, - "rank": 26 + "elo": 1274, + "win_rate": 53.6, + "rank": 30 }, { "arena": "models", "category": "website", - "elo": 1274, + "elo": 1273, "win_rate": 52.2, - "rank": 26 + "rank": 28 } ], "artificial_analysis": { - "intelligence_index": 38.2, + "intelligence_index": null, "coding_index": 71.5, "agentic_index": 43.6 } @@ -6141,7 +6648,7 @@ "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -6164,74 +6671,94 @@ "links": { "details": "/api/v1/models/anthropic/claude-sonnet-5.5-20260928/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1261, + "win_rate": 64.4, + "rank": 4 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1255, - "win_rate": 55.9, - "rank": 6 + "elo": 1268, + "win_rate": 57.9, + "rank": 4 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1264, + "win_rate": 60.5, + "rank": 7 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1237, - "win_rate": 51.7, - "rank": 6 + "elo": 1296, + "win_rate": 53.5, + "rank": 5 }, { "arena": "agents", "category": "webapps", - "elo": 1306, - "win_rate": 60.5, - "rank": 3 + "elo": 1294, + "win_rate": 60.2, + "rank": 4 }, { "arena": "models", "category": "3d", - "elo": 1452, - "win_rate": 69.2, - "rank": 3 + "elo": 1399, + "win_rate": 52, + "rank": 6 }, { "arena": "models", "category": "codecategories", - "elo": 1364, - "win_rate": 60.7, - "rank": 3 + "elo": 1351, + "win_rate": 56.5, + "rank": 6 }, { "arena": "models", "category": "dataviz", - "elo": 1394, - "win_rate": 67.8, + "elo": 1366, + "win_rate": 64.6, "rank": 2 }, { "arena": "models", "category": "gamedev", - "elo": 1471, - "win_rate": 72.5, - "rank": 1 + "elo": 1407, + "win_rate": 62, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1364, - "win_rate": 61.5, + "elo": 1376, + "win_rate": 63.5, "rank": 3 }, { "arena": "models", "category": "website", - "elo": 1327, - "win_rate": 56.1, - "rank": 5 + "elo": 1319, + "win_rate": 54.7, + "rank": 6 } ], "artificial_analysis": { - "intelligence_index": 56, + "intelligence_index": 54.5, "coding_index": null, "agentic_index": null } @@ -6290,74 +6817,89 @@ "links": { "details": "/api/v1/models/anthropic/claude-sonnet-5.5-20260928/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1261, + "win_rate": 64.4, + "rank": 4 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1255, - "win_rate": 55.9, - "rank": 6 + "elo": 1268, + "win_rate": 57.9, + "rank": 4 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1264, + "win_rate": 60.5, + "rank": 7 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1237, - "win_rate": 51.7, - "rank": 6 + "elo": 1296, + "win_rate": 53.5, + "rank": 5 }, { "arena": "agents", "category": "webapps", - "elo": 1306, - "win_rate": 60.5, - "rank": 3 + "elo": 1294, + "win_rate": 60.2, + "rank": 4 }, { "arena": "models", "category": "3d", - "elo": 1452, - "win_rate": 69.2, - "rank": 3 + "elo": 1399, + "win_rate": 52, + "rank": 6 }, { "arena": "models", "category": "codecategories", - "elo": 1364, - "win_rate": 60.7, - "rank": 3 + "elo": 1351, + "win_rate": 56.5, + "rank": 6 }, { "arena": "models", "category": "dataviz", - "elo": 1394, - "win_rate": 67.8, + "elo": 1366, + "win_rate": 64.6, "rank": 2 }, { "arena": "models", "category": "gamedev", - "elo": 1471, - "win_rate": 72.5, - "rank": 1 + "elo": 1407, + "win_rate": 62, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1364, - "win_rate": 61.5, + "elo": 1376, + "win_rate": 63.5, "rank": 3 }, { "arena": "models", "category": "website", - "elo": 1327, - "win_rate": 56.1, - "rank": 5 + "elo": 1319, + "win_rate": 54.7, + "rank": 6 } ], "artificial_analysis": { - "intelligence_index": 56, + "intelligence_index": 54.5, "coding_index": null, "agentic_index": null } @@ -6368,125 +6910,6 @@ "default_effort": "high" } }, - { - "id": "arcee-ai/trinity-large-thinking", - "canonical_slug": "arcee-ai/trinity-large-thinking", - "hugging_face_id": "arcee-ai/Trinity-Large-Thinking", - "name": "Arcee AI: Trinity Large Thinking", - "created": 1775058318, - "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000025", - "completion": "0.0000008", - "input_cache_read": "0.00000006" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 80000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": 0.3, - "top_p": 0.8, - "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/arcee-ai/trinity-large-thinking/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1082, - "win_rate": 41.3, - "rank": 93 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1041, - "win_rate": 37.1, - "rank": 68 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1117, - "win_rate": 40.1, - "rank": 97 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1098, - "win_rate": 39.3, - "rank": 100 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1079, - "win_rate": 38.4, - "rank": 106 - }, - { - "arena": "models", - "category": "svg", - "elo": 1017, - "win_rate": 35.2, - "rank": 82 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1045, - "win_rate": 32.6, - "rank": 106 - }, - { - "arena": "models", - "category": "website", - "elo": 1137, - "win_rate": 41.3, - "rank": 98 - } - ], - "artificial_analysis": { - "intelligence_index": 10.8, - "coding_index": 25.8, - "agentic_index": 1 - } - }, - "reasoning": { - "mandatory": true - } - }, { "id": "bytedance-seed/seed-1.6", "canonical_slug": "bytedance-seed/seed-1.6-20250625", @@ -6543,6 +6966,12 @@ "links": { "details": "/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -6603,6 +7032,12 @@ "links": { "details": "/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -6652,6 +7087,12 @@ "links": { "details": "/api/v1/models/bytedance-seed/seed-2-1-turbo-20260810/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -6709,6 +7150,12 @@ "links": { "details": "/api/v1/models/bytedance-seed/seed-2.0-code-20260730/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["high", "medium", "low", "none"], @@ -6775,6 +7222,12 @@ "links": { "details": "/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["high", "medium", "low", "minimal", "none"], @@ -6838,6 +7291,12 @@ "links": { "details": "/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["high", "medium", "low", "minimal", "none"], @@ -6891,7 +7350,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition", @@ -6934,7 +7399,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/venice/uncensored/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "cohere/command-a", @@ -6980,14 +7451,12 @@ "links": { "details": "/api/v1/models/cohere/command-a-03-2025/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 13.1, - "coding_index": 27.8, - "agentic_index": 1 - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "cohere/command-a-plus", @@ -7037,6 +7506,20 @@ "links": { "details": "/api/v1/models/cohere/command-a-plus-05-2026/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 6.2, + "coding_index": 27.8, + "agentic_index": 1 + } + }, "reasoning": { "mandatory": false } @@ -7086,7 +7569,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/cohere/command-r-08-2024/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "cohere/command-r-plus-08-2024", @@ -7133,7 +7622,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/cohere/command-r-plus-08-2024/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "cohere/command-r7b-12-2024", @@ -7178,7 +7673,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/cohere/command-r7b-12-2024/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "cohere/north-mini-code:free", @@ -7233,10 +7734,16 @@ "links": { "details": "/api/v1/models/cohere/north-mini-code-20260617/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 9.9, + "intelligence_index": null, "coding_index": 36.5, "agentic_index": 1.1 } @@ -7294,56 +7801,62 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-chat-v3/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1087, + "elo": 1084, "win_rate": 50.5, - "rank": 91 + "rank": 93 }, { "arena": "models", "category": "codecategories", - "elo": 1108, + "elo": 1106, "win_rate": 48.4, - "rank": 102 + "rank": 106 }, { "arena": "models", "category": "dataviz", "elo": 1089, "win_rate": 50, - "rank": 103 + "rank": 104 }, { "arena": "models", "category": "gamedev", "elo": 1053, "win_rate": 43.7, - "rank": 112 + "rank": 113 }, { "arena": "models", "category": "svg", - "elo": 977, + "elo": 973, "win_rate": 38.8, - "rank": 88 + "rank": 94 }, { "arena": "models", "category": "uicomponent", - "elo": 1093, + "elo": 1088, "win_rate": 52.7, - "rank": 97 + "rank": 101 }, { "arena": "models", "category": "website", - "elo": 1120, + "elo": 1118, "win_rate": 48.5, - "rank": 103 + "rank": 105 } ] } @@ -7395,10 +7908,16 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 9.7, + "intelligence_index": null, "coding_index": 21.2, "agentic_index": 0.8 } @@ -7426,7 +7945,7 @@ }, "top_provider": { "context_length": 163840, - "max_completion_tokens": 32768, + "max_completion_tokens": 147456, "is_moderated": false }, "per_request_limits": null, @@ -7458,63 +7977,64 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1077, + "elo": 1074, "win_rate": 47.9, - "rank": 98 + "rank": 101 }, { "arena": "models", "category": "codecategories", - "elo": 1112, + "elo": 1110, "win_rate": 47.8, - "rank": 100 + "rank": 104 }, { "arena": "models", "category": "dataviz", "elo": 1096, "win_rate": 46.2, - "rank": 102 + "rank": 103 }, { "arena": "models", "category": "gamedev", "elo": 1084, "win_rate": 47.1, - "rank": 103 + "rank": 104 }, { "arena": "models", "category": "svg", - "elo": 967, + "elo": 963, "win_rate": 38.2, - "rank": 89 + "rank": 95 }, { "arena": "models", "category": "uicomponent", - "elo": 1085, + "elo": 1080, "win_rate": 47.1, - "rank": 100 + "rank": 104 }, { "arena": "models", "category": "website", "elo": 1122, "win_rate": 48, - "rank": 102 + "rank": 104 } - ], - "artificial_analysis": { - "intelligence_index": 13.7, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -7578,63 +8098,64 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-r1-0528/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1111, + "elo": 1108, "win_rate": 53.3, - "rank": 86 + "rank": 89 }, { "arena": "models", "category": "codecategories", - "elo": 1139, + "elo": 1137, "win_rate": 52.6, - "rank": 93 + "rank": 96 }, { "arena": "models", "category": "dataviz", "elo": 1182, "win_rate": 60.9, - "rank": 64 + "rank": 65 }, { "arena": "models", "category": "gamedev", "elo": 1097, "win_rate": 49.3, - "rank": 98 + "rank": 99 }, { "arena": "models", "category": "svg", - "elo": 1039, + "elo": 1035, "win_rate": 48.7, - "rank": 75 + "rank": 81 }, { "arena": "models", "category": "uicomponent", - "elo": 1103, + "elo": 1097, "win_rate": 54.9, - "rank": 93 + "rank": 96 }, { "arena": "models", "category": "website", "elo": 1149, "win_rate": 52.7, - "rank": 92 + "rank": 93 } - ], - "artificial_analysis": { - "intelligence_index": 13.1, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true @@ -7671,7 +8192,6 @@ "max_tokens", "reasoning", "response_format", - "stop", "structured_outputs", "temperature", "tool_choice", @@ -7690,60 +8210,66 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1141, + "elo": 1138, "win_rate": 56, - "rank": 70 + "rank": 73 }, { "arena": "models", "category": "codecategories", - "elo": 1175, + "elo": 1173, "win_rate": 56, - "rank": 70 + "rank": 73 }, { "arena": "models", "category": "dataviz", "elo": 1168, "win_rate": 53.4, - "rank": 72 + "rank": 73 }, { "arena": "models", "category": "gamedev", - "elo": 1131, + "elo": 1129, "win_rate": 52.5, - "rank": 88 + "rank": 89 }, { "arena": "models", "category": "svg", - "elo": 1065, + "elo": 1061, "win_rate": 50.1, - "rank": 70 + "rank": 77 }, { "arena": "models", "category": "uicomponent", - "elo": 1182, + "elo": 1177, "win_rate": 59.5, - "rank": 64 + "rank": 67 }, { "arena": "models", "category": "website", - "elo": 1187, + "elo": 1185, "win_rate": 56.4, - "rank": 71 + "rank": 73 } ], "artificial_analysis": { - "intelligence_index": 14.8, + "intelligence_index": null, "coding_index": 43.5, "agentic_index": 6.8 } @@ -7768,13 +8294,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000028", - "completion": "0.00000042", - "input_cache_read": "0.000000028" + "prompt": "0.00000026", + "completion": "0.00000038", + "input_cache_read": "0.00000013" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 65536, + "context_length": 163840, + "max_completion_tokens": 147456, "is_moderated": false }, "per_request_limits": null, @@ -7813,28 +8339,34 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1133, + "elo": 1130, "win_rate": 49.4, - "rank": 74 + "rank": 77 }, { "arena": "models", "category": "asciiart", - "elo": 1083, + "elo": 1080, "win_rate": 40.5, - "rank": 65 + "rank": 68 }, { "arena": "models", "category": "codecategories", - "elo": 1164, + "elo": 1162, "win_rate": 49.3, - "rank": 79 + "rank": 82 }, { "arena": "models", @@ -7846,34 +8378,34 @@ { "arena": "models", "category": "gamedev", - "elo": 1132, + "elo": 1130, "win_rate": 46.5, - "rank": 87 + "rank": 88 }, { "arena": "models", "category": "svg", - "elo": 1033, + "elo": 1029, "win_rate": 40.8, - "rank": 77 + "rank": 84 }, { "arena": "models", "category": "uicomponent", - "elo": 1149, + "elo": 1144, "win_rate": 46.8, - "rank": 78 + "rank": 81 }, { "arena": "models", "category": "website", - "elo": 1175, + "elo": 1173, "win_rate": 50.2, - "rank": 79 + "rank": 81 } ], "artificial_analysis": { - "intelligence_index": 21.5, + "intelligence_index": null, "coding_index": 44.2, "agentic_index": null } @@ -7932,28 +8464,34 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1148, + "elo": 1145, "win_rate": 56.4, - "rank": 68 + "rank": 71 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1170, "win_rate": 54.2, - "rank": 72 + "rank": 74 }, { "arena": "models", "category": "dataviz", "elo": 1152, "win_rate": 50.6, - "rank": 81 + "rank": 82 }, { "arena": "models", @@ -7965,30 +8503,25 @@ { "arena": "models", "category": "svg", - "elo": 1032, + "elo": 1028, "win_rate": 42, - "rank": 78 + "rank": 85 }, { "arena": "models", "category": "uicomponent", - "elo": 1167, + "elo": 1161, "win_rate": 53.3, - "rank": 70 + "rank": 73 }, { "arena": "models", "category": "website", - "elo": 1179, + "elo": 1177, "win_rate": 54.3, - "rank": 76 + "rank": 77 } - ], - "artificial_analysis": { - "intelligence_index": 16.6, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -8051,69 +8584,75 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1189, + "elo": 1186, "win_rate": 49.3, - "rank": 55 + "rank": 57 }, { "arena": "models", "category": "asciiart", - "elo": 1109, + "elo": 1107, "win_rate": 42.7, - "rank": 58 + "rank": 61 }, { "arena": "models", "category": "codecategories", - "elo": 1205, + "elo": 1204, "win_rate": 48.9, - "rank": 59 + "rank": 62 }, { "arena": "models", "category": "dataviz", "elo": 1127, "win_rate": 40.7, - "rank": 92 + "rank": 93 }, { "arena": "models", "category": "gamedev", "elo": 1197, "win_rate": 50.2, - "rank": 57 + "rank": 58 }, { "arena": "models", "category": "svg", - "elo": 1156, + "elo": 1152, "win_rate": 48.4, - "rank": 41 + "rank": 47 }, { "arena": "models", "category": "uicomponent", - "elo": 1165, + "elo": 1159, "win_rate": 44.7, - "rank": 73 + "rank": 76 }, { "arena": "models", "category": "website", - "elo": 1208, + "elo": 1206, "win_rate": 49.1, - "rank": 62 + "rank": 63 } ], "artificial_analysis": { - "intelligence_index": 24.4, - "coding_index": 52, - "agentic_index": 26.3 + "intelligence_index": null, + "coding_index": 56.2, + "agentic_index": 22.2 } }, "reasoning": { @@ -8138,13 +8677,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000044", - "completion": "0.00000132", - "input_cache_read": "0.000000014" + "prompt": "0.000000059", + "completion": "0.0000003", + "input_cache_read": "0.000000035" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 131072, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -8179,67 +8718,73 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1209, + "elo": 1205, "win_rate": 48.7, - "rank": 45 + "rank": 47 }, { "arena": "models", "category": "asciiart", - "elo": 1090, + "elo": 1088, "win_rate": 33.3, - "rank": 63 + "rank": 67 }, { "arena": "models", "category": "codecategories", - "elo": 1230, + "elo": 1228, "win_rate": 46.4, - "rank": 51 + "rank": 53 }, { "arena": "models", "category": "dataviz", "elo": 1180, "win_rate": 41.1, - "rank": 65 + "rank": 66 }, { "arena": "models", "category": "gamedev", - "elo": 1208, + "elo": 1207, "win_rate": 44.6, "rank": 53 }, { "arena": "models", "category": "svg", - "elo": 1185, + "elo": 1180, "win_rate": 45.1, - "rank": 31 + "rank": 37 }, { "arena": "models", "category": "uicomponent", - "elo": 1235, + "elo": 1230, "win_rate": 46.8, - "rank": 48 + "rank": 50 }, { "arena": "models", "category": "website", - "elo": 1238, + "elo": 1236, "win_rate": 46.7, "rank": 51 } ], "artificial_analysis": { - "intelligence_index": 34.3, + "intelligence_index": null, "coding_index": 69.1, "agentic_index": 41 } @@ -8306,10 +8851,16 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4-flash-vision-exp-20260821/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 34.8, + "intelligence_index": null, "coding_index": 65, "agentic_index": 47.5 } @@ -8337,13 +8888,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000095526", - "completion": "0.00000191052", - "input_cache_read": "0.000000079605" + "prompt": "0.0000016", + "completion": "0.0000032", + "input_cache_read": "0.000000135" }, "top_provider": { - "context_length": 1024000, - "max_completion_tokens": 384000, + "context_length": 1048576, + "max_completion_tokens": 393216, "is_moderated": false }, "per_request_limits": null, @@ -8380,6 +8931,12 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -8401,67 +8958,67 @@ "category": "webapps", "elo": 1000, "win_rate": 26.4, - "rank": 45 + "rank": 46 }, { "arena": "models", "category": "3d", - "elo": 1254, + "elo": 1251, "win_rate": 56.8, - "rank": 31 + "rank": 33 }, { "arena": "models", "category": "asciiart", - "elo": 1149, + "elo": 1146, "win_rate": 46.4, - "rank": 44 + "rank": 47 }, { "arena": "models", "category": "codecategories", - "elo": 1240, + "elo": 1238, "win_rate": 51.9, - "rank": 45 + "rank": 47 }, { "arena": "models", "category": "dataviz", "elo": 1203, "win_rate": 48.7, - "rank": 58 + "rank": 59 }, { "arena": "models", "category": "gamedev", "elo": 1229, "win_rate": 52.3, - "rank": 43 + "rank": 44 }, { "arena": "models", "category": "svg", - "elo": 1140, + "elo": 1136, "win_rate": 45.4, - "rank": 49 + "rank": 55 }, { "arena": "models", "category": "uicomponent", - "elo": 1222, + "elo": 1216, "win_rate": 50.6, - "rank": 52 + "rank": 54 }, { "arena": "models", "category": "website", - "elo": 1235, + "elo": 1233, "win_rate": 50.5, "rank": 53 } ], "artificial_analysis": { - "intelligence_index": 30.4, + "intelligence_index": null, "coding_index": 59.4, "agentic_index": 26.3 } @@ -8488,61 +9045,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000066", - "completion": "0.00000198", - "input_cache_read": "0.000000022", - "overrides": [ - { - "utc_days": ["saturday", "sunday"], - "prompt": "0.00000066", - "completion": "0.00000198", - "input_cache_read": "0.000000022" - }, - { - "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], - "utc_start": 0, - "utc_end": 100, - "prompt": "0.00000066", - "completion": "0.00000198", - "input_cache_read": "0.000000022" - }, - { - "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], - "utc_start": 100, - "utc_end": 400, - "prompt": "0.00000132", - "completion": "0.00000396", - "input_cache_read": "0.000000044" - }, - { - "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], - "utc_start": 400, - "utc_end": 600, - "prompt": "0.00000066", - "completion": "0.00000198", - "input_cache_read": "0.000000022" - }, - { - "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], - "utc_start": 600, - "utc_end": 1000, - "prompt": "0.00000132", - "completion": "0.00000396", - "input_cache_read": "0.000000044" - }, - { - "utc_days": ["monday", "tuesday", "wednesday", "thursday", "friday"], - "utc_start": 1000, - "utc_end": 0, - "prompt": "0.00000066", - "completion": "0.00000198", - "input_cache_read": "0.000000022" - } - ] + "prompt": "0.000000115", + "completion": "0.0000046", + "input_cache_read": "0.00000011" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 393216, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -8578,10 +9087,16 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4-pro-20260813/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 36, + "intelligence_index": 23.1, "coding_index": 68.8, "agentic_index": 41.3 } @@ -8608,9 +9123,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012", - "input_cache_read": "0.000000006" + "prompt": "0.000000045", + "completion": "0.0000005", + "input_cache_read": "0.000000018" }, "top_provider": { "context_length": 1048576, @@ -8625,6 +9140,7 @@ "logprobs", "max_tokens", "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", @@ -8636,6 +9152,7 @@ "temperature", "tool_choice", "tools", + "top_a", "top_k", "top_logprobs", "top_p" @@ -8647,14 +9164,12 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 24.7, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -8767,67 +9282,80 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "spreadsheet", - "elo": 1224, + "elo": 1290, "win_rate": 51.2, - "rank": 8 + "rank": 6 }, { "arena": "models", "category": "3d", - "elo": 1373, - "win_rate": 60.8, - "rank": 9 + "elo": 1361, + "win_rate": 47.6, + "rank": 10 }, { "arena": "models", "category": "asciiart", - "elo": 1243, - "win_rate": 55, - "rank": 18 + "elo": 1234, + "win_rate": 49.7, + "rank": 20 }, { "arena": "models", "category": "codecategories", - "elo": 1333, - "win_rate": 58.6, - "rank": 8 + "elo": 1290, + "win_rate": 48.5, + "rank": 19 }, { "arena": "models", "category": "dataviz", - "elo": 1325, - "win_rate": 57.7, - "rank": 11 + "elo": 1272, + "win_rate": 51.1, + "rank": 27 }, { "arena": "models", "category": "gamedev", - "elo": 1361, - "win_rate": 61.8, - "rank": 7 + "elo": 1260, + "win_rate": 43.4, + "rank": 36 + }, + { + "arena": "models", + "category": "svg", + "elo": 1249, + "win_rate": 52.1, + "rank": 17 }, { "arena": "models", "category": "uicomponent", - "elo": 1300, - "win_rate": 54.1, - "rank": 16 + "elo": 1301, + "win_rate": 50.4, + "rank": 18 }, { "arena": "models", "category": "website", - "elo": 1312, - "win_rate": 56.2, - "rank": 11 + "elo": 1297, + "win_rate": 51.9, + "rank": 16 } ], "artificial_analysis": { - "intelligence_index": 39.5, + "intelligence_index": 28.6, "coding_index": null, "agentic_index": null } @@ -8894,14 +9422,7 @@ "links": { "details": "/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 24.7, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": false, "default_enabled": true, @@ -8952,6 +9473,12 @@ "links": { "details": "/api/v1/models/dots-studio/dots-3-note-preview-20260813/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -9009,6 +9536,12 @@ "links": { "details": "/api/v1/models/elorian/glimpse-20261016/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -9066,6 +9599,12 @@ "links": { "details": "/api/v1/models/fireworks/ember-1-20260923/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -9132,63 +9671,64 @@ "links": { "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1071, + "elo": 1068, "win_rate": 47.4, - "rank": 101 + "rank": 104 }, { "arena": "models", "category": "codecategories", - "elo": 1104, + "elo": 1102, "win_rate": 46.9, - "rank": 103 + "rank": 107 }, { "arena": "models", "category": "dataviz", "elo": 1134, "win_rate": 49.1, - "rank": 89 + "rank": 90 }, { "arena": "models", "category": "gamedev", - "elo": 1066, + "elo": 1064, "win_rate": 44.3, - "rank": 110 + "rank": 111 }, { "arena": "models", "category": "uicomponent", - "elo": 1093, + "elo": 1087, "win_rate": 48.9, - "rank": 98 + "rank": 103 }, { "arena": "models", "category": "website", - "elo": 1115, + "elo": 1113, "win_rate": 47.1, - "rank": 105 + "rank": 107 }, { "arena": "models", "category": "svg", - "elo": 1020, + "elo": 1016, "win_rate": 43.1, - "rank": 81 + "rank": 87 } - ], - "artificial_analysis": { - "intelligence_index": 15.5, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -9247,6 +9787,13 @@ "links": { "details": "/api/v1/models/google/gemini-2.5-flash-image/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "benchmarks": { "design_arena": [ { @@ -9259,7 +9806,7 @@ { "arena": "models", "category": "image", - "elo": 1186, + "elo": 1183, "win_rate": 55.6, "rank": 10 }, @@ -9329,14 +9876,12 @@ "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 - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -9406,53 +9951,59 @@ "links": { "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1081, + "elo": 1078, "win_rate": 50.6, - "rank": 94 + "rank": 98 }, { "arena": "models", "category": "codecategories", - "elo": 1152, + "elo": 1150, "win_rate": 57.5, - "rank": 84 + "rank": 87 }, { "arena": "models", "category": "dataviz", "elo": 1222, "win_rate": 68.2, - "rank": 50 + "rank": 51 }, { "arena": "models", "category": "gamedev", "elo": 1111, "win_rate": 54.2, - "rank": 92 + "rank": 93 }, { "arena": "models", "category": "uicomponent", - "elo": 1140, + "elo": 1134, "win_rate": 57.5, - "rank": 82 + "rank": 86 }, { "arena": "models", "category": "website", - "elo": 1167, + "elo": 1165, "win_rate": 58.4, - "rank": 83 + "rank": 84 } ], "artificial_analysis": { - "intelligence_index": 16.1, + "intelligence_index": null, "coding_index": 33.3, "agentic_index": 1.6 } @@ -9523,6 +10074,12 @@ "links": { "details": "/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -9587,6 +10144,12 @@ "links": { "details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -9606,9 +10169,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1050, + "elo": 1047, "win_rate": 48.1, - "rank": 34 + "rank": 36 }, { "arena": "agents", @@ -9629,56 +10192,51 @@ "category": "mobileapps", "elo": 1090, "win_rate": 46.6, - "rank": 41 + "rank": 43 }, { "arena": "agents", "category": "python-pptxslides", "elo": 1036, "win_rate": 38.3, - "rank": 27 + "rank": 28 }, { "arena": "agents", "category": "webapps", - "elo": 1110, + "elo": 1097, "win_rate": 48.5, - "rank": 37 + "rank": 38 }, { "arena": "models", "category": "3d", - "elo": 1184, + "elo": 1181, "win_rate": 62.7, - "rank": 56 + "rank": 58 }, { "arena": "models", "category": "codecategories", - "elo": 1189, + "elo": 1187, "win_rate": 57.6, - "rank": 62 + "rank": 65 }, { "arena": "models", "category": "gamedev", "elo": 1166, "win_rate": 58.3, - "rank": 70 + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1196, + "elo": 1194, "win_rate": 57, - "rank": 64 + "rank": 67 } - ], - "artificial_analysis": { - "intelligence_index": 26.3, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -9743,6 +10301,7 @@ "links": { "details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { @@ -9762,9 +10321,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1050, + "elo": 1047, "win_rate": 48.1, - "rank": 34 + "rank": 36 }, { "arena": "agents", @@ -9785,56 +10344,51 @@ "category": "mobileapps", "elo": 1090, "win_rate": 46.6, - "rank": 41 + "rank": 43 }, { "arena": "agents", "category": "python-pptxslides", "elo": 1036, "win_rate": 38.3, - "rank": 27 + "rank": 28 }, { "arena": "agents", "category": "webapps", - "elo": 1110, + "elo": 1097, "win_rate": 48.5, - "rank": 37 + "rank": 38 }, { "arena": "models", "category": "3d", - "elo": 1184, + "elo": 1181, "win_rate": 62.7, - "rank": 56 + "rank": 58 }, { "arena": "models", "category": "codecategories", - "elo": 1189, + "elo": 1187, "win_rate": 57.6, - "rank": 62 + "rank": 65 }, { "arena": "models", "category": "gamedev", "elo": 1166, "win_rate": 58.3, - "rank": 70 + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1196, + "elo": 1194, "win_rate": 57, - "rank": 64 + "rank": 67 } - ], - "artificial_analysis": { - "intelligence_index": 26.3, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -9895,6 +10449,13 @@ "links": { "details": "/api/v1/models/google/gemini-3-pro-image-20260528/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "reasoning": { "mandatory": true } @@ -9954,6 +10515,13 @@ "links": { "details": "/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "benchmarks": { "design_arena": [ { @@ -9966,7 +10534,7 @@ { "arena": "models", "category": "image", - "elo": 1244, + "elo": 1241, "win_rate": 62.1, "rank": 5 }, @@ -10035,6 +10603,13 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-flash-image-20260528/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -10094,6 +10669,13 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-flash-image-preview-20260226/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "benchmarks": { "design_arena": [ { @@ -10106,7 +10688,7 @@ { "arena": "models", "category": "image", - "elo": 1276, + "elo": 1274, "win_rate": 65.1, "rank": 4 }, @@ -10186,6 +10768,12 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -10237,6 +10825,13 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-flash-lite-image-20260630/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -10303,67 +10898,73 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-flash-lite-preview-20260303/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1048, + "elo": 1045, "win_rate": 38.8, - "rank": 105 + "rank": 108 }, { "arena": "models", "category": "asciiart", - "elo": 1167, + "elo": 1164, "win_rate": 50.8, - "rank": 32 + "rank": 35 }, { "arena": "models", "category": "codecategories", - "elo": 1072, + "elo": 1070, "win_rate": 36.5, - "rank": 109 + "rank": 113 }, { "arena": "models", "category": "dataviz", "elo": 1045, "win_rate": 33.3, - "rank": 110 + "rank": 111 }, { "arena": "models", "category": "gamedev", "elo": 1029, "win_rate": 33.7, - "rank": 119 + "rank": 120 }, { "arena": "models", "category": "svg", - "elo": 1053, + "elo": 1049, "win_rate": 42.5, - "rank": 72 + "rank": 78 }, { "arena": "models", "category": "uicomponent", - "elo": 1072, + "elo": 1066, "win_rate": 37.7, - "rank": 103 + "rank": 107 }, { "arena": "models", "category": "website", - "elo": 1083, + "elo": 1081, "win_rate": 36.6, - "rank": 113 + "rank": 115 } ], "artificial_analysis": { - "intelligence_index": 15.6, + "intelligence_index": 6.2, "coding_index": 34.7, "agentic_index": 1.6 } @@ -10434,6 +11035,7 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": false, "default_enabled": true, @@ -10511,14 +11113,20 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1113, - "win_rate": 44.1, - "rank": 22 + "elo": 1059, + "win_rate": 43.9, + "rank": 23 }, { "arena": "agents", @@ -10551,9 +11159,23 @@ { "arena": "agents", "category": "androidnative", - "elo": 1049, + "elo": 1045, "win_rate": 41.3, - "rank": 35 + "rank": 37 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1037, + "win_rate": 39.8, + "rank": 18 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1153, + "win_rate": 47.6, + "rank": 9 }, { "arena": "agents", @@ -10572,16 +11194,23 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1154, + "elo": 1049, "win_rate": 48.6, - "rank": 16 + "rank": 18 }, { "arena": "agents", "category": "mobileapps", - "elo": 1094, - "win_rate": 43, - "rank": 39 + "elo": 1093, + "win_rate": 42.6, + "rank": 41 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1148, + "win_rate": 42.3, + "rank": 22 }, { "arena": "agents", @@ -10595,74 +11224,81 @@ "category": "python-pptxslides", "elo": 1109, "win_rate": 31.9, - "rank": 25 + "rank": 24 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1006, + "win_rate": 32.1, + "rank": 26 }, { "arena": "agents", "category": "webapps", - "elo": 1125, + "elo": 1113, "win_rate": 44.3, "rank": 34 }, { "arena": "models", "category": "3d", - "elo": 1234, + "elo": 1231, "win_rate": 58.4, - "rank": 40 + "rank": 42 }, { "arena": "models", "category": "asciiart", - "elo": 1270, + "elo": 1267, "win_rate": 63.5, - "rank": 11 + "rank": 14 }, { "arena": "models", "category": "codecategories", - "elo": 1244, + "elo": 1242, "win_rate": 64.4, - "rank": 43 + "rank": 45 }, { "arena": "models", "category": "dataviz", "elo": 1239, "win_rate": 61.8, - "rank": 39 + "rank": 41 }, { "arena": "models", "category": "gamedev", - "elo": 1203, + "elo": 1202, "win_rate": 52.2, - "rank": 56 + "rank": 57 }, { "arena": "models", "category": "svg", - "elo": 1285, + "elo": 1281, "win_rate": 67.8, - "rank": 9 + "rank": 12 }, { "arena": "models", "category": "uicomponent", - "elo": 1280, + "elo": 1275, "win_rate": 69.4, - "rank": 27 + "rank": 29 }, { "arena": "models", "category": "website", - "elo": 1253, + "elo": 1251, "win_rate": 64.4, "rank": 43 } ], "artificial_analysis": { - "intelligence_index": 29.7, + "intelligence_index": null, "coding_index": 68.8, "agentic_index": 8.2 } @@ -10739,6 +11375,12 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["high", "medium", "low"], @@ -10810,14 +11452,15 @@ "links": { "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1113, - "win_rate": 44.1, - "rank": 22 + "elo": 1059, + "win_rate": 43.9, + "rank": 23 }, { "arena": "agents", @@ -10850,9 +11493,23 @@ { "arena": "agents", "category": "androidnative", - "elo": 1049, + "elo": 1045, "win_rate": 41.3, - "rank": 35 + "rank": 37 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1037, + "win_rate": 39.8, + "rank": 18 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1153, + "win_rate": 47.6, + "rank": 9 }, { "arena": "agents", @@ -10871,16 +11528,23 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1154, + "elo": 1049, "win_rate": 48.6, - "rank": 16 + "rank": 18 }, { "arena": "agents", "category": "mobileapps", - "elo": 1094, - "win_rate": 43, - "rank": 39 + "elo": 1093, + "win_rate": 42.6, + "rank": 41 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1148, + "win_rate": 42.3, + "rank": 22 }, { "arena": "agents", @@ -10894,74 +11558,81 @@ "category": "python-pptxslides", "elo": 1109, "win_rate": 31.9, - "rank": 25 + "rank": 24 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1006, + "win_rate": 32.1, + "rank": 26 }, { "arena": "agents", "category": "webapps", - "elo": 1125, + "elo": 1113, "win_rate": 44.3, "rank": 34 }, { "arena": "models", "category": "3d", - "elo": 1234, + "elo": 1231, "win_rate": 58.4, - "rank": 40 + "rank": 42 }, { "arena": "models", "category": "asciiart", - "elo": 1270, + "elo": 1267, "win_rate": 63.5, - "rank": 11 + "rank": 14 }, { "arena": "models", "category": "codecategories", - "elo": 1244, + "elo": 1242, "win_rate": 64.4, - "rank": 43 + "rank": 45 }, { "arena": "models", "category": "dataviz", "elo": 1239, "win_rate": 61.8, - "rank": 39 + "rank": 41 }, { "arena": "models", "category": "gamedev", - "elo": 1203, + "elo": 1202, "win_rate": 52.2, - "rank": 56 + "rank": 57 }, { "arena": "models", "category": "svg", - "elo": 1285, + "elo": 1281, "win_rate": 67.8, - "rank": 9 + "rank": 12 }, { "arena": "models", "category": "uicomponent", - "elo": 1280, + "elo": 1275, "win_rate": 69.4, - "rank": 27 + "rank": 29 }, { "arena": "models", "category": "website", - "elo": 1253, + "elo": 1251, "win_rate": 64.4, "rank": 43 } ], "artificial_analysis": { - "intelligence_index": 29.7, + "intelligence_index": null, "coding_index": 68.8, "agentic_index": 8.2 } @@ -11032,14 +11703,20 @@ "links": { "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1180, - "win_rate": 55.4, - "rank": 12 + "elo": 1128, + "win_rate": 55.3, + "rank": 14 }, { "arena": "agents", @@ -11072,9 +11749,16 @@ { "arena": "agents", "category": "androidnative", - "elo": 1184, - "win_rate": 57.7, - "rank": 15 + "elo": 1181, + "win_rate": 57.5, + "rank": 16 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 949, + "win_rate": 31.5, + "rank": 24 }, { "arena": "agents", @@ -11093,16 +11777,23 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1143, + "elo": 1039, "win_rate": 46.5, - "rank": 19 + "rank": 21 }, { "arena": "agents", "category": "mobileapps", "elo": 1174, - "win_rate": 50.6, - "rank": 24 + "win_rate": 50.3, + "rank": 26 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1135, + "win_rate": 45.2, + "rank": 23 }, { "arena": "agents", @@ -11116,76 +11807,83 @@ "category": "python-pptxslides", "elo": 1247, "win_rate": 57.4, - "rank": 9 + "rank": 5 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1097, + "win_rate": 43.3, + "rank": 18 }, { "arena": "agents", "category": "webapps", - "elo": 1202, - "win_rate": 52.2, - "rank": 23 + "elo": 1189, + "win_rate": 52, + "rank": 25 }, { "arena": "models", "category": "3d", - "elo": 1244, + "elo": 1240, "win_rate": 55.8, - "rank": 35 + "rank": 38 }, { "arena": "models", "category": "asciiart", - "elo": 1254, - "win_rate": 59, - "rank": 17 + "elo": 1250, + "win_rate": 58.8, + "rank": 19 }, { "arena": "models", "category": "codecategories", - "elo": 1266, + "elo": 1265, "win_rate": 54, - "rank": 33 + "rank": 36 }, { "arena": "models", "category": "dataviz", - "elo": 1236, - "win_rate": 52.9, - "rank": 40 + "elo": 1239, + "win_rate": 53.2, + "rank": 42 }, { "arena": "models", "category": "gamedev", - "elo": 1263, - "win_rate": 52.7, - "rank": 32 + "elo": 1262, + "win_rate": 52.4, + "rank": 33 }, { "arena": "models", "category": "svg", - "elo": 1254, - "win_rate": 58.3, - "rank": 13 + "elo": 1251, + "win_rate": 58.1, + "rank": 16 }, { "arena": "models", "category": "uicomponent", - "elo": 1273, - "win_rate": 54.3, - "rank": 31 + "elo": 1267, + "win_rate": 54.1, + "rank": 33 }, { "arena": "models", "category": "website", - "elo": 1268, + "elo": 1267, "win_rate": 53.7, "rank": 32 } ], "artificial_analysis": { - "intelligence_index": 33.6, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 70.1, + "agentic_index": 26 } }, "reasoning": { @@ -11255,10 +11953,16 @@ "links": { "details": "/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 22.2, + "intelligence_index": 11.7, "coding_index": 49.3, "agentic_index": 14.3 } @@ -11327,10 +12031,11 @@ "links": { "details": "/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 22.2, + "intelligence_index": 11.7, "coding_index": 49.3, "agentic_index": 14.3 } @@ -11401,14 +12106,15 @@ "links": { "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1180, - "win_rate": 55.4, - "rank": 12 + "elo": 1128, + "win_rate": 55.3, + "rank": 14 }, { "arena": "agents", @@ -11441,9 +12147,16 @@ { "arena": "agents", "category": "androidnative", - "elo": 1184, - "win_rate": 57.7, - "rank": 15 + "elo": 1181, + "win_rate": 57.5, + "rank": 16 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 949, + "win_rate": 31.5, + "rank": 24 }, { "arena": "agents", @@ -11462,16 +12175,23 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1143, + "elo": 1039, "win_rate": 46.5, - "rank": 19 + "rank": 21 }, { "arena": "agents", "category": "mobileapps", "elo": 1174, - "win_rate": 50.6, - "rank": 24 + "win_rate": 50.3, + "rank": 26 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1135, + "win_rate": 45.2, + "rank": 23 }, { "arena": "agents", @@ -11485,76 +12205,83 @@ "category": "python-pptxslides", "elo": 1247, "win_rate": 57.4, - "rank": 9 + "rank": 5 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1097, + "win_rate": 43.3, + "rank": 18 }, { "arena": "agents", "category": "webapps", - "elo": 1202, - "win_rate": 52.2, - "rank": 23 + "elo": 1189, + "win_rate": 52, + "rank": 25 }, { "arena": "models", "category": "3d", - "elo": 1244, + "elo": 1240, "win_rate": 55.8, - "rank": 35 + "rank": 38 }, { "arena": "models", "category": "asciiart", - "elo": 1254, - "win_rate": 59, - "rank": 17 + "elo": 1250, + "win_rate": 58.8, + "rank": 19 }, { "arena": "models", "category": "codecategories", - "elo": 1266, + "elo": 1265, "win_rate": 54, - "rank": 33 + "rank": 36 }, { "arena": "models", "category": "dataviz", - "elo": 1236, - "win_rate": 52.9, - "rank": 40 + "elo": 1239, + "win_rate": 53.2, + "rank": 42 }, { "arena": "models", "category": "gamedev", - "elo": 1263, - "win_rate": 52.7, - "rank": 32 + "elo": 1262, + "win_rate": 52.4, + "rank": 33 }, { "arena": "models", "category": "svg", - "elo": 1254, - "win_rate": 58.3, - "rank": 13 + "elo": 1251, + "win_rate": 58.1, + "rank": 16 }, { "arena": "models", "category": "uicomponent", - "elo": 1273, - "win_rate": 54.3, - "rank": 31 + "elo": 1267, + "win_rate": 54.1, + "rank": 33 }, { "arena": "models", "category": "website", - "elo": 1268, + "elo": 1267, "win_rate": 53.7, "rank": 32 } ], "artificial_analysis": { - "intelligence_index": 33.6, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 70.1, + "agentic_index": 26 } }, "reasoning": { @@ -11624,21 +12351,34 @@ "links": { "details": "/api/v1/models/google/gemini-3.6-flash-20260721/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1180, - "win_rate": 47.6, - "rank": 13 + "elo": 1125, + "win_rate": 47.3, + "rank": 15 }, { "arena": "agents", "category": "androidnative", - "elo": 1203, - "win_rate": 53.5, - "rank": 11 + "elo": 1199, + "win_rate": 53.3, + "rank": 13 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1098, + "win_rate": 49.6, + "rank": 13 }, { "arena": "agents", @@ -11650,90 +12390,97 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1149, + "elo": 1045, "win_rate": 41.9, - "rank": 17 + "rank": 19 }, { "arena": "agents", "category": "mobileapps", - "elo": 1199, - "win_rate": 50.1, - "rank": 18 + "elo": 1196, + "win_rate": 49.7, + "rank": 20 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1214, + "win_rate": 52.2, + "rank": 14 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1144, - "win_rate": 38.9, - "rank": 24 + "elo": 1098, + "win_rate": 39.2, + "rank": 25 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1072, - "win_rate": 43.1, - "rank": 11 + "elo": 1097, + "win_rate": 46.8, + "rank": 19 }, { "arena": "agents", "category": "webapps", - "elo": 1197, - "win_rate": 45.6, - "rank": 25 + "elo": 1183, + "win_rate": 45.4, + "rank": 26 }, { "arena": "models", "category": "3d", - "elo": 1272, - "win_rate": 52.9, - "rank": 24 + "elo": 1269, + "win_rate": 52.8, + "rank": 26 }, { "arena": "models", "category": "asciiart", - "elo": 1281, - "win_rate": 57.3, - "rank": 5 + "elo": 1274, + "win_rate": 56.7, + "rank": 10 }, { "arena": "models", "category": "codecategories", - "elo": 1290, - "win_rate": 53.4, - "rank": 19 + "elo": 1288, + "win_rate": 52.9, + "rank": 21 }, { "arena": "models", "category": "dataviz", - "elo": 1289, - "win_rate": 52.3, - "rank": 16 + "elo": 1290, + "win_rate": 52.2, + "rank": 15 }, { "arena": "models", "category": "gamedev", "elo": 1263, "win_rate": 51, - "rank": 33 + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1297, - "win_rate": 53.8, + "elo": 1296, + "win_rate": 54, "rank": 19 }, { "arena": "models", "category": "website", - "elo": 1300, - "win_rate": 55.4, - "rank": 16 + "elo": 1297, + "win_rate": 54.1, + "rank": 17 } ], "artificial_analysis": { - "intelligence_index": 34, + "intelligence_index": null, "coding_index": 69.2, "agentic_index": 29 } @@ -11803,21 +12550,29 @@ "links": { "details": "/api/v1/models/google/gemini-3.6-flash-20260721/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1180, - "win_rate": 47.6, - "rank": 13 + "elo": 1125, + "win_rate": 47.3, + "rank": 15 }, { "arena": "agents", "category": "androidnative", - "elo": 1203, - "win_rate": 53.5, - "rank": 11 + "elo": 1199, + "win_rate": 53.3, + "rank": 13 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1098, + "win_rate": 49.6, + "rank": 13 }, { "arena": "agents", @@ -11829,90 +12584,97 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1149, + "elo": 1045, "win_rate": 41.9, - "rank": 17 + "rank": 19 }, { "arena": "agents", "category": "mobileapps", - "elo": 1199, - "win_rate": 50.1, - "rank": 18 + "elo": 1196, + "win_rate": 49.7, + "rank": 20 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1214, + "win_rate": 52.2, + "rank": 14 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1144, - "win_rate": 38.9, - "rank": 24 + "elo": 1098, + "win_rate": 39.2, + "rank": 25 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1072, - "win_rate": 43.1, - "rank": 11 + "elo": 1097, + "win_rate": 46.8, + "rank": 19 }, { "arena": "agents", "category": "webapps", - "elo": 1197, - "win_rate": 45.6, - "rank": 25 + "elo": 1183, + "win_rate": 45.4, + "rank": 26 }, { "arena": "models", "category": "3d", - "elo": 1272, - "win_rate": 52.9, - "rank": 24 + "elo": 1269, + "win_rate": 52.8, + "rank": 26 }, { "arena": "models", "category": "asciiart", - "elo": 1281, - "win_rate": 57.3, - "rank": 5 + "elo": 1274, + "win_rate": 56.7, + "rank": 10 }, { "arena": "models", "category": "codecategories", - "elo": 1290, - "win_rate": 53.4, - "rank": 19 + "elo": 1288, + "win_rate": 52.9, + "rank": 21 }, { "arena": "models", "category": "dataviz", - "elo": 1289, - "win_rate": 52.3, - "rank": 16 + "elo": 1290, + "win_rate": 52.2, + "rank": 15 }, { "arena": "models", "category": "gamedev", "elo": 1263, "win_rate": 51, - "rank": 33 + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1297, - "win_rate": 53.8, + "elo": 1296, + "win_rate": 54, "rank": 19 }, { "arena": "models", "category": "website", - "elo": 1300, - "win_rate": 55.4, - "rank": 16 + "elo": 1297, + "win_rate": 54.1, + "rank": 17 } ], "artificial_analysis": { - "intelligence_index": 34, + "intelligence_index": null, "coding_index": 69.2, "agentic_index": 29 } @@ -11977,118 +12739,138 @@ "links": { "details": "/api/v1/models/google/gemini-3.7-flash-20260813/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1235, - "win_rate": 52, - "rank": 6 + "elo": 1181, + "win_rate": 52.1, + "rank": 7 }, { "arena": "agents", "category": "androidnative", - "elo": 1242, - "win_rate": 53.3, - "rank": 6 + "elo": 1239, + "win_rate": 53.1, + "rank": 7 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1112, + "win_rate": 49.6, + "rank": 12 }, { "arena": "agents", "category": "fullstack", - "elo": 1208, - "win_rate": 43.5, - "rank": 16 + "elo": 1210, + "win_rate": 43.7, + "rank": 15 }, { "arena": "agents", "category": "godotgamedev", "elo": 1264, - "win_rate": 50.8, + "win_rate": 50.6, "rank": 6 }, { "arena": "agents", "category": "mobileapps", - "elo": 1231, - "win_rate": 52.6, - "rank": 9 + "elo": 1230, + "win_rate": 52.7, + "rank": 12 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1175, + "win_rate": 47.5, + "rank": 16 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1071, - "win_rate": 46.5, - "rank": 12 + "elo": 1135, + "win_rate": 47.1, + "rank": 14 }, { "arena": "agents", "category": "webapps", - "elo": 1223, - "win_rate": 47.3, - "rank": 16 + "elo": 1207, + "win_rate": 46.9, + "rank": 18 }, { "arena": "models", "category": "3d", - "elo": 1308, - "win_rate": 53.7, - "rank": 18 + "elo": 1306, + "win_rate": 53.8, + "rank": 19 }, { "arena": "models", "category": "asciiart", - "elo": 1276, - "win_rate": 55.2, - "rank": 9 + "elo": 1275, + "win_rate": 54.8, + "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1308, - "win_rate": 53.9, + "elo": 1306, + "win_rate": 53.7, "rank": 14 }, { "arena": "models", "category": "dataviz", - "elo": 1315, - "win_rate": 55.2, - "rank": 13 + "elo": 1316, + "win_rate": 55.1, + "rank": 11 }, { "arena": "models", "category": "gamedev", - "elo": 1318, + "elo": 1319, "win_rate": 53.5, - "rank": 12 + "rank": 13 }, { "arena": "models", "category": "svg", - "elo": 1284, - "win_rate": 54, - "rank": 12 + "elo": 1283, + "win_rate": 53.9, + "rank": 11 }, { "arena": "models", "category": "uicomponent", - "elo": 1298, - "win_rate": 52, - "rank": 18 + "elo": 1294, + "win_rate": 51.9, + "rank": 20 }, { "arena": "models", "category": "website", - "elo": 1304, - "win_rate": 54, - "rank": 14 + "elo": 1303, + "win_rate": 53.8, + "rank": 13 } ], "artificial_analysis": { - "intelligence_index": 39.6, - "coding_index": 71.5, - "agentic_index": null + "intelligence_index": null, + "coding_index": 76.1, + "agentic_index": 35.2 } }, "reasoning": { @@ -12149,118 +12931,133 @@ "links": { "details": "/api/v1/models/google/gemini-3.7-flash-20260813/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1235, - "win_rate": 52, - "rank": 6 + "elo": 1181, + "win_rate": 52.1, + "rank": 7 }, { "arena": "agents", "category": "androidnative", - "elo": 1242, - "win_rate": 53.3, - "rank": 6 + "elo": 1239, + "win_rate": 53.1, + "rank": 7 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1112, + "win_rate": 49.6, + "rank": 12 }, { "arena": "agents", "category": "fullstack", - "elo": 1208, - "win_rate": 43.5, - "rank": 16 + "elo": 1210, + "win_rate": 43.7, + "rank": 15 }, { "arena": "agents", "category": "godotgamedev", "elo": 1264, - "win_rate": 50.8, + "win_rate": 50.6, "rank": 6 }, { "arena": "agents", "category": "mobileapps", - "elo": 1231, - "win_rate": 52.6, - "rank": 9 + "elo": 1230, + "win_rate": 52.7, + "rank": 12 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1175, + "win_rate": 47.5, + "rank": 16 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1071, - "win_rate": 46.5, - "rank": 12 + "elo": 1135, + "win_rate": 47.1, + "rank": 14 }, { "arena": "agents", "category": "webapps", - "elo": 1223, - "win_rate": 47.3, - "rank": 16 + "elo": 1207, + "win_rate": 46.9, + "rank": 18 }, { "arena": "models", "category": "3d", - "elo": 1308, - "win_rate": 53.7, - "rank": 18 + "elo": 1306, + "win_rate": 53.8, + "rank": 19 }, { "arena": "models", "category": "asciiart", - "elo": 1276, - "win_rate": 55.2, - "rank": 9 + "elo": 1275, + "win_rate": 54.8, + "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1308, - "win_rate": 53.9, + "elo": 1306, + "win_rate": 53.7, "rank": 14 }, { "arena": "models", "category": "dataviz", - "elo": 1315, - "win_rate": 55.2, - "rank": 13 + "elo": 1316, + "win_rate": 55.1, + "rank": 11 }, { "arena": "models", "category": "gamedev", - "elo": 1318, + "elo": 1319, "win_rate": 53.5, - "rank": 12 + "rank": 13 }, { "arena": "models", "category": "svg", - "elo": 1284, - "win_rate": 54, - "rank": 12 + "elo": 1283, + "win_rate": 53.9, + "rank": 11 }, { "arena": "models", "category": "uicomponent", - "elo": 1298, - "win_rate": 52, - "rank": 18 + "elo": 1294, + "win_rate": 51.9, + "rank": 20 }, { "arena": "models", "category": "website", - "elo": 1304, - "win_rate": 54, - "rank": 14 + "elo": 1303, + "win_rate": 53.8, + "rank": 13 } ], "artificial_analysis": { - "intelligence_index": 39.6, - "coding_index": 71.5, - "agentic_index": null + "intelligence_index": null, + "coding_index": 76.1, + "agentic_index": 35.2 } }, "reasoning": { @@ -12323,15 +13120,35 @@ "links": { "details": "/api/v1/models/google/gemini-3.8-flash-20260902/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1075, - "win_rate": 32.8, + "elo": 1092, + "win_rate": 34.4, "rank": 32 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1198, + "win_rate": 54.7, + "rank": 6 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1236, + "win_rate": 58.3, + "rank": 3 + }, { "arena": "agents", "category": "fullstack", @@ -12349,90 +13166,97 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1236, + "elo": 1232, "win_rate": 54.4, - "rank": 7 + "rank": 9 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1220, + "win_rate": 54, + "rank": 11 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1174, - "win_rate": 39.9, - "rank": 19 + "elo": 1138, + "win_rate": 40.4, + "rank": 21 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1056, - "win_rate": 39.8, - "rank": 14 + "elo": 1070, + "win_rate": 42.2, + "rank": 21 }, { "arena": "agents", "category": "webapps", - "elo": 1238, - "win_rate": 46.7, - "rank": 14 + "elo": 1226, + "win_rate": 46.9, + "rank": 15 }, { "arena": "models", "category": "3d", - "elo": 1295, - "win_rate": 50, - "rank": 20 + "elo": 1291, + "win_rate": 49.8, + "rank": 21 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 51.1, + "elo": 1269, + "win_rate": 51.8, "rank": 13 }, { "arena": "models", "category": "codecategories", - "elo": 1304, + "elo": 1302, "win_rate": 50.4, "rank": 16 }, { "arena": "models", "category": "dataviz", - "elo": 1270, - "win_rate": 51, + "elo": 1273, + "win_rate": 51.5, "rank": 26 }, { "arena": "models", "category": "gamedev", "elo": 1305, - "win_rate": 51, - "rank": 18 + "win_rate": 51.1, + "rank": 17 }, { "arena": "models", "category": "svg", - "elo": 1296, - "win_rate": 54.8, - "rank": 7 + "elo": 1293, + "win_rate": 54.5, + "rank": 10 }, { "arena": "models", "category": "uicomponent", - "elo": 1318, - "win_rate": 53.8, - "rank": 13 + "elo": 1313, + "win_rate": 53, + "rank": 15 }, { "arena": "models", "category": "website", - "elo": 1301, + "elo": 1299, "win_rate": 50, "rank": 15 } ], "artificial_analysis": { - "intelligence_index": 40.9, + "intelligence_index": 30.8, "coding_index": 76.3, "agentic_index": 40.2 } @@ -12495,15 +13319,30 @@ "links": { "details": "/api/v1/models/google/gemini-3.8-flash-20260902/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1075, - "win_rate": 32.8, + "elo": 1092, + "win_rate": 34.4, "rank": 32 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1198, + "win_rate": 54.7, + "rank": 6 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1236, + "win_rate": 58.3, + "rank": 3 + }, { "arena": "agents", "category": "fullstack", @@ -12521,90 +13360,97 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1236, + "elo": 1232, "win_rate": 54.4, - "rank": 7 + "rank": 9 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1220, + "win_rate": 54, + "rank": 11 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1174, - "win_rate": 39.9, - "rank": 19 + "elo": 1138, + "win_rate": 40.4, + "rank": 21 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1056, - "win_rate": 39.8, - "rank": 14 + "elo": 1070, + "win_rate": 42.2, + "rank": 21 }, { "arena": "agents", "category": "webapps", - "elo": 1238, - "win_rate": 46.7, - "rank": 14 + "elo": 1226, + "win_rate": 46.9, + "rank": 15 }, { "arena": "models", "category": "3d", - "elo": 1295, - "win_rate": 50, - "rank": 20 + "elo": 1291, + "win_rate": 49.8, + "rank": 21 }, { "arena": "models", "category": "asciiart", - "elo": 1262, - "win_rate": 51.1, + "elo": 1269, + "win_rate": 51.8, "rank": 13 }, { "arena": "models", "category": "codecategories", - "elo": 1304, + "elo": 1302, "win_rate": 50.4, "rank": 16 }, { "arena": "models", "category": "dataviz", - "elo": 1270, - "win_rate": 51, + "elo": 1273, + "win_rate": 51.5, "rank": 26 }, { "arena": "models", "category": "gamedev", "elo": 1305, - "win_rate": 51, - "rank": 18 + "win_rate": 51.1, + "rank": 17 }, { "arena": "models", "category": "svg", - "elo": 1296, - "win_rate": 54.8, - "rank": 7 + "elo": 1293, + "win_rate": 54.5, + "rank": 10 }, { "arena": "models", "category": "uicomponent", - "elo": 1318, - "win_rate": 53.8, - "rank": 13 + "elo": 1313, + "win_rate": 53, + "rank": 15 }, { "arena": "models", "category": "website", - "elo": 1301, + "elo": 1299, "win_rate": 50, "rank": 15 } ], "artificial_analysis": { - "intelligence_index": 40.9, + "intelligence_index": 30.8, "coding_index": 76.3, "agentic_index": 40.2 } @@ -12676,60 +13522,87 @@ "links": { "details": "/api/v1/models/google/gemini-4-argon-20261013/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1266, + "win_rate": 51.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1408, + "win_rate": 68.2, + "rank": 1 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1134, + "elo": 1200, "win_rate": 32.8, - "rank": 10 + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1389, - "win_rate": 64.7, - "rank": 7 + "elo": 1369, + "win_rate": 50.3, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1329, - "win_rate": 57.7, + "elo": 1327, + "win_rate": 53.9, "rank": 9 }, { "arena": "models", "category": "dataviz", - "elo": 1334, - "win_rate": 60.7, + "elo": 1335, + "win_rate": 61.5, "rank": 8 }, { "arena": "models", "category": "gamedev", - "elo": 1376, - "win_rate": 63.1, - "rank": 6 + "elo": 1367, + "win_rate": 54, + "rank": 7 + }, + { + "arena": "models", + "category": "svg", + "elo": 1327, + "win_rate": 60.5, + "rank": 2 }, { "arena": "models", "category": "uicomponent", - "elo": 1330, - "win_rate": 57.6, - "rank": 10 + "elo": 1332, + "win_rate": 57.9, + "rank": 12 }, { "arena": "models", "category": "website", - "elo": 1315, - "win_rate": 56.3, - "rank": 8 + "elo": 1316, + "win_rate": 55.4, + "rank": 7 } ], "artificial_analysis": { - "intelligence_index": 52.6, + "intelligence_index": 50.4, "coding_index": null, "agentic_index": null } @@ -12800,60 +13673,82 @@ "links": { "details": "/api/v1/models/google/gemini-4-argon-20261013/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1266, + "win_rate": 51.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1408, + "win_rate": 68.2, + "rank": 1 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1134, + "elo": 1200, "win_rate": 32.8, - "rank": 10 + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1389, - "win_rate": 64.7, - "rank": 7 + "elo": 1369, + "win_rate": 50.3, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1329, - "win_rate": 57.7, + "elo": 1327, + "win_rate": 53.9, "rank": 9 }, { "arena": "models", "category": "dataviz", - "elo": 1334, - "win_rate": 60.7, + "elo": 1335, + "win_rate": 61.5, "rank": 8 }, { "arena": "models", "category": "gamedev", - "elo": 1376, - "win_rate": 63.1, - "rank": 6 + "elo": 1367, + "win_rate": 54, + "rank": 7 + }, + { + "arena": "models", + "category": "svg", + "elo": 1327, + "win_rate": 60.5, + "rank": 2 }, { "arena": "models", "category": "uicomponent", - "elo": 1330, - "win_rate": 57.6, - "rank": 10 + "elo": 1332, + "win_rate": 57.9, + "rank": 12 }, { "arena": "models", "category": "website", - "elo": 1315, - "win_rate": 56.3, - "rank": 8 + "elo": 1316, + "win_rate": 55.4, + "rank": 7 } ], "artificial_analysis": { - "intelligence_index": 52.6, + "intelligence_index": 50.4, "coding_index": null, "agentic_index": null } @@ -12911,6 +13806,13 @@ "links": { "details": "/api/v1/models/google/gemini-nano-banana-2.1-20261006/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -12961,7 +13863,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/google/gemma-2-27b-it/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "google/gemma-3-12b-it", @@ -13012,10 +13920,16 @@ "links": { "details": "/api/v1/models/google/gemma-3-12b-it/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 3.8, + "intelligence_index": null, "coding_index": 5.8, "agentic_index": 0.1 } @@ -13077,10 +13991,16 @@ "links": { "details": "/api/v1/models/google/gemma-3-27b-it/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 4.9, + "intelligence_index": null, "coding_index": 10.1, "agentic_index": 0.1 } @@ -13102,13 +14022,12 @@ "instruct_type": "gemma" }, "pricing": { - "prompt": "0.00000004", - "completion": "0.00000005", - "input_cache_read": "0.00000002" + "prompt": "0.00000005", + "completion": "0.0000001" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 117964, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, @@ -13136,10 +14055,16 @@ "links": { "details": "/api/v1/models/google/gemma-3-4b-it/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 4.8, + "intelligence_index": null, "coding_index": 2.7, "agentic_index": null } @@ -13161,13 +14086,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.0000003", - "input_cache_read": "0.00000005" + "prompt": "0.000000072", + "completion": "0.000000217", + "input_cache_read": "0.000000036" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 235929, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, @@ -13176,6 +14101,7 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", @@ -13203,10 +14129,16 @@ "links": { "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 16.7, + "intelligence_index": null, "coding_index": 39.3, "agentic_index": 2.9 } @@ -13263,10 +14195,16 @@ "links": { "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 16.7, + "intelligence_index": null, "coding_index": 39.3, "agentic_index": 2.9 } @@ -13306,6 +14244,7 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", @@ -13336,10 +14275,16 @@ "links": { "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 14.7, + "intelligence_index": null, "coding_index": 43.4, "agentic_index": 4.2 } @@ -13399,10 +14344,16 @@ "links": { "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 14.7, + "intelligence_index": null, "coding_index": 43.4, "agentic_index": 4.2 } @@ -13457,7 +14408,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/google/lyria-3-clip-preview-20260330/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "google/lyria-3-pro-preview", @@ -13504,7 +14461,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/google/lyria-3-pro-preview-20260330/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "gryphe/mythomax-l2-13b", @@ -13555,68 +14518,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/gryphe/mythomax-l2-13b/endpoints" - } - }, - { - "id": "ibm-granite/granite-4.0-h-micro", - "canonical_slug": "ibm-granite/granite-4.0-h-micro", - "hugging_face_id": "ibm-granite/granite-4.0-h-micro", - "name": "IBM: Granite 4.0 Micro", - "created": 1760927695, - "description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...", - "context_length": 131000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000000017", - "completion": "0.000000112" - }, - "top_provider": { - "context_length": 131000, - "max_completion_tokens": 117900, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "temperature", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.1, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "ibm-granite/granite-4.2-8b", @@ -13676,10 +14584,16 @@ "links": { "details": "/api/v1/models/ibm-granite/granite-4.2-8b-20260831/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 11.1, + "intelligence_index": 5.1, "coding_index": 22.4, "agentic_index": 1.3 } @@ -13739,71 +14653,77 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-08", "links": { "details": "/api/v1/models/inception/mercury-2-20260304/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 983, - "win_rate": 21.9, - "rank": 115 + "elo": 974, + "win_rate": 21.1, + "rank": 118 }, { "arena": "models", "category": "asciiart", - "elo": 989, - "win_rate": 24.4, - "rank": 71 + "elo": 986, + "win_rate": 24.2, + "rank": 74 }, { "arena": "models", "category": "codecategories", - "elo": 1022, - "win_rate": 21.4, - "rank": 121 + "elo": 1019, + "win_rate": 21.2, + "rank": 125 }, { "arena": "models", "category": "dataviz", - "elo": 1009, - "win_rate": 22.3, - "rank": 115 + "elo": 1015, + "win_rate": 22.9, + "rank": 116 }, { "arena": "models", "category": "gamedev", - "elo": 985, - "win_rate": 18.9, - "rank": 125 + "elo": 979, + "win_rate": 18.4, + "rank": 126 }, { "arena": "models", "category": "svg", - "elo": 999, - "win_rate": 24.6, - "rank": 84 + "elo": 1001, + "win_rate": 24.8, + "rank": 90 }, { "arena": "models", "category": "uicomponent", - "elo": 998, + "elo": 993, "win_rate": 19.6, - "rank": 116 + "rank": 120 }, { "arena": "models", "category": "website", "elo": 1036, - "win_rate": 22.1, - "rank": 125 + "win_rate": 22.2, + "rank": 127 } ], "artificial_analysis": { - "intelligence_index": 10.8, + "intelligence_index": null, "coding_index": 31.1, "agentic_index": 1.6 } @@ -13856,18 +14776,16 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-08", "links": { "details": "/api/v1/models/inception/mercury-2.5-20260908/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 12.3, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -13916,46 +14834,59 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-08", "links": { "details": "/api/v1/models/inception/mercury-3-20261019/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1239, - "win_rate": 46.3, - "rank": 46 + "elo": 1229, + "win_rate": 45.4, + "rank": 52 }, { "arena": "models", "category": "dataviz", - "elo": 1207, - "win_rate": 45.6, - "rank": 55 + "elo": 1206, + "win_rate": 45, + "rank": 56 }, { "arena": "models", "category": "gamedev", - "elo": 1227, - "win_rate": 44.4, - "rank": 44 + "elo": 1216, + "win_rate": 44.2, + "rank": 49 + }, + { + "arena": "models", + "category": "svg", + "elo": 1175, + "win_rate": 42.8, + "rank": 41 }, { "arena": "models", "category": "uicomponent", - "elo": 1266, - "win_rate": 47.6, - "rank": 35 + "elo": 1232, + "win_rate": 45.5, + "rank": 48 }, { "arena": "models", "category": "website", - "elo": 1242, - "win_rate": 47.2, - "rank": 50 + "elo": 1231, + "win_rate": 45.7, + "rank": 54 } ] }, @@ -14019,10 +14950,16 @@ "links": { "details": "/api/v1/models/inclusionai/ling-3.0-flash-20260723/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 20.1, + "intelligence_index": null, "coding_index": 50.6, "agentic_index": 19.3 } @@ -14084,10 +15021,16 @@ "links": { "details": "/api/v1/models/inclusionai/ling-3.0-flash-vl-20260910/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 24.6, + "intelligence_index": null, "coding_index": 57, "agentic_index": 28.7 } @@ -14104,7 +15047,7 @@ "name": "inclusionAI: Ling 3.1 Flash", "created": 1790950024, "description": "Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.", - "context_length": 262144, + "context_length": 1000000, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -14118,8 +15061,8 @@ "input_cache_read": "0.000000015" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 235929, + "context_length": 1000000, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -14151,14 +15094,12 @@ "links": { "details": "/api/v1/models/inclusionai/ling-3.1-flash-20261002/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 41.1, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true @@ -14211,7 +15152,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/inference-net/schematron-v2-small-20260902/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "inference-net/schematron-v2-turbo", @@ -14260,6 +15207,88 @@ "expiration_date": null, "links": { "details": "/api/v1/models/inference-net/schematron-v2-turbo-20260902/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] + }, + { + "id": "liquid/lfm-2.5-2.6b", + "canonical_slug": "liquid/lfm-2.5-2.6b-20260811", + "hugging_face_id": "LiquidAI/LFM2.5-2.6B", + "name": "LiquidAI: LFM2.5-2.6B", + "created": 1786470519, + "description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...", + "context_length": 128000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000035", + "completion": "0.0000005", + "input_cache_read": "0.00000004" + }, + "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", + "top_p" + ], + "default_parameters": { + "temperature": 0.1, + "top_k": 50, + "repetition_penalty": 1.1 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/liquid/lfm-2.5-2.6b-20260811/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 7.7, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true } }, { @@ -14305,7 +15334,8 @@ "tool_choice", "tools", "top_k", - "top_logprobs" + "top_logprobs", + "top_p" ], "default_parameters": { "temperature": 0.1, @@ -14318,10 +15348,16 @@ "links": { "details": "/api/v1/models/liquid/lfm-2.5-2.6b-20260811/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 8.4, + "intelligence_index": null, "coding_index": 7.7, "agentic_index": null } @@ -14374,7 +15410,8 @@ "tool_choice", "tools", "top_k", - "top_logprobs" + "top_logprobs", + "top_p" ], "default_parameters": { "temperature": 0.1, @@ -14387,6 +15424,12 @@ "links": { "details": "/api/v1/models/liquid/lfm-2.5-24b-a2b-20261012/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -14439,7 +15482,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/mancer/weaver/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "meituan/longcat-2.0", @@ -14491,10 +15540,16 @@ "links": { "details": "/api/v1/models/meituan/longcat-2.0-20260720/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 19.1, + "intelligence_index": null, "coding_index": 45.3, "agentic_index": 14 } @@ -14521,18 +15576,66 @@ "instruct_type": "llama3" }, "pricing": { - "prompt": "0.0000004", - "completion": "0.0000004" + "prompt": "0.00000072", + "completion": "0.00000072" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 16384, + "max_completion_tokens": 8192, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] + }, + { + "id": "meta-llama/llama-3.1-8b-instruct", + "canonical_slug": "meta-llama/llama-3.1-8b-instruct", + "hugging_face_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", + "name": "Meta: Llama 3.1 8B Instruct", + "created": 1721692800, + "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000008", + "input_cache_read": "0.000000025" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 117964, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -14545,6 +15648,7 @@ "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -14552,24 +15656,82 @@ "knowledge_cutoff": "2023-12-31", "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints" + "details": "/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 6.6, - "coding_index": null, + "intelligence_index": null, + "coding_index": 5.4, "agentic_index": null } } }, { - "id": "meta-llama/llama-3.1-8b-instruct", - "canonical_slug": "meta-llama/llama-3.1-8b-instruct", - "hugging_face_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", - "name": "Meta: Llama 3.1 8B Instruct", - "created": 1721692800, - "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...", + "id": "meta-llama/llama-3.2-1b-instruct", + "canonical_slug": "meta-llama/llama-3.2-1b-instruct", + "hugging_face_id": "meta-llama/Llama-3.2-1B-Instruct", + "name": "Meta: Llama 3.2 1B Instruct", + "created": 1727222400, + "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...", + "context_length": 60000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.000000027", + "completion": "0.000000201" + }, + "top_provider": { + "context_length": 60000, + "max_completion_tokens": 54000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] + }, + { + "id": "meta-llama/llama-3.2-3b-instruct", + "canonical_slug": "meta-llama/llama-3.2-3b-instruct", + "hugging_face_id": "meta-llama/Llama-3.2-3B-Instruct", + "name": "Meta: Llama 3.2 3B Instruct", + "created": 1727222400, + "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", "context_length": 131072, "architecture": { "modality": "text->text", @@ -14579,184 +15741,67 @@ "instruct_type": "llama3" }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000008", - "input_cache_read": "0.000000025" + "prompt": "0.0000000509", + "completion": "0.000000335" + }, + "top_provider": { + "context_length": 80000, + "max_completion_tokens": 72000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] + }, + { + "id": "meta-llama/llama-3.3-70b-instruct", + "canonical_slug": "meta-llama/llama-3.3-70b-instruct", + "hugging_face_id": "meta-llama/Llama-3.3-70B-Instruct", + "name": "Meta: Llama 3.3 70B Instruct", + "created": 1733506137, + "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.00000032" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 117964, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "min_p", - "presence_penalty", - "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": "2023-12-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.9, - "coding_index": 5.4, - "agentic_index": null - } - } - }, - { - "id": "meta-llama/llama-3.2-1b-instruct", - "canonical_slug": "meta-llama/llama-3.2-1b-instruct", - "hugging_face_id": "meta-llama/Llama-3.2-1B-Instruct", - "name": "Meta: Llama 3.2 1B Instruct", - "created": 1727222400, - "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...", - "context_length": 60000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" - }, - "pricing": { - "prompt": "0.000000027", - "completion": "0.000000201" - }, - "top_provider": { - "context_length": 60000, - "max_completion_tokens": 54000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "seed", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-12-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 4.8, - "coding_index": null, - "agentic_index": null - } - } - }, - { - "id": "meta-llama/llama-3.2-3b-instruct", - "canonical_slug": "meta-llama/llama-3.2-3b-instruct", - "hugging_face_id": "meta-llama/Llama-3.2-3B-Instruct", - "name": "Meta: Llama 3.2 3B Instruct", - "created": 1727222400, - "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" - }, - "pricing": { - "prompt": "0.0000000509", - "completion": "0.000000335" - }, - "top_provider": { - "context_length": 80000, - "max_completion_tokens": 72000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-12-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.7, - "coding_index": null, - "agentic_index": null - } - } - }, - { - "id": "meta-llama/llama-3.3-70b-instruct", - "canonical_slug": "meta-llama/llama-3.3-70b-instruct", - "hugging_face_id": "meta-llama/Llama-3.3-70B-Instruct", - "name": "Meta: Llama 3.3 70B Instruct", - "created": 1733506137, - "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" - }, - "pricing": { - "prompt": "0.0000001", - "completion": "0.00000032" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, @@ -14786,10 +15831,16 @@ "links": { "details": "/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 7.7, + "intelligence_index": null, "coding_index": 11.9, "agentic_index": null } @@ -14846,53 +15897,59 @@ "links": { "details": "/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 901, + "elo": 898, "win_rate": 40.2, - "rank": 121 + "rank": 124 }, { "arena": "models", "category": "codecategories", - "elo": 880, + "elo": 878, "win_rate": 35.8, - "rank": 135 + "rank": 139 }, { "arena": "models", "category": "dataviz", "elo": 882, "win_rate": 38.4, - "rank": 130 + "rank": 131 }, { "arena": "models", "category": "gamedev", - "elo": 838, + "elo": 836, "win_rate": 33.7, - "rank": 139 + "rank": 140 }, { "arena": "models", "category": "uicomponent", - "elo": 899, + "elo": 894, "win_rate": 40.8, - "rank": 128 + "rank": 132 }, { "arena": "models", "category": "website", - "elo": 871, + "elo": 869, "win_rate": 34.4, - "rank": 140 + "rank": 142 } ], "artificial_analysis": { - "intelligence_index": 9.3, + "intelligence_index": null, "coding_index": 16.3, "agentic_index": 0.6 } @@ -14947,46 +16004,52 @@ "links": { "details": "/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 790, + "elo": 788, "win_rate": 26.6, - "rank": 138 + "rank": 142 }, { "arena": "models", "category": "dataviz", "elo": 896, "win_rate": 39.3, - "rank": 128 + "rank": 129 }, { "arena": "models", "category": "gamedev", "elo": 773, "win_rate": 27.4, - "rank": 140 + "rank": 141 }, { "arena": "models", "category": "uicomponent", - "elo": 768, + "elo": 762, "win_rate": 25.5, - "rank": 132 + "rank": 136 }, { "arena": "models", "category": "website", "elo": 750, "win_rate": 22.7, - "rank": 146 + "rank": 148 } ], "artificial_analysis": { - "intelligence_index": 6.5, + "intelligence_index": null, "coding_index": 8.2, "agentic_index": 0.5 } @@ -15036,7 +16099,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/meta-llama/llama-guard-4-12b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "meta/muse-glimmer-30b", @@ -15095,18 +16164,45 @@ "links": { "details": "/api/v1/models/meta/muse-glimmer-30b-20260810/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1151, + "win_rate": 34.8, + "rank": 86 + }, { "arena": "models", "category": "gamedev", - "elo": 1164, - "win_rate": 35.6, - "rank": 72 + "elo": 1110, + "win_rate": 30.4, + "rank": 94 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1204, + "win_rate": 40.2, + "rank": 59 + }, + { + "arena": "models", + "category": "website", + "elo": 1166, + "win_rate": 36.7, + "rank": 83 } ], "artificial_analysis": { - "intelligence_index": 17.5, + "intelligence_index": 6.3, "coding_index": 49, "agentic_index": 8.5 } @@ -15165,21 +16261,34 @@ "links": { "details": "/api/v1/models/meta/muse-spark-1.1-20260709/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1183, + "elo": 1128, "win_rate": 48.2, - "rank": 11 + "rank": 13 }, { "arena": "agents", "category": "androidnative", - "elo": 1178, - "win_rate": 47.7, - "rank": 17 + "elo": 1170, + "win_rate": 47, + "rank": 21 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1009, + "win_rate": 35.9, + "rank": 19 }, { "arena": "agents", @@ -15198,97 +16307,104 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1195, + "elo": 1091, "win_rate": 51.8, - "rank": 8 + "rank": 12 }, { "arena": "agents", "category": "mobileapps", "elo": 1175, - "win_rate": 46.1, - "rank": 23 + "win_rate": 46.3, + "rank": 25 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1174, + "win_rate": 50.7, + "rank": 17 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1155, - "win_rate": 44.1, - "rank": 21 + "elo": 1114, + "win_rate": 44.4, + "rank": 22 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1042, - "win_rate": 33.3, - "rank": 18 + "elo": 1069, + "win_rate": 38.6, + "rank": 22 }, { "arena": "agents", "category": "webapps", - "elo": 1207, - "win_rate": 49.1, - "rank": 21 + "elo": 1194, + "win_rate": 49, + "rank": 22 }, { "arena": "models", "category": "3d", - "elo": 1260, - "win_rate": 49, - "rank": 29 + "elo": 1257, + "win_rate": 48.9, + "rank": 31 }, { "arena": "models", "category": "asciiart", - "elo": 1271, - "win_rate": 55, - "rank": 10 + "elo": 1259, + "win_rate": 53, + "rank": 15 }, { "arena": "models", "category": "codecategories", - "elo": 1276, - "win_rate": 51.2, - "rank": 26 + "elo": 1274, + "win_rate": 51.1, + "rank": 28 }, { "arena": "models", "category": "dataviz", - "elo": 1268, - "win_rate": 50.2, - "rank": 27 + "elo": 1267, + "win_rate": 50.1, + "rank": 29 }, { "arena": "models", "category": "gamedev", "elo": 1269, - "win_rate": 48, + "win_rate": 48.1, "rank": 26 }, { "arena": "models", "category": "svg", - "elo": 1235, + "elo": 1230, "win_rate": 49, - "rank": 15 + "rank": 20 }, { "arena": "models", "category": "uicomponent", - "elo": 1289, - "win_rate": 51.1, - "rank": 24 + "elo": 1282, + "win_rate": 50.8, + "rank": 25 }, { "arena": "models", "category": "website", - "elo": 1270, + "elo": 1269, "win_rate": 51.3, - "rank": 29 + "rank": 30 } ], "artificial_analysis": { - "intelligence_index": 33.7, + "intelligence_index": null, "coding_index": 71.3, "agentic_index": 25.8 } @@ -15347,116 +16463,143 @@ "links": { "details": "/api/v1/models/meta/muse-spark-1.2-20260805/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1179, - "win_rate": 42.5, - "rank": 15 + "elo": 1129, + "win_rate": 42.9, + "rank": 12 }, { "arena": "agents", "category": "androidnative", "elo": 1221, - "win_rate": 53.1, + "win_rate": 53.2, "rank": 10 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1053, + "win_rate": 42.9, + "rank": 16 + }, { "arena": "agents", "category": "fullstack", "elo": 1210, "win_rate": 48, - "rank": 15 + "rank": 16 }, { "arena": "agents", "category": "htmlslides", - "elo": 1135, + "elo": 1031, "win_rate": 40, - "rank": 20 + "rank": 22 }, { "arena": "agents", "category": "mobileapps", - "elo": 1181, - "win_rate": 47.7, - "rank": 22 + "elo": 1184, + "win_rate": 48.1, + "rank": 24 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1111, + "win_rate": 37.1, + "rank": 25 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1195, - "win_rate": 48.5, - "rank": 15 + "elo": 1149, + "win_rate": 48.3, + "rank": 19 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1048, + "win_rate": 44.8, + "rank": 24 }, { "arena": "agents", "category": "webapps", - "elo": 1221, - "win_rate": 50.2, - "rank": 18 + "elo": 1207, + "win_rate": 49.8, + "rank": 19 }, { "arena": "models", "category": "3d", - "elo": 1302, - "win_rate": 51.8, - "rank": 19 + "elo": 1300, + "win_rate": 51.9, + "rank": 20 }, { "arena": "models", "category": "asciiart", - "elo": 1284, - "win_rate": 56.1, - "rank": 4 + "elo": 1280, + "win_rate": 55.2, + "rank": 7 }, { "arena": "models", "category": "codecategories", - "elo": 1313, - "win_rate": 52, + "elo": 1311, + "win_rate": 52.1, "rank": 12 }, { "arena": "models", "category": "dataviz", - "elo": 1334, - "win_rate": 57.6, - "rank": 9 + "elo": 1328, + "win_rate": 56.6, + "rank": 10 }, { "arena": "models", "category": "gamedev", - "elo": 1302, - "win_rate": 50.5, + "elo": 1300, + "win_rate": 50.4, "rank": 19 }, { "arena": "models", "category": "svg", - "elo": 1285, - "win_rate": 55.3, - "rank": 10 + "elo": 1278, + "win_rate": 54.3, + "rank": 13 }, { "arena": "models", "category": "uicomponent", - "elo": 1300, - "win_rate": 52, + "elo": 1302, + "win_rate": 52.2, "rank": 17 }, { "arena": "models", "category": "website", "elo": 1313, - "win_rate": 52.1, - "rank": 10 + "win_rate": 52.2, + "rank": 9 } ], "artificial_analysis": { - "intelligence_index": 39.6, + "intelligence_index": null, "coding_index": 72.2, "agentic_index": 43.2 } @@ -15515,6 +16658,12 @@ "links": { "details": "/api/v1/models/meta/muse-spark-1.2-contributor-20260805/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium", "low", "minimal"], @@ -15569,8 +16718,28 @@ "links": { "details": "/api/v1/models/meta/muse-spark-1.3-20260902/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1293, + "win_rate": 62, + "rank": 2 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1145, + "win_rate": 56.3, + "rank": 11 + }, { "arena": "agents", "category": "fullstack", @@ -15582,84 +16751,91 @@ "arena": "agents", "category": "mobileapps", "elo": 1219, - "win_rate": 48.3, - "rank": 13 + "win_rate": 50.2, + "rank": 14 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1149, + "win_rate": 46.1, + "rank": 20 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1240, + "elo": 1201, "win_rate": 51.4, "rank": 10 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1050, - "win_rate": 29.4, - "rank": 16 + "elo": 1107, + "win_rate": 31.2, + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1297, - "win_rate": 56.6, - "rank": 6 + "elo": 1284, + "win_rate": 55, + "rank": 7 }, { "arena": "models", "category": "3d", - "elo": 1396, + "elo": 1393, "win_rate": 63.5, - "rank": 5 + "rank": 7 }, { "arena": "models", "category": "asciiart", - "elo": 1280, - "win_rate": 53.6, - "rank": 6 + "elo": 1293, + "win_rate": 55, + "rank": 5 }, { "arena": "models", "category": "codecategories", - "elo": 1353, - "win_rate": 57.4, - "rank": 5 + "elo": 1350, + "win_rate": 56.9, + "rank": 7 }, { "arena": "models", "category": "dataviz", - "elo": 1343, - "win_rate": 58.1, + "elo": 1342, + "win_rate": 57.9, "rank": 6 }, { "arena": "models", "category": "gamedev", - "elo": 1344, + "elo": 1343, "win_rate": 56, "rank": 9 }, { "arena": "models", "category": "svg", - "elo": 1325, - "win_rate": 54.4, - "rank": 2 + "elo": 1322, + "win_rate": 55.2, + "rank": 4 }, { "arena": "models", "category": "uicomponent", - "elo": 1351, - "win_rate": 57.9, - "rank": 4 + "elo": 1347, + "win_rate": 57.8, + "rank": 5 }, { "arena": "models", "category": "website", "elo": 1356, - "win_rate": 58.2, + "win_rate": 58.1, "rank": 2 }, { @@ -15671,7 +16847,7 @@ } ], "artificial_analysis": { - "intelligence_index": 48.1, + "intelligence_index": 36.6, "coding_index": 75.8, "agentic_index": 55.5 } @@ -15730,6 +16906,12 @@ "links": { "details": "/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low", "minimal"], @@ -15791,23 +16973,55 @@ "links": { "details": "/api/v1/models/meta/muse-spark-open-20261015/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1270, + "win_rate": 48.7, + "rank": 25 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1303, + "win_rate": 51.3, + "rank": 15 + }, { "arena": "models", "category": "gamedev", - "elo": 1289, - "win_rate": 53, - "rank": 22 + "elo": 1276, + "win_rate": 51, + "rank": 23 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1327, + "win_rate": 53.2, + "rank": 13 }, { "arena": "models", "category": "website", - "elo": 1317, - "win_rate": 56.5, - "rank": 7 + "elo": 1303, + "win_rate": 50.9, + "rank": 14 } - ] + ], + "artificial_analysis": { + "intelligence_index": 24.9, + "coding_index": null, + "agentic_index": null + } }, "reasoning": { "mandatory": true, @@ -15863,58 +17077,90 @@ "links": { "details": "/api/v1/models/meta/muse-wonder-20261012/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1190, + "win_rate": 42.9, + "rank": 7 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1133, + "win_rate": 13.9, + "rank": 7 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1096, + "win_rate": 14.2, + "rank": 26 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1221, + "elo": 1288, "win_rate": 49.7, - "rank": 9 + "rank": 7 }, { "arena": "models", "category": "3d", - "elo": 1426, - "win_rate": 67.7, - "rank": 4 + "elo": 1441, + "win_rate": 60.2, + "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1371, - "win_rate": 63, - "rank": 2 + "elo": 1386, + "win_rate": 61.8, + "rank": 1 }, { "arena": "models", "category": "dataviz", - "elo": 1321, - "win_rate": 56.9, - "rank": 12 + "elo": 1303, + "win_rate": 55, + "rank": 13 }, { "arena": "models", "category": "gamedev", - "elo": 1379, - "win_rate": 63.1, - "rank": 5 + "elo": 1414, + "win_rate": 61.6, + "rank": 4 }, { "arena": "models", "category": "uicomponent", - "elo": 1376, - "win_rate": 62.5, + "elo": 1377, + "win_rate": 63.1, "rank": 2 }, { "arena": "models", "category": "website", - "elo": 1362, - "win_rate": 62.5, + "elo": 1370, + "win_rate": 62.7, "rank": 1 } - ] + ], + "artificial_analysis": { + "intelligence_index": 43.6, + "coding_index": null, + "agentic_index": null + } }, "reasoning": { "mandatory": true, @@ -15969,14 +17215,12 @@ "links": { "details": "/api/v1/models/microsoft/phi-4/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.9, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "minimax/minimax-01", @@ -16011,10 +17255,16 @@ }, "supported_voices": null, "knowledge_cutoff": "2024-03-31", - "expiration_date": null, + "expiration_date": "2026-11-05", "links": { "details": "/api/v1/models/minimax/minimax-01/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "minimax/minimax-m1", @@ -16067,14 +17317,12 @@ "links": { "details": "/api/v1/models/minimax/minimax-m1/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.7, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -16105,22 +17353,12 @@ }, "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": { @@ -16130,32 +17368,38 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-05", "links": { "details": "/api/v1/models/minimax/minimax-m2/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1098, + "elo": 1095, "win_rate": 48.3, - "rank": 90 + "rank": 92 }, { "arena": "models", "category": "codecategories", - "elo": 1135, + "elo": 1133, "win_rate": 48.1, - "rank": 95 + "rank": 99 }, { "arena": "models", "category": "dataviz", "elo": 1140, "win_rate": 50, - "rank": 86 + "rank": 87 }, { "arena": "models", @@ -16167,30 +17411,25 @@ { "arena": "models", "category": "svg", - "elo": 1100, + "elo": 1096, "win_rate": 55.3, - "rank": 60 + "rank": 66 }, { "arena": "models", "category": "uicomponent", - "elo": 1137, + "elo": 1131, "win_rate": 49.2, - "rank": 85 + "rank": 88 }, { "arena": "models", "category": "website", - "elo": 1143, + "elo": 1141, "win_rate": 48, - "rank": 97 + "rank": 99 } - ], - "artificial_analysis": { - "intelligence_index": 18.6, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true @@ -16230,10 +17469,16 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-05", "links": { "details": "/api/v1/models/minimax/minimax-m2-her-20260123/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "minimax/minimax-m2.1", @@ -16278,32 +17523,38 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-05", "links": { "details": "/api/v1/models/minimax/minimax-m2.1/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1165, + "elo": 1162, "win_rate": 57.5, - "rank": 62 + "rank": 65 }, { "arena": "models", "category": "codecategories", - "elo": 1190, + "elo": 1188, "win_rate": 55.3, - "rank": 61 + "rank": 64 }, { "arena": "models", "category": "dataviz", "elo": 1206, "win_rate": 57, - "rank": 56 + "rank": 57 }, { "arena": "models", @@ -16315,30 +17566,25 @@ { "arena": "models", "category": "svg", - "elo": 1132, + "elo": 1128, "win_rate": 55.4, - "rank": 53 + "rank": 59 }, { "arena": "models", "category": "uicomponent", - "elo": 1223, + "elo": 1218, "win_rate": 60.9, - "rank": 51 + "rank": 53 }, { "arena": "models", "category": "website", "elo": 1201, "win_rate": 55.4, - "rank": 63 + "rank": 64 } - ], - "artificial_analysis": { - "intelligence_index": 20.9, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true @@ -16405,63 +17651,64 @@ "links": { "details": "/api/v1/models/minimax/minimax-m2.5-20260211/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1170, + "elo": 1167, "win_rate": 57.6, - "rank": 60 + "rank": 62 }, { "arena": "models", "category": "codecategories", - "elo": 1207, + "elo": 1205, "win_rate": 56.8, - "rank": 57 + "rank": 60 }, { "arena": "models", "category": "dataviz", "elo": 1172, "win_rate": 51.2, - "rank": 70 + "rank": 72 }, { "arena": "models", "category": "gamedev", "elo": 1176, "win_rate": 55.5, - "rank": 64 + "rank": 65 }, { "arena": "models", "category": "svg", - "elo": 1150, + "elo": 1146, "win_rate": 54.5, - "rank": 44 + "rank": 50 }, { "arena": "models", "category": "uicomponent", - "elo": 1173, + "elo": 1167, "win_rate": 53.4, - "rank": 69 + "rank": 72 }, { "arena": "models", "category": "website", "elo": 1222, "win_rate": 57.5, - "rank": 58 + "rank": 59 } - ], - "artificial_analysis": { - "intelligence_index": 22.8, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true @@ -16521,71 +17768,77 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-11-05", "links": { "details": "/api/v1/models/minimax/minimax-m2.7-20260318/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1195, + "elo": 1191, "win_rate": 49.9, - "rank": 51 + "rank": 54 }, { "arena": "models", "category": "asciiart", - "elo": 1136, - "win_rate": 46.5, - "rank": 51 + "elo": 1133, + "win_rate": 46.2, + "rank": 54 }, { "arena": "models", "category": "codecategories", - "elo": 1233, - "win_rate": 50.9, - "rank": 49 + "elo": 1232, + "win_rate": 50.7, + "rank": 50 }, { "arena": "models", "category": "dataviz", "elo": 1233, - "win_rate": 52.4, - "rank": 45 + "win_rate": 52.3, + "rank": 46 }, { "arena": "models", "category": "gamedev", - "elo": 1209, - "win_rate": 49.5, + "elo": 1208, + "win_rate": 49.2, "rank": 52 }, { "arena": "models", "category": "svg", - "elo": 1137, - "win_rate": 47.3, - "rank": 52 + "elo": 1132, + "win_rate": 46.9, + "rank": 58 }, { "arena": "models", "category": "uicomponent", - "elo": 1210, + "elo": 1206, "win_rate": 48.5, - "rank": 55 + "rank": 58 }, { "arena": "models", "category": "website", - "elo": 1243, - "win_rate": 51.4, + "elo": 1241, + "win_rate": 51.3, "rank": 48 } ], "artificial_analysis": { - "intelligence_index": 22.8, + "intelligence_index": null, "coding_index": 52.6, "agentic_index": 15.3 } @@ -16655,22 +17908,42 @@ "links": { "details": "/api/v1/models/minimax/minimax-m3-20260531/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1158, - "win_rate": 44.2, - "rank": 19 + "elo": 1114, + "win_rate": 44.9, + "rank": 18 }, { "arena": "agents", "category": "androidnative", "elo": 1158, - "win_rate": 44.3, + "win_rate": 44.5, "rank": 24 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1072, + "win_rate": 47.8, + "rank": 15 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1223, + "win_rate": 56.1, + "rank": 4 + }, { "arena": "agents", "category": "fullstack", @@ -16681,97 +17954,104 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1180, + "elo": 1076, "win_rate": 46.7, - "rank": 12 + "rank": 14 }, { "arena": "agents", "category": "mobileapps", - "elo": 1169, - "win_rate": 45.8, - "rank": 25 + "elo": 1173, + "win_rate": 46.4, + "rank": 27 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1288, + "win_rate": 62.9, + "rank": 3 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1203, - "win_rate": 47, - "rank": 14 + "elo": 1163, + "win_rate": 47.5, + "rank": 16 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1052, - "win_rate": 46.8, - "rank": 15 + "elo": 1079, + "win_rate": 45.8, + "rank": 20 }, { "arena": "agents", "category": "webapps", - "elo": 1200, - "win_rate": 46.9, + "elo": 1193, + "win_rate": 47.5, "rank": 24 }, { "arena": "models", "category": "3d", - "elo": 1209, - "win_rate": 50.1, - "rank": 47 + "elo": 1205, + "win_rate": 50, + "rank": 49 }, { "arena": "models", "category": "asciiart", - "elo": 1161, - "win_rate": 46.4, - "rank": 36 + "elo": 1155, + "win_rate": 46.1, + "rank": 43 }, { "arena": "models", "category": "codecategories", - "elo": 1247, - "win_rate": 50.8, - "rank": 41 + "elo": 1245, + "win_rate": 50.6, + "rank": 43 }, { "arena": "models", "category": "dataviz", - "elo": 1236, - "win_rate": 51.4, - "rank": 41 + "elo": 1234, + "win_rate": 51.2, + "rank": 45 }, { "arena": "models", "category": "gamedev", "elo": 1211, - "win_rate": 45.7, + "win_rate": 45.6, "rank": 50 }, { "arena": "models", "category": "svg", - "elo": 1162, - "win_rate": 45.2, - "rank": 39 + "elo": 1157, + "win_rate": 44.6, + "rank": 46 }, { "arena": "models", "category": "uicomponent", - "elo": 1245, - "win_rate": 50.6, - "rank": 43 + "elo": 1241, + "win_rate": 50.5, + "rank": 44 }, { "arena": "models", "category": "website", - "elo": 1257, - "win_rate": 51.7, - "rank": 40 + "elo": 1256, + "win_rate": 51.5, + "rank": 41 } ], "artificial_analysis": { - "intelligence_index": 29.2, + "intelligence_index": 18.9, "coding_index": 58.6, "agentic_index": 29.5 } @@ -16781,13 +18061,13 @@ } }, { - "id": "minimax/minimax-m3.1-flash:free", + "id": "minimax/minimax-m3.1-flash", "canonical_slug": "minimax/minimax-m3.1-flash-20261019", - "hugging_face_id": null, - "name": "MiniMax: MiniMax M3.1 Flash (free)", + "hugging_face_id": "MiniMaxAI/MiniMax-M3.1-Flash", + "name": "MiniMax: MiniMax M3.1 Flash", "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, + "context_length": 1048576, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -16796,24 +18076,52 @@ "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000015", + "overrides": [ + { + "utc_start": 1500, + "utc_end": 100, + "prompt": "0.000000075", + "completion": "0.0000003", + "input_cache_read": "0.0000000075" + }, + { + "utc_start": 100, + "utc_end": 1500, + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000015" + } + ] }, "top_provider": { - "context_length": 1000000, + "context_length": 1048576, "max_completion_tokens": 524288, "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": {}, @@ -16823,10 +18131,16 @@ "links": { "details": "/api/v1/models/minimax/minimax-m3.1-flash-20261019/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 42.7, + "intelligence_index": 29.1, "coding_index": null, "agentic_index": null } @@ -16886,145 +18200,55 @@ "links": { "details": "/api/v1/models/mistralai/codestral-2508/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1007, - "win_rate": 38.5, - "rank": 124 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1017, - "win_rate": 41.1, - "rank": 114 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 968, - "win_rate": 36.3, - "rank": 128 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1017, - "win_rate": 46.7, - "rank": 113 - }, - { - "arena": "models", - "category": "website", - "elo": 1013, - "win_rate": 37.8, - "rank": 129 - }, - { - "arena": "models", - "category": "3d", - "elo": 1020, - "win_rate": 45.4, - "rank": 109 - } - ] - } - }, - { - "id": "mistralai/codestral-2508:batch", - "canonical_slug": "mistralai/codestral-2508", - "hugging_face_id": "", - "name": "Mistral: Codestral 2508 (batch)", - "created": 1754079630, - "description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)", - "context_length": 256000, - "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], - "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000015", - "completion": "0.00000045", - "input_cache_read": "0.000000015" - }, - "top_provider": { - "context_length": 256000, - "max_completion_tokens": 204800, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "prediction", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": { - "temperature": 0.3 - }, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/mistralai/codestral-2508/endpoints" - }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1007, + "elo": 1005, "win_rate": 38.5, - "rank": 124 + "rank": 128 }, { "arena": "models", "category": "dataviz", "elo": 1017, "win_rate": 41.1, - "rank": 114 + "rank": 115 }, { "arena": "models", "category": "gamedev", - "elo": 968, + "elo": 966, "win_rate": 36.3, - "rank": 128 + "rank": 129 }, { "arena": "models", "category": "uicomponent", - "elo": 1017, + "elo": 1012, "win_rate": 46.7, - "rank": 113 + "rank": 117 }, { "arena": "models", "category": "website", - "elo": 1013, + "elo": 1011, "win_rate": 37.8, - "rank": 129 + "rank": 131 }, { "arena": "models", "category": "3d", - "elo": 1020, + "elo": 1017, "win_rate": 45.4, - "rank": 109 + "rank": 112 } ] } @@ -17079,10 +18303,16 @@ "links": { "details": "/api/v1/models/mistralai/devstral-2512/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 8.6, + "intelligence_index": null, "coding_index": 31.3, "agentic_index": 2.3 } @@ -17138,39 +18368,45 @@ "links": { "details": "/api/v1/models/mistralai/ministral-14b-2512/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 990, + "elo": 987, "win_rate": 39.6, - "rank": 113 + "rank": 116 }, { "arena": "models", "category": "codecategories", - "elo": 1065, + "elo": 1063, "win_rate": 44, - "rank": 112 + "rank": 116 }, { "arena": "models", "category": "gamedev", "elo": 1038, "win_rate": 43.6, - "rank": 116 + "rank": 117 }, { "arena": "models", "category": "website", "elo": 1081, "win_rate": 44.8, - "rank": 114 + "rank": 116 } ], "artificial_analysis": { - "intelligence_index": 6, + "intelligence_index": null, "coding_index": 14.4, "agentic_index": 1.1 } @@ -17226,39 +18462,45 @@ "links": { "details": "/api/v1/models/mistralai/ministral-3b-2512/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 963, + "elo": 960, "win_rate": 35.9, - "rank": 118 + "rank": 121 }, { "arena": "models", "category": "codecategories", - "elo": 1010, + "elo": 1008, "win_rate": 37.3, - "rank": 123 + "rank": 127 }, { "arena": "models", "category": "gamedev", - "elo": 949, + "elo": 947, "win_rate": 33, - "rank": 132 + "rank": 133 }, { "arena": "models", "category": "website", - "elo": 1028, + "elo": 1026, "win_rate": 38.2, - "rank": 127 + "rank": 129 } ], "artificial_analysis": { - "intelligence_index": 4.8, + "intelligence_index": null, "coding_index": 4.8, "agentic_index": 0.8 } @@ -17314,127 +18556,45 @@ "links": { "details": "/api/v1/models/mistralai/ministral-8b-2512/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1032, - "win_rate": 46.2, - "rank": 108 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1053, - "win_rate": 42.9, - "rank": 114 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 990, - "win_rate": 38.7, - "rank": 124 - }, - { - "arena": "models", - "category": "website", - "elo": 1065, - "win_rate": 42.9, - "rank": 116 - } - ], - "artificial_analysis": { - "intelligence_index": 5.5, - "coding_index": 9.7, - "agentic_index": 0.6 - } - } - }, - { - "id": "mistralai/ministral-8b-2512:batch", - "canonical_slug": "mistralai/ministral-8b-2512", - "hugging_face_id": "mistralai/Ministral-3-8B-Instruct-2512", - "name": "Mistral: Ministral 3 8B 2512 (batch)", - "created": 1764681654, - "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", - "context_length": 262144, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000000075", - "completion": "0.000000075", - "input_cache_read": "0.0000000075" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 209715, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": { - "temperature": 0.3, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/mistralai/ministral-8b-2512/endpoints" - }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1032, + "elo": 1029, "win_rate": 46.2, - "rank": 108 + "rank": 111 }, { "arena": "models", "category": "codecategories", - "elo": 1053, + "elo": 1051, "win_rate": 42.9, - "rank": 114 + "rank": 118 }, { "arena": "models", "category": "gamedev", "elo": 990, "win_rate": 38.7, - "rank": 124 + "rank": 125 }, { "arena": "models", "category": "website", - "elo": 1065, + "elo": 1063, "win_rate": 42.9, - "rank": 116 + "rank": 118 } ], "artificial_analysis": { - "intelligence_index": 5.5, + "intelligence_index": null, "coding_index": 9.7, "agentic_index": 0.6 } @@ -17488,14 +18648,12 @@ "links": { "details": "/api/v1/models/mistralai/mistral-large/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.8, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/mistral-large-2407", @@ -17545,14 +18703,12 @@ "links": { "details": "/api/v1/models/mistralai/mistral-large-2407/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.6, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/mistral-large-2512", @@ -17604,151 +18760,41 @@ "links": { "details": "/api/v1/models/mistralai/mistral-large-2512/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1099, - "win_rate": 46.9, - "rank": 89 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1069, - "win_rate": 40.3, - "rank": 66 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1142, - "win_rate": 47.6, - "rank": 92 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1136, - "win_rate": 45.7, - "rank": 87 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1080, - "win_rate": 41.5, - "rank": 105 - }, - { - "arena": "models", - "category": "svg", - "elo": 993, - "win_rate": 38, - "rank": 85 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1102, - "win_rate": 43, - "rank": 94 - }, - { - "arena": "models", - "category": "website", - "elo": 1162, - "win_rate": 49.5, - "rank": 87 - } - ], - "artificial_analysis": { - "intelligence_index": 9.3, - "coding_index": 20.1, - "agentic_index": 1 - } - } - }, - { - "id": "mistralai/mistral-large-2512:batch", - "canonical_slug": "mistralai/mistral-large-2512", - "hugging_face_id": "", - "name": "Mistral: Mistral Large 3 2512 (batch)", - "created": 1764624472, - "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", - "context_length": 262144, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000025", - "completion": "0.00000075", - "input_cache_read": "0.000000025" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 209715, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": { - "temperature": 0.0645, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/mistralai/mistral-large-2512/endpoints" - }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1099, + "elo": 1096, "win_rate": 46.9, - "rank": 89 + "rank": 91 }, { "arena": "models", "category": "asciiart", - "elo": 1069, + "elo": 1066, "win_rate": 40.3, - "rank": 66 + "rank": 69 }, { "arena": "models", "category": "codecategories", - "elo": 1142, + "elo": 1140, "win_rate": 47.6, - "rank": 92 + "rank": 95 }, { "arena": "models", "category": "dataviz", "elo": 1136, "win_rate": 45.7, - "rank": 87 + "rank": 88 }, { "arena": "models", @@ -17760,16 +18806,16 @@ { "arena": "models", "category": "svg", - "elo": 993, + "elo": 989, "win_rate": 38, - "rank": 85 + "rank": 91 }, { "arena": "models", "category": "uicomponent", - "elo": 1102, + "elo": 1097, "win_rate": 43, - "rank": 94 + "rank": 97 }, { "arena": "models", @@ -17780,7 +18826,7 @@ } ], "artificial_analysis": { - "intelligence_index": 9.3, + "intelligence_index": null, "coding_index": 20.1, "agentic_index": 1 } @@ -17789,7 +18835,7 @@ { "id": "mistralai/mistral-large-4-0", "canonical_slug": "mistralai/mistral-large-4-0-20261006", - "hugging_face_id": null, + "hugging_face_id": "mistralai/Mistral-Large-4-1T-A52B", "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 1M-token context window with up...", @@ -17802,9 +18848,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000136", - "completion": "0.00000418", - "input_cache_read": "0.00000014" + "prompt": "0.0000007", + "completion": "0.0000021", + "input_cache_read": "0.00000007" }, "top_provider": { "context_length": 1048576, @@ -17837,67 +18883,73 @@ "links": { "details": "/api/v1/models/mistralai/mistral-large-4-0-20261006/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1253, - "win_rate": 45, - "rank": 32 + "elo": 1250, + "win_rate": 45.2, + "rank": 34 }, { "arena": "models", "category": "asciiart", - "elo": 1202, + "elo": 1206, "win_rate": 43.5, - "rank": 24 + "rank": 25 }, { "arena": "models", "category": "codecategories", - "elo": 1259, + "elo": 1258, "win_rate": 46.6, - "rank": 38 + "rank": 40 }, { "arena": "models", "category": "dataviz", "elo": 1275, "win_rate": 51, - "rank": 24 + "rank": 25 }, { "arena": "models", "category": "gamedev", - "elo": 1226, + "elo": 1225, "win_rate": 42.2, "rank": 45 }, { "arena": "models", "category": "svg", - "elo": 1233, + "elo": 1231, "win_rate": 45.3, - "rank": 17 + "rank": 19 }, { "arena": "models", "category": "uicomponent", - "elo": 1275, - "win_rate": 47.8, - "rank": 30 + "elo": 1269, + "win_rate": 47.6, + "rank": 31 }, { "arena": "models", "category": "website", - "elo": 1258, - "win_rate": 47.2, - "rank": 39 + "elo": 1256, + "win_rate": 47.3, + "rank": 42 } ], "artificial_analysis": { - "intelligence_index": 38.4, + "intelligence_index": 26.1, "coding_index": null, "agentic_index": null } @@ -17957,56 +19009,57 @@ "links": { "details": "/api/v1/models/mistralai/mistral-medium-3/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1084, + "elo": 1081, "win_rate": 54.7, - "rank": 92 + "rank": 94 }, { "arena": "models", "category": "codecategories", - "elo": 1069, + "elo": 1067, "win_rate": 48.1, - "rank": 110 + "rank": 114 }, { "arena": "models", "category": "dataviz", "elo": 1034, "win_rate": 46, - "rank": 112 + "rank": 113 }, { "arena": "models", "category": "gamedev", - "elo": 1018, + "elo": 1016, "win_rate": 45.2, - "rank": 120 + "rank": 121 }, { "arena": "models", "category": "uicomponent", - "elo": 1025, + "elo": 1019, "win_rate": 49.6, - "rank": 112 + "rank": 116 }, { "arena": "models", "category": "website", - "elo": 1079, + "elo": 1077, "win_rate": 47.6, - "rank": 115 + "rank": 117 } - ], - "artificial_analysis": { - "intelligence_index": 9, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -18064,10 +19117,16 @@ "links": { "details": "/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 14.2, + "intelligence_index": null, "coding_index": 46.9, "agentic_index": 7 } @@ -18133,10 +19192,11 @@ "links": { "details": "/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 14.2, + "intelligence_index": null, "coding_index": 46.9, "agentic_index": 7 } @@ -18195,181 +19255,73 @@ "links": { "details": "/api/v1/models/mistralai/mistral-medium-3.1/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1081, - "win_rate": 44.6, - "rank": 95 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 997, - "win_rate": 30.8, - "rank": 70 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1120, - "win_rate": 45.1, - "rank": 96 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1144, - "win_rate": 47.2, - "rank": 83 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1074, - "win_rate": 40.8, - "rank": 107 - }, - { - "arena": "models", - "category": "svg", - "elo": 993, - "win_rate": 38.2, - "rank": 86 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1100, - "win_rate": 43.6, - "rank": 96 - }, - { - "arena": "models", - "category": "website", - "elo": 1133, - "win_rate": 46, - "rank": 99 - } - ], - "artificial_analysis": { - "intelligence_index": 9.2, - "coding_index": 20.5, - "agentic_index": 1.9 - } - } - }, - { - "id": "mistralai/mistral-medium-3.1:batch", - "canonical_slug": "mistralai/mistral-medium-3.1", - "hugging_face_id": "", - "name": "Mistral: Mistral Medium 3.1 (batch)", - "created": 1755095639, - "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...", - "context_length": 131072, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000002", - "completion": "0.000001", - "input_cache_read": "0.00000002" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 104857, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": { - "temperature": 0.3 - }, - "supported_voices": null, - "knowledge_cutoff": "2025-06-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/mistralai/mistral-medium-3.1/endpoints" - }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1081, + "elo": 1078, "win_rate": 44.6, - "rank": 95 + "rank": 99 }, { "arena": "models", "category": "asciiart", - "elo": 997, + "elo": 995, "win_rate": 30.8, - "rank": 70 + "rank": 73 }, { "arena": "models", "category": "codecategories", - "elo": 1120, + "elo": 1118, "win_rate": 45.1, - "rank": 96 + "rank": 100 }, { "arena": "models", "category": "dataviz", "elo": 1144, "win_rate": 47.2, - "rank": 83 + "rank": 84 }, { "arena": "models", "category": "gamedev", "elo": 1074, "win_rate": 40.8, - "rank": 107 + "rank": 108 }, { "arena": "models", "category": "svg", - "elo": 993, + "elo": 989, "win_rate": 38.2, - "rank": 86 + "rank": 92 }, { "arena": "models", "category": "uicomponent", - "elo": 1100, + "elo": 1094, "win_rate": 43.6, - "rank": 96 + "rank": 99 }, { "arena": "models", "category": "website", - "elo": 1133, + "elo": 1131, "win_rate": 46, - "rank": 99 + "rank": 101 } ], "artificial_analysis": { - "intelligence_index": 9.2, + "intelligence_index": null, "coding_index": 20.5, "agentic_index": 1.9 } @@ -18427,7 +19379,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/mistralai/mistral-nemo/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/mistral-saba", @@ -18477,14 +19435,12 @@ "links": { "details": "/api/v1/models/mistralai/mistral-saba-2502/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.5, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/mistral-small-24b-instruct-2501", @@ -18537,14 +19493,12 @@ "links": { "details": "/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/mistral-small-2603", @@ -18602,81 +19556,16 @@ "links": { "details": "/api/v1/models/mistralai/mistral-small-2603/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.3, - "coding_index": 26.6, - "agentic_index": 0.8 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": false, - "supported_efforts": ["high", "none"], - "default_effort": "high" - } - }, - { - "id": "mistralai/mistral-small-2603:batch", - "canonical_slug": "mistralai/mistral-small-2603", - "hugging_face_id": "mistralai/Mistral-Small-4-119B-2603", - "name": "Mistral: Mistral Small 4 (batch)", - "created": 1773695685, - "description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...", - "context_length": 262144, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000000075", - "completion": "0.0000003", - "input_cache_read": "0.0000000075" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 209715, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "reasoning_effort", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "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/mistralai/mistral-small-2603/endpoints" - }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 11.3, + "intelligence_index": 4.3, "coding_index": 26.6, "agentic_index": 0.8 } @@ -18739,7 +19628,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/mistral-small-3.2-24b-instruct", @@ -18757,11 +19652,11 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009375", - "completion": "0.00000025" + "prompt": "0.000000075", + "completion": "0.0000002" }, "top_provider": { - "context_length": 256000, + "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": false }, @@ -18794,42 +19689,48 @@ "links": { "details": "/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 907, + "elo": 905, "win_rate": 39.8, - "rank": 134 + "rank": 138 }, { "arena": "models", "category": "dataviz", "elo": 929, "win_rate": 43.3, - "rank": 125 + "rank": 126 }, { "arena": "models", "category": "gamedev", - "elo": 889, + "elo": 887, "win_rate": 39.4, - "rank": 137 + "rank": 138 }, { "arena": "models", "category": "uicomponent", - "elo": 907, + "elo": 902, "win_rate": 40.5, - "rank": 127 + "rank": 131 }, { "arena": "models", "category": "website", - "elo": 896, + "elo": 894, "win_rate": 38.3, - "rank": 139 + "rank": 141 } ] } @@ -18882,14 +19783,12 @@ "links": { "details": "/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "mistralai/voxtral-small-24b-2507", @@ -18941,7 +19840,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "moondream/moondream3-preview", @@ -18986,6 +19891,12 @@ "links": { "details": "/api/v1/models/moondream/moondream3-preview-20261013/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": false @@ -19034,6 +19945,12 @@ "links": { "details": "/api/v1/models/moondream/moondream3.1-9b-a2b-20261013/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": false @@ -19084,49 +20001,50 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k2/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1034, + "elo": 1032, "win_rate": 51.7, - "rank": 117 + "rank": 121 }, { "arena": "models", "category": "dataviz", "elo": 1018, "win_rate": 49.4, - "rank": 113 + "rank": 114 }, { "arena": "models", "category": "gamedev", "elo": 974, "win_rate": 46.4, - "rank": 126 + "rank": 127 }, { "arena": "models", "category": "uicomponent", - "elo": 1030, + "elo": 1025, "win_rate": 55.1, - "rank": 110 + "rank": 114 }, { "arena": "models", "category": "website", "elo": 1050, "win_rate": 53.1, - "rank": 121 + "rank": 123 } - ], - "artificial_analysis": { - "intelligence_index": 12.7, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -19176,28 +20094,29 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k2-0905/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1098, + "elo": 1096, "win_rate": 48.5, - "rank": 105 + "rank": 109 }, { "arena": "models", "category": "website", "elo": 1107, "win_rate": 48.3, - "rank": 108 + "rank": 110 } - ], - "artificial_analysis": { - "intelligence_index": 15.3, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -19229,7 +20148,6 @@ "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logprobs", "max_tokens", "presence_penalty", "reasoning", @@ -19242,7 +20160,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -19259,19 +20176,25 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "website", - "elo": 1113, + "elo": 1111, "win_rate": 48.8, - "rank": 106 + "rank": 108 } ], "artificial_analysis": { - "intelligence_index": 22, - "coding_index": null, + "intelligence_index": null, + "coding_index": 21, "agentic_index": null } }, @@ -19341,14 +20264,20 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k2.5-0127/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1118, + "elo": 1114, "win_rate": 57.8, - "rank": 27 + "rank": 30 }, { "arena": "agents", @@ -19369,74 +20298,74 @@ "category": "mobileapps", "elo": 1147, "win_rate": 54.7, - "rank": 30 + "rank": 32 }, { "arena": "agents", "category": "webapps", - "elo": 1136, + "elo": 1122, "win_rate": 51.6, - "rank": 32 + "rank": 33 }, { "arena": "models", "category": "3d", - "elo": 1205, + "elo": 1202, "win_rate": 53.1, - "rank": 48 + "rank": 50 }, { "arena": "models", "category": "asciiart", - "elo": 1166, - "win_rate": 46.4, - "rank": 33 + "elo": 1163, + "win_rate": 46.5, + "rank": 36 }, { "arena": "models", "category": "codecategories", - "elo": 1236, + "elo": 1234, "win_rate": 54.1, - "rank": 47 + "rank": 48 }, { "arena": "models", "category": "dataviz", "elo": 1219, "win_rate": 51.3, - "rank": 52 + "rank": 53 }, { "arena": "models", "category": "gamedev", - "elo": 1207, + "elo": 1205, "win_rate": 53.4, - "rank": 54 + "rank": 55 }, { "arena": "models", "category": "svg", - "elo": 1150, + "elo": 1146, "win_rate": 48.4, - "rank": 45 + "rank": 52 }, { "arena": "models", "category": "uicomponent", - "elo": 1237, + "elo": 1231, "win_rate": 53.6, - "rank": 47 + "rank": 49 }, { "arena": "models", "category": "website", - "elo": 1248, + "elo": 1247, "win_rate": 55.2, "rank": 45 } ], "artificial_analysis": { - "intelligence_index": 23.5, + "intelligence_index": null, "coding_index": 46.8, "agentic_index": null } @@ -19508,14 +20437,20 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1141, + "elo": 1088, "win_rate": 47.5, - "rank": 20 + "rank": 21 }, { "arena": "agents", @@ -19548,9 +20483,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1161, + "elo": 1158, "win_rate": 49.2, - "rank": 22 + "rank": 23 }, { "arena": "agents", @@ -19569,16 +20504,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1185, + "elo": 1081, "win_rate": 52.3, - "rank": 10 + "rank": 13 }, { "arena": "agents", "category": "mobileapps", - "elo": 1156, + "elo": 1154, "win_rate": 47.6, - "rank": 28 + "rank": 31 }, { "arena": "agents", @@ -19592,81 +20527,81 @@ "category": "python-pptxslides", "elo": 1180, "win_rate": 42.1, - "rank": 18 + "rank": 13 }, { "arena": "agents", "category": "spreadsheet", "elo": 1276, "win_rate": 54.8, - "rank": 5 + "rank": 8 }, { "arena": "agents", "category": "webapps", "elo": 1268, "win_rate": 59.3, - "rank": 9 + "rank": 10 }, { "arena": "models", "category": "3d", - "elo": 1268, + "elo": 1264, "win_rate": 57.6, - "rank": 26 + "rank": 27 }, { "arena": "models", "category": "asciiart", - "elo": 1165, + "elo": 1162, "win_rate": 47.5, - "rank": 35 + "rank": 38 }, { "arena": "models", "category": "codecategories", - "elo": 1272, + "elo": 1270, "win_rate": 54.8, - "rank": 29 + "rank": 32 }, { "arena": "models", "category": "dataviz", "elo": 1249, "win_rate": 52, - "rank": 35 + "rank": 37 }, { "arena": "models", "category": "gamedev", - "elo": 1251, - "win_rate": 54.9, - "rank": 37 + "elo": 1249, + "win_rate": 54.8, + "rank": 39 }, { "arena": "models", "category": "svg", - "elo": 1182, + "elo": 1178, "win_rate": 51.2, - "rank": 32 + "rank": 39 }, { "arena": "models", "category": "uicomponent", - "elo": 1266, + "elo": 1261, "win_rate": 55.6, - "rank": 34 + "rank": 36 }, { "arena": "models", "category": "website", - "elo": 1269, + "elo": 1268, "win_rate": 54.2, - "rank": 30 + "rank": 31 } ], "artificial_analysis": { - "intelligence_index": 27, + "intelligence_index": null, "coding_index": 61.8, "agentic_index": 20.5 } @@ -19692,9 +20627,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000006712", - "completion": "0.00000335", - "input_cache_read": "0.00000018" + "prompt": "0.0000006", + "completion": "0.0000035", + "input_cache_read": "0.00000015" }, "top_provider": { "context_length": 262144, @@ -19738,21 +20673,27 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1130, + "elo": 1078, "win_rate": 43, - "rank": 21 + "rank": 22 }, { "arena": "agents", "category": "androidnative", - "elo": 1137, + "elo": 1136, "win_rate": 46, - "rank": 26 + "rank": 28 }, { "arena": "agents", @@ -19771,90 +20712,90 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1202, + "elo": 1097, "win_rate": 53.6, - "rank": 7 + "rank": 11 }, { "arena": "agents", "category": "mobileapps", - "elo": 1143, + "elo": 1141, "win_rate": 46.2, - "rank": 31 + "rank": 34 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1152, + "elo": 1110, "win_rate": 44.6, "rank": 23 }, { "arena": "agents", "category": "webapps", - "elo": 1176, + "elo": 1163, "win_rate": 46.9, - "rank": 28 + "rank": 29 }, { "arena": "models", "category": "3d", - "elo": 1241, - "win_rate": 50.3, - "rank": 37 + "elo": 1237, + "win_rate": 50.2, + "rank": 39 }, { "arena": "models", "category": "asciiart", - "elo": 1196, - "win_rate": 48.3, - "rank": 27 + "elo": 1190, + "win_rate": 48, + "rank": 30 }, { "arena": "models", "category": "codecategories", - "elo": 1253, - "win_rate": 49.9, - "rank": 40 + "elo": 1251, + "win_rate": 49.8, + "rank": 42 }, { "arena": "models", "category": "dataviz", - "elo": 1227, - "win_rate": 48.7, - "rank": 48 + "elo": 1224, + "win_rate": 48.3, + "rank": 50 }, { "arena": "models", "category": "gamedev", "elo": 1220, - "win_rate": 47, - "rank": 48 + "win_rate": 46.7, + "rank": 47 }, { "arena": "models", "category": "svg", - "elo": 1177, - "win_rate": 44.4, - "rank": 36 + "elo": 1172, + "win_rate": 44, + "rank": 42 }, { "arena": "models", "category": "uicomponent", - "elo": 1259, - "win_rate": 50.6, - "rank": 39 + "elo": 1254, + "win_rate": 50.5, + "rank": 40 }, { "arena": "models", "category": "website", - "elo": 1264, - "win_rate": 51.3, - "rank": 35 + "elo": 1262, + "win_rate": 51.1, + "rank": 36 } ], "artificial_analysis": { - "intelligence_index": 25.8, + "intelligence_index": null, "coding_index": 60.8, "agentic_index": 21 } @@ -19880,9 +20821,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000239", - "completion": "0.000011936", - "input_cache_read": "0.00000021" + "prompt": "0.000000192", + "completion": "0.000016", + "input_cache_read": "0.000000182" }, "top_provider": { "context_length": 1048576, @@ -19895,8 +20836,10 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", @@ -19926,27 +20869,40 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k3-20260715/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1252, - "win_rate": 54.9, - "rank": 3 + "elo": 1202, + "win_rate": 53.8, + "rank": 4 }, { "arena": "agents", "category": "androidnative", - "elo": 1251, - "win_rate": 55.9, + "elo": 1255, + "win_rate": 56.7, "rank": 5 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1181, + "win_rate": 45.6, + "rank": 8 + }, { "arena": "agents", "category": "fullstack", "elo": 1315, - "win_rate": 61.8, + "win_rate": 61.6, "rank": 2 }, { @@ -19959,92 +20915,99 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1255, - "win_rate": 59.2, - "rank": 2 + "elo": 1153, + "win_rate": 55.6, + "rank": 5 }, { "arena": "agents", "category": "mobileapps", - "elo": 1269, - "win_rate": 57.5, - "rank": 3 + "elo": 1264, + "win_rate": 57.2, + "rank": 6 }, { "arena": "agents", - "category": "python-pptxslides", - "elo": 1270, - "win_rate": 58.9, + "category": "pdf", + "elo": 1283, + "win_rate": 64.5, "rank": 4 }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1219, + "win_rate": 54.8, + "rank": 6 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1057, - "win_rate": 33.1, - "rank": 13 + "elo": 1120, + "win_rate": 32, + "rank": 16 }, { "arena": "agents", "category": "webapps", - "elo": 1295, + "elo": 1284, "win_rate": 59.3, - "rank": 7 + "rank": 6 }, { "arena": "models", "category": "3d", - "elo": 1388, - "win_rate": 67.2, + "elo": 1381, + "win_rate": 64.2, "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1360, - "win_rate": 62.3, - "rank": 4 + "elo": 1353, + "win_rate": 60, + "rank": 5 }, { "arena": "models", "category": "dataviz", - "elo": 1351, - "win_rate": 63.3, + "elo": 1350, + "win_rate": 63.1, "rank": 4 }, { "arena": "models", "category": "gamedev", - "elo": 1359, - "win_rate": 60.4, + "elo": 1352, + "win_rate": 54.5, "rank": 8 }, { "arena": "models", "category": "svg", - "elo": 1302, - "win_rate": 59.3, - "rank": 5 + "elo": 1305, + "win_rate": 60.1, + "rank": 7 }, { "arena": "models", "category": "uicomponent", - "elo": 1344, - "win_rate": 60.1, - "rank": 6 + "elo": 1341, + "win_rate": 60.4, + "rank": 8 }, { "arena": "models", "category": "website", - "elo": 1335, - "win_rate": 59.2, - "rank": 4 + "elo": 1334, + "win_rate": 58.6, + "rank": 3 } ], "artificial_analysis": { - "intelligence_index": 43.6, - "coding_index": 76.2, - "agentic_index": 50 + "intelligence_index": 17.4, + "coding_index": 72, + "agentic_index": 29.3 } }, "reasoning": { @@ -20114,27 +21077,35 @@ "links": { "details": "/api/v1/models/moonshotai/kimi-k3-20260715/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1252, - "win_rate": 54.9, - "rank": 3 + "elo": 1202, + "win_rate": 53.8, + "rank": 4 }, { "arena": "agents", "category": "androidnative", - "elo": 1251, - "win_rate": 55.9, + "elo": 1255, + "win_rate": 56.7, "rank": 5 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1181, + "win_rate": 45.6, + "rank": 8 + }, { "arena": "agents", "category": "fullstack", "elo": 1315, - "win_rate": 61.8, + "win_rate": 61.6, "rank": 2 }, { @@ -20147,92 +21118,257 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1255, - "win_rate": 59.2, - "rank": 2 + "elo": 1153, + "win_rate": 55.6, + "rank": 5 }, { "arena": "agents", "category": "mobileapps", - "elo": 1269, - "win_rate": 57.5, - "rank": 3 + "elo": 1264, + "win_rate": 57.2, + "rank": 6 }, { "arena": "agents", - "category": "python-pptxslides", - "elo": 1270, - "win_rate": 58.9, + "category": "pdf", + "elo": 1283, + "win_rate": 64.5, "rank": 4 }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1219, + "win_rate": 54.8, + "rank": 6 + }, { "arena": "agents", "category": "spreadsheet", - "elo": 1057, - "win_rate": 33.1, - "rank": 13 + "elo": 1120, + "win_rate": 32, + "rank": 16 }, { "arena": "agents", "category": "webapps", - "elo": 1295, + "elo": 1284, "win_rate": 59.3, - "rank": 7 + "rank": 6 }, { "arena": "models", "category": "3d", - "elo": 1388, - "win_rate": 67.2, + "elo": 1381, + "win_rate": 64.2, "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1360, - "win_rate": 62.3, - "rank": 4 + "elo": 1353, + "win_rate": 60, + "rank": 5 }, { "arena": "models", "category": "dataviz", - "elo": 1351, - "win_rate": 63.3, + "elo": 1350, + "win_rate": 63.1, "rank": 4 }, { "arena": "models", "category": "gamedev", - "elo": 1359, - "win_rate": 60.4, + "elo": 1352, + "win_rate": 54.5, "rank": 8 }, { "arena": "models", "category": "svg", - "elo": 1302, - "win_rate": 59.3, - "rank": 5 + "elo": 1305, + "win_rate": 60.1, + "rank": 7 }, { "arena": "models", "category": "uicomponent", - "elo": 1344, - "win_rate": 60.1, + "elo": 1341, + "win_rate": 60.4, + "rank": 8 + }, + { + "arena": "models", + "category": "website", + "elo": 1334, + "win_rate": 58.6, + "rank": 3 + } + ], + "artificial_analysis": { + "intelligence_index": 17.4, + "coding_index": 72, + "agentic_index": 29.3 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "high", "low", "none"], + "default_effort": "max" + } + }, + { + "id": "moonshotai/kimi-k3.1-pro", + "canonical_slug": "moonshotai/kimi-k3.1-pro-20261023", + "hugging_face_id": null, + "name": "MoonshotAI: Kimi K3.1 Pro", + "created": 1792778188, + "description": "Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.00001", + "input_cache_read": "0.0000002" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 943718, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "top_p": 0.95 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/moonshotai/kimi-k3.1-pro-20261023/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1146, + "win_rate": 42.6, + "rank": 26 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1270, + "win_rate": 59.1, + "rank": 3 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1246, + "win_rate": 57.6, + "rank": 8 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1312, + "win_rate": 61.2, + "rank": 1 + }, + { + "arena": "models", + "category": "3d", + "elo": 1449, + "win_rate": 72, + "rank": 2 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1292, + "win_rate": 58, "rank": 6 }, + { + "arena": "models", + "category": "codecategories", + "elo": 1356, + "win_rate": 61.3, + "rank": 4 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1301, + "win_rate": 55.9, + "rank": 14 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1414, + "win_rate": 67.4, + "rank": 3 + }, + { + "arena": "models", + "category": "svg", + "elo": 1330, + "win_rate": 62.5, + "rank": 1 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1394, + "win_rate": 66.1, + "rank": 1 + }, { "arena": "models", "category": "website", - "elo": 1335, - "win_rate": 59.2, + "elo": 1326, + "win_rate": 58.1, "rank": 4 } ], "artificial_analysis": { - "intelligence_index": 43.6, - "coding_index": 76.2, - "agentic_index": 50 + "intelligence_index": 46.5, + "coding_index": null, + "agentic_index": null } }, "reasoning": { @@ -20286,7 +21422,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/morph/morph-v3-fast/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "morph/morph-v3-large", @@ -20332,7 +21474,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/morph/morph-v3-large/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "nex-agi/nex-n2.5-mini", @@ -20383,6 +21531,12 @@ "links": { "details": "/api/v1/models/nex-agi/nex-n2.5-mini-20260908/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["high", "medium", "none"], @@ -20440,115 +21594,18 @@ "links": { "details": "/api/v1/models/nex-agi/nex-n2.5-pro-20260907/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["high", "medium", "none"], "default_effort": "high" } }, - { - "id": "nousresearch/hermes-3-llama-3.1-405b", - "canonical_slug": "nousresearch/hermes-3-llama-3.1-405b", - "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-405B", - "name": "Nous: Hermes 3 405B Instruct", - "created": 1723766400, - "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "chatml" - }, - "pricing": { - "prompt": "0.000001", - "completion": "0.000001" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-12-31", - "expiration_date": "2026-11-02", - "links": { - "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" - } - }, - { - "id": "nousresearch/hermes-3-llama-3.1-70b", - "canonical_slug": "nousresearch/hermes-3-llama-3.1-70b", - "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-70B", - "name": "Nous: Hermes 3 70B Instruct", - "created": 1723939200, - "description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "chatml" - }, - "pricing": { - "prompt": "0.0000007", - "completion": "0.0000007" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-12-31", - "expiration_date": "2026-11-02", - "links": { - "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.7, - "coding_index": null, - "agentic_index": null - } - } - }, { "id": "nousresearch/hermes-4-405b", "canonical_slug": "nousresearch/hermes-4-405b", @@ -20566,7 +21623,8 @@ }, "pricing": { "prompt": "0.000001", - "completion": "0.000003" + "completion": "0.000003", + "input_cache_read": "0.0000002" }, "top_provider": { "context_length": 131072, @@ -20577,12 +21635,15 @@ "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", + "seed", + "stop", "structured_outputs", "temperature", "top_k", @@ -20596,14 +21657,12 @@ "links": { "details": "/api/v1/models/nousresearch/hermes-4-405b/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.5, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -20625,7 +21684,8 @@ }, "pricing": { "prompt": "0.00000006", - "completion": "0.00000024" + "completion": "0.00000024", + "input_cache_read": "0.000000012" }, "top_provider": { "context_length": 262144, @@ -20637,7 +21697,6 @@ "frequency_penalty", "include_reasoning", "logit_bias", - "logprobs", "max_tokens", "presence_penalty", "reasoning", @@ -20650,7 +21709,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -20664,10 +21722,16 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 8.9, + "intelligence_index": null, "coding_index": 14.4, "agentic_index": 1 } @@ -20725,10 +21789,16 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 10.3, + "intelligence_index": null, "coding_index": 13.8, "agentic_index": null } @@ -20746,7 +21816,7 @@ "name": "NVIDIA: Nemotron 3 Super", "created": 1773245239, "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. Built on a hybrid Mamba-Transformer...", - "context_length": 262144, + "context_length": 1048576, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -20760,8 +21830,8 @@ "input_cache_read": "0.00000015" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 235929, + "context_length": 1048576, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -20801,78 +21871,16 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 12.8, - "coding_index": 37.7, - "agentic_index": 1.7 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supports_max_tokens": true, - "supported_efforts": ["medium", "low", "none"], - "default_effort": "medium" - } - }, - { - "id": "nvidia/nemotron-3-super-120b-a12b:free", - "canonical_slug": "nvidia/nemotron-3-super-120b-a12b-20230311", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", - "name": "NVIDIA: Nemotron 3 Super (free)", - "created": 1773245239, - "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. Built on a hybrid Mamba-Transformer...", - "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", - "max_tokens", - "reasoning", - "reasoning_effort", - "response_format", - "seed", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": { - "temperature": 1, - "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/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" - }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 12.8, + "intelligence_index": null, "coding_index": 37.7, "agentic_index": 1.7 } @@ -20945,67 +21953,73 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1132, - "win_rate": 38.9, - "rank": 76 + "elo": 1127, + "win_rate": 38.2, + "rank": 81 }, { "arena": "models", "category": "asciiart", - "elo": 1100, - "win_rate": 37.6, - "rank": 60 + "elo": 1097, + "win_rate": 37.2, + "rank": 63 }, { "arena": "models", "category": "codecategories", - "elo": 1147, - "win_rate": 36.1, - "rank": 87 + "elo": 1145, + "win_rate": 36, + "rank": 90 }, { "arena": "models", "category": "dataviz", - "elo": 1141, + "elo": 1143, "win_rate": 37.5, "rank": 85 }, { "arena": "models", "category": "gamedev", - "elo": 1138, - "win_rate": 36.2, - "rank": 82 + "elo": 1139, + "win_rate": 35.9, + "rank": 80 }, { "arena": "models", "category": "svg", - "elo": 1070, - "win_rate": 32.4, - "rank": 69 + "elo": 1067, + "win_rate": 32.2, + "rank": 75 }, { "arena": "models", "category": "uicomponent", - "elo": 1139, - "win_rate": 35.8, - "rank": 83 + "elo": 1137, + "win_rate": 36, + "rank": 84 }, { "arena": "models", "category": "website", "elo": 1145, - "win_rate": 35.2, - "rank": 96 + "win_rate": 35.3, + "rank": 97 } ], "artificial_analysis": { - "intelligence_index": 22.9, + "intelligence_index": 11.8, "coding_index": 49.3, "agentic_index": 20.1 } @@ -21068,67 +22082,73 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1132, - "win_rate": 38.9, - "rank": 76 + "elo": 1127, + "win_rate": 38.2, + "rank": 81 }, { "arena": "models", "category": "asciiart", - "elo": 1100, - "win_rate": 37.6, - "rank": 60 + "elo": 1097, + "win_rate": 37.2, + "rank": 63 }, { "arena": "models", "category": "codecategories", - "elo": 1147, - "win_rate": 36.1, - "rank": 87 + "elo": 1145, + "win_rate": 36, + "rank": 90 }, { "arena": "models", "category": "dataviz", - "elo": 1141, + "elo": 1143, "win_rate": 37.5, "rank": 85 }, { "arena": "models", "category": "gamedev", - "elo": 1138, - "win_rate": 36.2, - "rank": 82 + "elo": 1139, + "win_rate": 35.9, + "rank": 80 }, { "arena": "models", "category": "svg", - "elo": 1070, - "win_rate": 32.4, - "rank": 69 + "elo": 1067, + "win_rate": 32.2, + "rank": 75 }, { "arena": "models", "category": "uicomponent", - "elo": 1139, - "win_rate": 35.8, - "rank": 83 + "elo": 1137, + "win_rate": 36, + "rank": 84 }, { "arena": "models", "category": "website", "elo": 1145, - "win_rate": 35.2, - "rank": 96 + "win_rate": 35.3, + "rank": 97 } ], "artificial_analysis": { - "intelligence_index": 22.9, + "intelligence_index": 11.8, "coding_index": 49.3, "agentic_index": 20.1 } @@ -21195,6 +22215,12 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true @@ -21247,6 +22273,12 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true @@ -21306,10 +22338,16 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 12.9, + "intelligence_index": 5.5, "coding_index": 26.8, "agentic_index": 3.5 } @@ -21360,10 +22398,16 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 12.9, + "intelligence_index": 5.5, "coding_index": 26.8, "agentic_index": 3.5 } @@ -21393,8 +22437,8 @@ "input_cache_read": "0.00000002" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 235929, + "context_length": 1048576, + "max_completion_tokens": 943718, "is_moderated": false }, "per_request_limits": null, @@ -21426,46 +22470,52 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-super-vl-20261015/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1129, - "win_rate": 28.5, - "rank": 78 + "elo": 1128, + "win_rate": 30.9, + "rank": 79 }, { "arena": "models", "category": "codecategories", - "elo": 1156, - "win_rate": 32.8, - "rank": 82 + "elo": 1150, + "win_rate": 33.2, + "rank": 89 }, { "arena": "models", "category": "gamedev", - "elo": 1111, - "win_rate": 29.2, - "rank": 93 + "elo": 1108, + "win_rate": 29.6, + "rank": 95 }, { "arena": "models", "category": "uicomponent", - "elo": 1143, - "win_rate": 32, - "rank": 81 + "elo": 1136, + "win_rate": 31, + "rank": 85 }, { "arena": "models", "category": "website", - "elo": 1173, - "win_rate": 34.9, - "rank": 81 + "elo": 1165, + "win_rate": 35, + "rank": 85 } ], "artificial_analysis": { - "intelligence_index": 26.5, + "intelligence_index": 13.6, "coding_index": null, "agentic_index": null } @@ -21518,46 +22568,52 @@ "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-super-vl-20261015/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1129, - "win_rate": 28.5, - "rank": 78 + "elo": 1128, + "win_rate": 30.9, + "rank": 79 }, { "arena": "models", "category": "codecategories", - "elo": 1156, - "win_rate": 32.8, - "rank": 82 + "elo": 1150, + "win_rate": 33.2, + "rank": 89 }, { "arena": "models", "category": "gamedev", - "elo": 1111, - "win_rate": 29.2, - "rank": 93 + "elo": 1108, + "win_rate": 29.6, + "rank": 95 }, { "arena": "models", "category": "uicomponent", - "elo": 1143, - "win_rate": 32, - "rank": 81 + "elo": 1136, + "win_rate": 31, + "rank": 85 }, { "arena": "models", "category": "website", - "elo": 1173, - "win_rate": 34.9, - "rank": 81 + "elo": 1165, + "win_rate": 35, + "rank": 85 } ], "artificial_analysis": { - "intelligence_index": 26.5, + "intelligence_index": 13.6, "coding_index": null, "agentic_index": null } @@ -21566,63 +22622,6 @@ "mandatory": false } }, - { - "id": "openai/gpt-3.5-turbo", - "canonical_slug": "openai/gpt-3.5-turbo", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo", - "created": 1685232000, - "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", - "context_length": 16385, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000005", - "completion": "0.0000015" - }, - "top_provider": { - "context_length": 16385, - "max_completion_tokens": 4096, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2021-09-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.5, - "coding_index": 10.7, - "agentic_index": null - } - } - }, { "id": "openai/gpt-3.5-turbo-0613", "canonical_slug": "openai/gpt-3.5-turbo-0613", @@ -21670,7 +22669,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-3.5-turbo-16k", @@ -21702,7 +22707,6 @@ "logit_bias", "logprobs", "max_completion_tokens", - "max_tokens", "presence_penalty", "response_format", "seed", @@ -21720,112 +22724,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints" - } - }, - { - "id": "openai/gpt-3.5-turbo-instruct", - "canonical_slug": "openai/gpt-3.5-turbo-instruct", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo Instruct", - "created": 1695859200, - "description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.", - "context_length": 4095, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": "chatml" - }, - "pricing": { - "prompt": "0.0000015", - "completion": "0.000002" - }, - "top_provider": { - "context_length": 4095, - "max_completion_tokens": 3685, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2021-09-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints" - } - }, - { - "id": "openai/gpt-3.5-turbo:batch", - "canonical_slug": "openai/gpt-3.5-turbo", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo (batch)", - "created": 1685232000, - "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", - "context_length": 16385, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null }, - "pricing": { - "prompt": "0.00000025", - "completion": "0.00000075", - "web_search": "0.01" - }, - "top_provider": { - "context_length": 16385, - "max_completion_tokens": 4096, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2021-09-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.5, - "coding_index": 10.7, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-4", @@ -21857,12 +22762,10 @@ "logit_bias", "logprobs", "max_completion_tokens", - "max_tokens", "presence_penalty", "response_format", "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -21876,20 +22779,26 @@ "links": { "details": "/api/v1/models/openai/gpt-4/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 6.7, + "intelligence_index": null, "coding_index": 13.1, "agentic_index": null } } }, { - "id": "openai/gpt-4-turbo", + "id": "openai/gpt-4-turbo:batch", "canonical_slug": "openai/gpt-4-turbo", "hugging_face_id": null, - "name": "OpenAI: GPT-4 Turbo", + "name": "OpenAI: GPT-4 Turbo (batch)", "created": 1712620800, "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", "context_length": 128000, @@ -21901,8 +22810,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00001", - "completion": "0.00003" + "prompt": "0.000005", + "completion": "0.000015", + "web_search": "0.01" }, "top_provider": { "context_length": 128000, @@ -21933,68 +22843,11 @@ "links": { "details": "/api/v1/models/openai/gpt-4-turbo/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 7, - "coding_index": 21.5, - "agentic_index": null - } - } - }, - { - "id": "openai/gpt-4-turbo:batch", - "canonical_slug": "openai/gpt-4-turbo", - "hugging_face_id": null, - "name": "OpenAI: GPT-4 Turbo (batch)", - "created": 1712620800, - "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", - "context_length": 128000, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000005", - "completion": "0.000015", - "web_search": "0.01" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 4096, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-12-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-4-turbo/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7, + "intelligence_index": null, "coding_index": 21.5, "agentic_index": null } @@ -22045,56 +22898,57 @@ "links": { "details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 850, + "elo": 847, "win_rate": 30.9, - "rank": 125 + "rank": 128 }, { "arena": "models", "category": "codecategories", - "elo": 1026, + "elo": 1024, "win_rate": 50.9, - "rank": 119 + "rank": 123 }, { "arena": "models", "category": "dataviz", "elo": 1104, "win_rate": 59.5, - "rank": 97 + "rank": 98 }, { "arena": "models", "category": "gamedev", - "elo": 1080, + "elo": 1078, "win_rate": 59.1, - "rank": 104 + "rank": 106 }, { "arena": "models", "category": "uicomponent", - "elo": 1000, + "elo": 995, "win_rate": 49.7, - "rank": 115 + "rank": 119 }, { "arena": "models", "category": "website", - "elo": 1039, + "elo": 1037, "win_rate": 52.3, - "rank": 122 + "rank": 125 } - ], - "artificial_analysis": { - "intelligence_index": 12.7, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -22142,53 +22996,59 @@ "links": { "details": "/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 837, + "elo": 834, "win_rate": 30.5, - "rank": 126 + "rank": 129 }, { "arena": "models", "category": "codecategories", - "elo": 994, + "elo": 992, "win_rate": 47.5, - "rank": 126 + "rank": 130 }, { "arena": "models", "category": "dataviz", "elo": 1034, "win_rate": 49.2, - "rank": 111 + "rank": 112 }, { "arena": "models", "category": "gamedev", - "elo": 1071, + "elo": 1069, "win_rate": 58.5, - "rank": 108 + "rank": 109 }, { "arena": "models", "category": "uicomponent", - "elo": 961, + "elo": 956, "win_rate": 45.4, - "rank": 119 + "rank": 123 }, { "arena": "models", "category": "website", "elo": 997, "win_rate": 47.8, - "rank": 130 + "rank": 132 } ], "artificial_analysis": { - "intelligence_index": 10.2, + "intelligence_index": null, "coding_index": 20.2, "agentic_index": null } @@ -22238,53 +23098,54 @@ "links": { "details": "/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 837, + "elo": 834, "win_rate": 30.5, - "rank": 126 + "rank": 129 }, { "arena": "models", "category": "codecategories", - "elo": 994, + "elo": 992, "win_rate": 47.5, - "rank": 126 + "rank": 130 }, { "arena": "models", "category": "dataviz", "elo": 1034, "win_rate": 49.2, - "rank": 111 + "rank": 112 }, { "arena": "models", "category": "gamedev", - "elo": 1071, + "elo": 1069, "win_rate": 58.5, - "rank": 108 + "rank": 109 }, { "arena": "models", "category": "uicomponent", - "elo": 961, + "elo": 956, "win_rate": 45.4, - "rank": 119 + "rank": 123 }, { "arena": "models", "category": "website", "elo": 997, "win_rate": 47.8, - "rank": 130 + "rank": 132 } ], "artificial_analysis": { - "intelligence_index": 10.2, + "intelligence_index": null, "coding_index": 20.2, "agentic_index": null } @@ -22309,17 +23170,16 @@ "prompt": "0.0000001", "completion": "0.0000004", "web_search": "0.01", - "input_cache_read": "0.000000025" + "input_cache_read": "0.00000003" }, "top_provider": { "context_length": 1047576, - "max_completion_tokens": 32768, - "is_moderated": true + "max_completion_tokens": 942818, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "max_completion_tokens", - "max_tokens", "response_format", "seed", "structured_outputs", @@ -22335,53 +23195,59 @@ "links": { "details": "/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 925, + "elo": 922, "win_rate": 46, - "rank": 119 + "rank": 122 }, { "arena": "models", "category": "codecategories", - "elo": 963, + "elo": 961, "win_rate": 47.3, - "rank": 130 + "rank": 134 }, { "arena": "models", "category": "dataviz", "elo": 891, "win_rate": 41.1, - "rank": 129 + "rank": 130 }, { "arena": "models", "category": "gamedev", - "elo": 971, + "elo": 969, "win_rate": 49.6, - "rank": 127 + "rank": 128 }, { "arena": "models", "category": "uicomponent", - "elo": 916, + "elo": 911, "win_rate": 43.9, - "rank": 125 + "rank": 130 }, { "arena": "models", "category": "website", - "elo": 973, + "elo": 971, "win_rate": 48.1, - "rank": 133 + "rank": 136 } ], "artificial_analysis": { - "intelligence_index": 7.8, + "intelligence_index": null, "coding_index": 11.1, "agentic_index": null } @@ -22431,53 +23297,54 @@ "links": { "details": "/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 925, + "elo": 922, "win_rate": 46, - "rank": 119 + "rank": 122 }, { "arena": "models", "category": "codecategories", - "elo": 963, + "elo": 961, "win_rate": 47.3, - "rank": 130 + "rank": 134 }, { "arena": "models", "category": "dataviz", "elo": 891, "win_rate": 41.1, - "rank": 129 + "rank": 130 }, { "arena": "models", "category": "gamedev", - "elo": 971, + "elo": 969, "win_rate": 49.6, - "rank": 127 + "rank": 128 }, { "arena": "models", "category": "uicomponent", - "elo": 916, + "elo": 911, "win_rate": 43.9, - "rank": 125 + "rank": 130 }, { "arena": "models", "category": "website", - "elo": 973, + "elo": 971, "win_rate": 48.1, - "rank": 133 + "rank": 136 } ], "artificial_analysis": { - "intelligence_index": 7.8, + "intelligence_index": null, "coding_index": 11.1, "agentic_index": null } @@ -22527,56 +23394,52 @@ "links": { "details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 850, + "elo": 847, "win_rate": 30.9, - "rank": 125 + "rank": 128 }, { "arena": "models", "category": "codecategories", - "elo": 1026, + "elo": 1024, "win_rate": 50.9, - "rank": 119 + "rank": 123 }, { "arena": "models", "category": "dataviz", "elo": 1104, "win_rate": 59.5, - "rank": 97 + "rank": 98 }, { "arena": "models", "category": "gamedev", - "elo": 1080, + "elo": 1078, "win_rate": 59.1, - "rank": 104 + "rank": 106 }, { "arena": "models", "category": "uicomponent", - "elo": 1000, + "elo": 995, "win_rate": 49.7, - "rank": 115 + "rank": 119 }, { "arena": "models", "category": "website", - "elo": 1039, + "elo": 1037, "win_rate": 52.3, - "rank": 122 + "rank": 125 } - ], - "artificial_analysis": { - "intelligence_index": 12.7, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -22631,49 +23494,55 @@ "links": { "details": "/api/v1/models/openai/gpt-4o/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 869, + "elo": 866, "win_rate": 39.2, - "rank": 122 + "rank": 125 }, { "arena": "models", "category": "codecategories", - "elo": 861, + "elo": 859, "win_rate": 34.8, - "rank": 136 + "rank": 140 }, { "arena": "models", "category": "dataviz", "elo": 858, "win_rate": 36, - "rank": 131 + "rank": 132 }, { "arena": "models", "category": "gamedev", "elo": 906, "win_rate": 42.3, - "rank": 135 + "rank": 136 }, { "arena": "models", "category": "uicomponent", - "elo": 885, + "elo": 880, "win_rate": 38.1, - "rank": 130 + "rank": 134 }, { "arena": "models", "category": "website", "elo": 831, "win_rate": 31.5, - "rank": 144 + "rank": 146 } ] } @@ -22708,8 +23577,6 @@ "logit_bias", "logprobs", "max_completion_tokens", - "max_tokens", - "prediction", "presence_penalty", "response_format", "seed", @@ -22729,10 +23596,16 @@ "links": { "details": "/api/v1/models/openai/gpt-4o-2024-05-13/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 7.3, + "intelligence_index": null, "coding_index": 24.2, "agentic_index": null } @@ -22790,14 +23663,12 @@ "links": { "details": "/api/v1/models/openai/gpt-4o-2024-08-06/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-4o-2024-11-20", @@ -22850,14 +23721,12 @@ "links": { "details": "/api/v1/models/openai/gpt-4o-2024-11-20/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 8.4, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-4o-mini", @@ -22911,10 +23780,16 @@ "links": { "details": "/api/v1/models/openai/gpt-4o-mini/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 6.7, + "intelligence_index": null, "coding_index": 11.4, "agentic_index": null } @@ -22970,7 +23845,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-4o-mini:batch", @@ -23024,10 +23905,11 @@ "links": { "details": "/api/v1/models/openai/gpt-4o-mini/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 6.7, + "intelligence_index": null, "coding_index": 11.4, "agentic_index": null } @@ -23085,49 +23967,50 @@ "links": { "details": "/api/v1/models/openai/gpt-4o/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 869, + "elo": 866, "win_rate": 39.2, - "rank": 122 + "rank": 125 }, { "arena": "models", "category": "codecategories", - "elo": 861, + "elo": 859, "win_rate": 34.8, - "rank": 136 + "rank": 140 }, { "arena": "models", "category": "dataviz", "elo": 858, "win_rate": 36, - "rank": 131 + "rank": 132 }, { "arena": "models", "category": "gamedev", "elo": 906, "win_rate": 42.3, - "rank": 135 + "rank": 136 }, { "arena": "models", "category": "uicomponent", - "elo": 885, + "elo": 880, "win_rate": 38.1, - "rank": 130 + "rank": 134 }, { "arena": "models", "category": "website", "elo": 831, "win_rate": 31.5, - "rank": 144 + "rank": 146 } ] } @@ -23186,67 +24069,73 @@ "links": { "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1056, + "elo": 1053, "win_rate": 41.3, - "rank": 104 + "rank": 107 }, { "arena": "models", "category": "asciiart", - "elo": 1141, + "elo": 1138, "win_rate": 49, - "rank": 48 + "rank": 51 }, { "arena": "models", "category": "codecategories", - "elo": 1168, + "elo": 1166, "win_rate": 54.5, - "rank": 75 + "rank": 78 }, { "arena": "models", "category": "dataviz", "elo": 1221, "win_rate": 60.5, - "rank": 51 + "rank": 52 }, { "arena": "models", "category": "gamedev", "elo": 1185, "win_rate": 59.3, - "rank": 62 + "rank": 63 }, { "arena": "models", "category": "svg", - "elo": 1189, + "elo": 1185, "win_rate": 64.1, - "rank": 30 + "rank": 36 }, { "arena": "models", "category": "uicomponent", - "elo": 1180, + "elo": 1174, "win_rate": 57.4, - "rank": 65 + "rank": 69 }, { "arena": "models", "category": "website", - "elo": 1184, + "elo": 1183, "win_rate": 53.7, - "rank": 74 + "rank": 75 } ], "artificial_analysis": { - "intelligence_index": 23, + "intelligence_index": null, "coding_index": 37.8, "agentic_index": null } @@ -23309,6 +24198,13 @@ "links": { "details": "/api/v1/models/openai/gpt-5-image/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "benchmarks": { "design_arena": [ { @@ -23321,7 +24217,7 @@ { "arena": "models", "category": "image", - "elo": 1191, + "elo": 1188, "win_rate": 53.9, "rank": 9 }, @@ -23390,6 +24286,13 @@ "links": { "details": "/api/v1/models/openai/gpt-5-image-mini/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "benchmarks": { "design_arena": [ { @@ -23402,7 +24305,7 @@ { "arena": "models", "category": "image", - "elo": 1184, + "elo": 1181, "win_rate": 51, "rank": 11 }, @@ -23473,69 +24376,75 @@ "links": { "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1037, + "elo": 1034, "win_rate": 36.9, - "rank": 106 + "rank": 109 }, { "arena": "models", "category": "asciiart", - "elo": 1125, + "elo": 1122, "win_rate": 44.8, - "rank": 53 + "rank": 57 }, { "arena": "models", "category": "codecategories", - "elo": 1115, + "elo": 1113, "win_rate": 43.5, - "rank": 99 + "rank": 103 }, { "arena": "models", "category": "dataviz", "elo": 1131, "win_rate": 43.7, - "rank": 90 + "rank": 91 }, { "arena": "models", "category": "gamedev", - "elo": 1130, + "elo": 1128, "win_rate": 46.5, "rank": 90 }, { "arena": "models", "category": "svg", - "elo": 1091, + "elo": 1088, "win_rate": 45.8, - "rank": 62 + "rank": 68 }, { "arena": "models", "category": "uicomponent", - "elo": 1106, + "elo": 1101, "win_rate": 41.9, - "rank": 92 + "rank": 95 }, { "arena": "models", "category": "website", - "elo": 1125, + "elo": 1124, "win_rate": 44.3, - "rank": 100 + "rank": 102 } ], "artificial_analysis": { - "intelligence_index": 20.6, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 15.6, + "agentic_index": 6.8 } }, "reasoning": { @@ -23597,69 +24506,70 @@ "links": { "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1037, + "elo": 1034, "win_rate": 36.9, - "rank": 106 + "rank": 109 }, { "arena": "models", "category": "asciiart", - "elo": 1125, + "elo": 1122, "win_rate": 44.8, - "rank": 53 + "rank": 57 }, { "arena": "models", "category": "codecategories", - "elo": 1115, + "elo": 1113, "win_rate": 43.5, - "rank": 99 + "rank": 103 }, { "arena": "models", "category": "dataviz", "elo": 1131, "win_rate": 43.7, - "rank": 90 + "rank": 91 }, { "arena": "models", "category": "gamedev", - "elo": 1130, + "elo": 1128, "win_rate": 46.5, "rank": 90 }, { "arena": "models", "category": "svg", - "elo": 1091, + "elo": 1088, "win_rate": 45.8, - "rank": 62 + "rank": 68 }, { "arena": "models", "category": "uicomponent", - "elo": 1106, + "elo": 1101, "win_rate": 41.9, - "rank": 92 + "rank": 95 }, { "arena": "models", "category": "website", - "elo": 1125, + "elo": 1124, "win_rate": 44.3, - "rank": 100 + "rank": 102 } ], "artificial_analysis": { - "intelligence_index": 20.6, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 15.6, + "agentic_index": 6.8 } }, "reasoning": { @@ -23722,56 +24632,57 @@ "links": { "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 966, + "elo": 963, "win_rate": 36.3, - "rank": 117 + "rank": 120 }, { "arena": "models", "category": "codecategories", - "elo": 1084, + "elo": 1082, "win_rate": 48, - "rank": 107 + "rank": 111 }, { "arena": "models", "category": "dataviz", "elo": 1056, "win_rate": 46.2, - "rank": 109 + "rank": 110 }, { "arena": "models", "category": "gamedev", - "elo": 1045, + "elo": 1043, "win_rate": 46.5, - "rank": 115 + "rank": 116 }, { "arena": "models", "category": "uicomponent", - "elo": 1067, + "elo": 1061, "win_rate": 51.9, - "rank": 104 + "rank": 108 }, { "arena": "models", "category": "website", "elo": 1101, "win_rate": 48.9, - "rank": 109 + "rank": 111 } - ], - "artificial_analysis": { - "intelligence_index": 13, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true, @@ -23832,56 +24743,52 @@ "links": { "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 966, + "elo": 963, "win_rate": 36.3, - "rank": 117 + "rank": 120 }, { "arena": "models", "category": "codecategories", - "elo": 1084, + "elo": 1082, "win_rate": 48, - "rank": 107 + "rank": 111 }, { "arena": "models", "category": "dataviz", "elo": 1056, "win_rate": 46.2, - "rank": 109 + "rank": 110 }, { "arena": "models", "category": "gamedev", - "elo": 1045, + "elo": 1043, "win_rate": 46.5, - "rank": 115 + "rank": 116 }, { "arena": "models", "category": "uicomponent", - "elo": 1067, + "elo": 1061, "win_rate": 51.9, - "rank": 104 + "rank": 108 }, { "arena": "models", "category": "website", "elo": 1101, "win_rate": 48.9, - "rank": 109 + "rank": 111 } - ], - "artificial_analysis": { - "intelligence_index": 13, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true, @@ -23938,6 +24845,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["high"], @@ -23993,6 +24906,7 @@ "links": { "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true, "supported_efforts": ["high"], @@ -24052,67 +24966,68 @@ "links": { "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1056, + "elo": 1053, "win_rate": 41.3, - "rank": 104 + "rank": 107 }, { "arena": "models", "category": "asciiart", - "elo": 1141, + "elo": 1138, "win_rate": 49, - "rank": 48 + "rank": 51 }, { "arena": "models", "category": "codecategories", - "elo": 1168, + "elo": 1166, "win_rate": 54.5, - "rank": 75 + "rank": 78 }, { "arena": "models", "category": "dataviz", "elo": 1221, "win_rate": 60.5, - "rank": 51 + "rank": 52 }, { "arena": "models", "category": "gamedev", "elo": 1185, "win_rate": 59.3, - "rank": 62 + "rank": 63 }, { "arena": "models", "category": "svg", - "elo": 1189, + "elo": 1185, "win_rate": 64.1, - "rank": 30 + "rank": 36 }, { "arena": "models", "category": "uicomponent", - "elo": 1180, + "elo": 1174, "win_rate": 57.4, - "rank": 65 + "rank": 69 }, { "arena": "models", "category": "website", - "elo": 1184, + "elo": 1183, "win_rate": 53.7, - "rank": 74 + "rank": 75 } ], "artificial_analysis": { - "intelligence_index": 23, + "intelligence_index": null, "coding_index": 37.8, "agentic_index": null } @@ -24177,67 +25092,73 @@ "links": { "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1061, + "elo": 1058, "win_rate": 43.7, - "rank": 102 + "rank": 106 }, { "arena": "models", "category": "asciiart", - "elo": 1119, + "elo": 1116, "win_rate": 48.6, - "rank": 55 + "rank": 58 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1169, "win_rate": 53, - "rank": 73 + "rank": 76 }, { "arena": "models", "category": "dataviz", "elo": 1204, "win_rate": 58, - "rank": 57 + "rank": 58 }, { "arena": "models", "category": "gamedev", - "elo": 1179, + "elo": 1177, "win_rate": 55.9, - "rank": 63 + "rank": 64 }, { "arena": "models", "category": "svg", - "elo": 1149, + "elo": 1146, "win_rate": 57.4, - "rank": 46 + "rank": 51 }, { "arena": "models", "category": "uicomponent", - "elo": 1166, + "elo": 1161, "win_rate": 52.9, - "rank": 71 + "rank": 74 }, { "arena": "models", "category": "website", - "elo": 1187, + "elo": 1185, "win_rate": 54, - "rank": 72 + "rank": 74 } ], "artificial_analysis": { - "intelligence_index": 24.7, + "intelligence_index": null, "coding_index": 49.4, "agentic_index": null } @@ -24302,6 +25223,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -24316,28 +25243,28 @@ "category": "mobileapps", "elo": 1191, "win_rate": 53.4, - "rank": 20 + "rank": 21 }, { "arena": "agents", "category": "webapps", - "elo": 1018, + "elo": 1005, "win_rate": 44, - "rank": 44 + "rank": 45 }, { "arena": "models", "category": "codecategories", - "elo": 1153, + "elo": 1151, "win_rate": 54.6, - "rank": 83 + "rank": 85 }, { "arena": "models", "category": "dataviz", "elo": 1213, "win_rate": 55.9, - "rank": 54 + "rank": 55 }, { "arena": "models", @@ -24349,23 +25276,18 @@ { "arena": "models", "category": "uicomponent", - "elo": 1237, + "elo": 1232, "win_rate": 60, - "rank": 46 + "rank": 47 }, { "arena": "models", "category": "website", - "elo": 1162, + "elo": 1160, "win_rate": 56.1, - "rank": 86 + "rank": 89 } - ], - "artificial_analysis": { - "intelligence_index": 23.7, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true, @@ -24426,6 +25348,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium", "low"], @@ -24485,70 +25413,71 @@ "links": { "details": "/api/v1/models/openai/gpt-5.1-codex-mini-20251113/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 988, + "elo": 986, "win_rate": 32.8, - "rank": 114 + "rank": 117 }, { "arena": "models", "category": "asciiart", - "elo": 1105, + "elo": 1102, "win_rate": 43, - "rank": 59 + "rank": 62 }, { "arena": "models", "category": "codecategories", - "elo": 1094, + "elo": 1092, "win_rate": 41.5, - "rank": 106 + "rank": 110 }, { "arena": "models", "category": "dataviz", "elo": 1097, "win_rate": 40.6, - "rank": 101 + "rank": 102 }, { "arena": "models", "category": "gamedev", "elo": 1092, "win_rate": 43.4, - "rank": 101 + "rank": 102 }, { "arena": "models", "category": "svg", - "elo": 978, + "elo": 974, "win_rate": 35.3, - "rank": 87 + "rank": 93 }, { "arena": "models", "category": "uicomponent", - "elo": 1081, + "elo": 1076, "win_rate": 41, - "rank": 101 + "rank": 105 }, { "arena": "models", "category": "website", - "elo": 1111, + "elo": 1109, "win_rate": 42.9, - "rank": 107 + "rank": 109 } - ], - "artificial_analysis": { - "intelligence_index": 20.4, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true, @@ -24609,67 +25538,68 @@ "links": { "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1061, + "elo": 1058, "win_rate": 43.7, - "rank": 102 + "rank": 106 }, { "arena": "models", "category": "asciiart", - "elo": 1119, + "elo": 1116, "win_rate": 48.6, - "rank": 55 + "rank": 58 }, { "arena": "models", "category": "codecategories", - "elo": 1171, + "elo": 1169, "win_rate": 53, - "rank": 73 + "rank": 76 }, { "arena": "models", "category": "dataviz", "elo": 1204, "win_rate": 58, - "rank": 57 + "rank": 58 }, { "arena": "models", "category": "gamedev", - "elo": 1179, + "elo": 1177, "win_rate": 55.9, - "rank": 63 + "rank": 64 }, { "arena": "models", "category": "svg", - "elo": 1149, + "elo": 1146, "win_rate": 57.4, - "rank": 46 + "rank": 51 }, { "arena": "models", "category": "uicomponent", - "elo": 1166, + "elo": 1161, "win_rate": 52.9, - "rank": 71 + "rank": 74 }, { "arena": "models", "category": "website", - "elo": 1187, + "elo": 1185, "win_rate": 54, - "rank": 72 + "rank": 74 } ], "artificial_analysis": { - "intelligence_index": 24.7, + "intelligence_index": null, "coding_index": 49.4, "agentic_index": null } @@ -24735,21 +25665,27 @@ "links": { "details": "/api/v1/models/openai/gpt-5.2-20251211/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "website", - "elo": 1195, + "elo": 1193, "win_rate": 54.4, - "rank": 67 + "rank": 68 }, { "arena": "agents", "category": "androidnative", - "elo": 1058, + "elo": 1055, "win_rate": 49.1, - "rank": 33 + "rank": 35 }, { "arena": "agents", @@ -24770,70 +25706,65 @@ "category": "mobileapps", "elo": 1093, "win_rate": 46.8, - "rank": 40 + "rank": 42 }, { "arena": "agents", "category": "webapps", - "elo": 1086, + "elo": 1072, "win_rate": 45.5, - "rank": 39 + "rank": 40 }, { "arena": "models", "category": "3d", - "elo": 1079, + "elo": 1075, "win_rate": 41.5, - "rank": 96 + "rank": 100 }, { "arena": "models", "category": "codecategories", - "elo": 1170, + "elo": 1168, "win_rate": 49.6, - "rank": 74 + "rank": 77 }, { "arena": "models", "category": "dataviz", "elo": 1202, "win_rate": 56.1, - "rank": 60 + "rank": 61 }, { "arena": "models", "category": "gamedev", "elo": 1195, "win_rate": 56, - "rank": 59 + "rank": 60 }, { "arena": "models", "category": "uicomponent", - "elo": 1190, + "elo": 1185, "win_rate": 51.3, - "rank": 63 + "rank": 66 }, { "arena": "models", "category": "asciiart", - "elo": 1152, + "elo": 1149, "win_rate": 50.7, - "rank": 43 + "rank": 45 }, { "arena": "models", "category": "svg", - "elo": 1139, + "elo": 1135, "win_rate": 53.7, - "rank": 51 + "rank": 57 } - ], - "artificial_analysis": { - "intelligence_index": 30.4, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -24887,7 +25818,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-5.2-codex", @@ -24939,6 +25876,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -24965,23 +25908,18 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1090, + "elo": 1088, "win_rate": 46.6, - "rank": 42 + "rank": 44 }, { "arena": "agents", "category": "webapps", - "elo": 1051, + "elo": 1037, "win_rate": 39.6, - "rank": 42 + "rank": 43 } - ], - "artificial_analysis": { - "intelligence_index": 28.5, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true, @@ -25038,6 +25976,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium"], @@ -25093,6 +26037,7 @@ "links": { "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium"], @@ -25152,21 +26097,22 @@ "links": { "details": "/api/v1/models/openai/gpt-5.2-20251211/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "website", - "elo": 1195, + "elo": 1193, "win_rate": 54.4, - "rank": 67 + "rank": 68 }, { "arena": "agents", "category": "androidnative", - "elo": 1058, + "elo": 1055, "win_rate": 49.1, - "rank": 33 + "rank": 35 }, { "arena": "agents", @@ -25187,70 +26133,65 @@ "category": "mobileapps", "elo": 1093, "win_rate": 46.8, - "rank": 40 + "rank": 42 }, { "arena": "agents", "category": "webapps", - "elo": 1086, + "elo": 1072, "win_rate": 45.5, - "rank": 39 + "rank": 40 }, { "arena": "models", "category": "3d", - "elo": 1079, + "elo": 1075, "win_rate": 41.5, - "rank": 96 + "rank": 100 }, { "arena": "models", "category": "codecategories", - "elo": 1170, + "elo": 1168, "win_rate": 49.6, - "rank": 74 + "rank": 77 }, { "arena": "models", "category": "dataviz", "elo": 1202, "win_rate": 56.1, - "rank": 60 + "rank": 61 }, { "arena": "models", "category": "gamedev", "elo": 1195, "win_rate": 56, - "rank": 59 + "rank": 60 }, { "arena": "models", "category": "uicomponent", - "elo": 1190, + "elo": 1185, "win_rate": 51.3, - "rank": 63 + "rank": 66 }, { "arena": "models", "category": "asciiart", - "elo": 1152, + "elo": 1149, "win_rate": 50.7, - "rank": 43 + "rank": 45 }, { "arena": "models", "category": "svg", - "elo": 1139, + "elo": 1135, "win_rate": 53.7, - "rank": 51 + "rank": 57 } - ], - "artificial_analysis": { - "intelligence_index": 30.4, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -25312,6 +26253,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.3-codex-20260224/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -25319,7 +26266,7 @@ "category": "androidnative", "elo": 1084, "win_rate": 35.2, - "rank": 31 + "rank": 33 }, { "arena": "agents", @@ -25340,42 +26287,42 @@ "category": "mobileapps", "elo": 1053, "win_rate": 41.4, - "rank": 46 + "rank": 48 }, { "arena": "agents", "category": "webapps", - "elo": 1032, + "elo": 1019, "win_rate": 36.9, - "rank": 43 + "rank": 44 }, { "arena": "models", "category": "3d", - "elo": 1008, + "elo": 1005, "win_rate": 35.3, - "rank": 110 + "rank": 113 }, { "arena": "models", "category": "asciiart", - "elo": 1152, + "elo": 1149, "win_rate": 51.2, - "rank": 42 + "rank": 44 }, { "arena": "models", "category": "codecategories", - "elo": 1145, + "elo": 1143, "win_rate": 47.2, - "rank": 88 + "rank": 91 }, { "arena": "models", "category": "dataviz", "elo": 1164, "win_rate": 50.6, - "rank": 75 + "rank": 76 }, { "arena": "models", @@ -25387,30 +26334,25 @@ { "arena": "models", "category": "svg", - "elo": 1129, + "elo": 1126, "win_rate": 54, - "rank": 54 + "rank": 60 }, { "arena": "models", "category": "uicomponent", - "elo": 1137, + "elo": 1132, "win_rate": 47.3, - "rank": 84 + "rank": 87 }, { "arena": "models", "category": "website", - "elo": 1163, + "elo": 1161, "win_rate": 48.6, - "rank": 85 + "rank": 88 } - ], - "artificial_analysis": { - "intelligence_index": 32.5, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -25480,70 +26422,76 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1102, + "elo": 1099, "win_rate": 42.3, - "rank": 88 + "rank": 90 }, { "arena": "models", "category": "asciiart", - "elo": 1199, + "elo": 1196, "win_rate": 55.4, - "rank": 26 + "rank": 28 }, { "arena": "models", "category": "codecategories", - "elo": 1212, + "elo": 1210, "win_rate": 52.5, - "rank": 56 + "rank": 59 }, { "arena": "models", "category": "dataviz", "elo": 1235, "win_rate": 56.6, - "rank": 42 + "rank": 43 }, { "arena": "models", "category": "gamedev", - "elo": 1239, + "elo": 1237, "win_rate": 57.6, - "rank": 40 + "rank": 41 }, { "arena": "models", "category": "svg", - "elo": 1195, + "elo": 1191, "win_rate": 57.8, - "rank": 28 + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1240, + "elo": 1234, "win_rate": 57.4, - "rank": 44 + "rank": 45 }, { "arena": "models", "category": "website", - "elo": 1220, + "elo": 1219, "win_rate": 52.5, - "rank": 60 + "rank": 61 }, { "arena": "agents", "category": "androidnative", - "elo": 1031, + "elo": 1027, "win_rate": 47.4, - "rank": 37 + "rank": 39 }, { "arena": "agents", @@ -25562,20 +26510,20 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1087, + "elo": 1085, "win_rate": 46.1, - "rank": 44 + "rank": 46 }, { "arena": "agents", "category": "webapps", - "elo": 1059, + "elo": 1045, "win_rate": 40.3, - "rank": 41 + "rank": 42 } ], "artificial_analysis": { - "intelligence_index": 39, + "intelligence_index": null, "coding_index": 71.1, "agentic_index": null } @@ -25641,6 +26589,13 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/v1/images" + ], "reasoning": { "mandatory": false, "default_enabled": false, @@ -25702,10 +26657,16 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 24.1, + "intelligence_index": null, "coding_index": 56.1, "agentic_index": 17.9 } @@ -25770,10 +26731,11 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 24.1, + "intelligence_index": null, "coding_index": 56.1, "agentic_index": 17.9 } @@ -25839,10 +26801,16 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 20.7, + "intelligence_index": null, "coding_index": 56.1, "agentic_index": 16 } @@ -25907,10 +26875,11 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 20.7, + "intelligence_index": null, "coding_index": 56.1, "agentic_index": 16 } @@ -25982,6 +26951,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium"], @@ -26047,6 +27022,7 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium"], @@ -26114,70 +27090,71 @@ "links": { "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1102, + "elo": 1099, "win_rate": 42.3, - "rank": 88 + "rank": 90 }, { "arena": "models", "category": "asciiart", - "elo": 1199, + "elo": 1196, "win_rate": 55.4, - "rank": 26 + "rank": 28 }, { "arena": "models", "category": "codecategories", - "elo": 1212, + "elo": 1210, "win_rate": 52.5, - "rank": 56 + "rank": 59 }, { "arena": "models", "category": "dataviz", "elo": 1235, "win_rate": 56.6, - "rank": 42 + "rank": 43 }, { "arena": "models", "category": "gamedev", - "elo": 1239, + "elo": 1237, "win_rate": 57.6, - "rank": 40 + "rank": 41 }, { "arena": "models", "category": "svg", - "elo": 1195, + "elo": 1191, "win_rate": 57.8, - "rank": 28 + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1240, + "elo": 1234, "win_rate": 57.4, - "rank": 44 + "rank": 45 }, { "arena": "models", "category": "website", - "elo": 1220, + "elo": 1219, "win_rate": 52.5, - "rank": 60 + "rank": 61 }, { "arena": "agents", "category": "androidnative", - "elo": 1031, + "elo": 1027, "win_rate": 47.4, - "rank": 37 + "rank": 39 }, { "arena": "agents", @@ -26196,20 +27173,20 @@ { "arena": "agents", "category": "mobileapps", - "elo": 1087, + "elo": 1085, "win_rate": 46.1, - "rank": 44 + "rank": 46 }, { "arena": "agents", "category": "webapps", - "elo": 1059, + "elo": 1045, "win_rate": 40.3, - "rank": 41 + "rank": 42 } ], "artificial_analysis": { - "intelligence_index": 39, + "intelligence_index": null, "coding_index": 71.1, "agentic_index": null } @@ -26283,14 +27260,20 @@ "links": { "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1179, + "elo": 1125, "win_rate": 52.4, - "rank": 14 + "rank": 16 }, { "arena": "agents", @@ -26323,9 +27306,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1163, + "elo": 1160, "win_rate": 50.9, - "rank": 21 + "rank": 22 }, { "arena": "agents", @@ -26344,16 +27327,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1068, + "elo": 963, "win_rate": 35.6, - "rank": 22 + "rank": 24 }, { "arena": "agents", "category": "mobileapps", "elo": 1142, "win_rate": 50.4, - "rank": 32 + "rank": 33 }, { "arena": "agents", @@ -26367,74 +27350,74 @@ "category": "python-pptxslides", "elo": 1152, "win_rate": 43.3, - "rank": 22 + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1117, + "elo": 1104, "win_rate": 42.6, - "rank": 36 + "rank": 37 }, { "arena": "models", "category": "3d", - "elo": 1197, - "win_rate": 49.3, - "rank": 50 + "elo": 1194, + "win_rate": 49.2, + "rank": 52 }, { "arena": "models", "category": "asciiart", - "elo": 1255, - "win_rate": 58.2, - "rank": 16 + "elo": 1252, + "win_rate": 58, + "rank": 18 }, { "arena": "models", "category": "codecategories", - "elo": 1260, - "win_rate": 53, - "rank": 36 + "elo": 1259, + "win_rate": 52.9, + "rank": 38 }, { "arena": "models", "category": "dataviz", - "elo": 1265, - "win_rate": 55.7, - "rank": 29 + "elo": 1263, + "win_rate": 55.3, + "rank": 31 }, { "arena": "models", "category": "gamedev", - "elo": 1294, - "win_rate": 56.9, + "elo": 1292, + "win_rate": 56.5, "rank": 21 }, { "arena": "models", "category": "svg", - "elo": 1235, - "win_rate": 55.1, - "rank": 16 + "elo": 1230, + "win_rate": 54.8, + "rank": 21 }, { "arena": "models", "category": "uicomponent", - "elo": 1260, + "elo": 1255, "win_rate": 53.3, - "rank": 38 + "rank": 39 }, { "arena": "models", "category": "website", "elo": 1256, - "win_rate": 52.2, - "rank": 41 + "win_rate": 52.1, + "rank": 40 } ], "artificial_analysis": { - "intelligence_index": 38.4, + "intelligence_index": null, "coding_index": 74.9, "agentic_index": 36.4 } @@ -26505,6 +27488,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium"], @@ -26570,6 +27559,7 @@ "links": { "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true, "supported_efforts": ["xhigh", "high", "medium"], @@ -26637,14 +27627,15 @@ "links": { "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1179, + "elo": 1125, "win_rate": 52.4, - "rank": 14 + "rank": 16 }, { "arena": "agents", @@ -26677,9 +27668,9 @@ { "arena": "agents", "category": "androidnative", - "elo": 1163, + "elo": 1160, "win_rate": 50.9, - "rank": 21 + "rank": 22 }, { "arena": "agents", @@ -26698,16 +27689,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1068, + "elo": 963, "win_rate": 35.6, - "rank": 22 + "rank": 24 }, { "arena": "agents", "category": "mobileapps", "elo": 1142, "win_rate": 50.4, - "rank": 32 + "rank": 33 }, { "arena": "agents", @@ -26721,74 +27712,74 @@ "category": "python-pptxslides", "elo": 1152, "win_rate": 43.3, - "rank": 22 + "rank": 17 }, { "arena": "agents", "category": "webapps", - "elo": 1117, + "elo": 1104, "win_rate": 42.6, - "rank": 36 + "rank": 37 }, { "arena": "models", "category": "3d", - "elo": 1197, - "win_rate": 49.3, - "rank": 50 + "elo": 1194, + "win_rate": 49.2, + "rank": 52 }, { "arena": "models", "category": "asciiart", - "elo": 1255, - "win_rate": 58.2, - "rank": 16 + "elo": 1252, + "win_rate": 58, + "rank": 18 }, { "arena": "models", "category": "codecategories", - "elo": 1260, - "win_rate": 53, - "rank": 36 + "elo": 1259, + "win_rate": 52.9, + "rank": 38 }, { "arena": "models", "category": "dataviz", - "elo": 1265, - "win_rate": 55.7, - "rank": 29 + "elo": 1263, + "win_rate": 55.3, + "rank": 31 }, { "arena": "models", "category": "gamedev", - "elo": 1294, - "win_rate": 56.9, + "elo": 1292, + "win_rate": 56.5, "rank": 21 }, { "arena": "models", "category": "svg", - "elo": 1235, - "win_rate": 55.1, - "rank": 16 + "elo": 1230, + "win_rate": 54.8, + "rank": 21 }, { "arena": "models", "category": "uicomponent", - "elo": 1260, + "elo": 1255, "win_rate": 53.3, - "rank": 38 + "rank": 39 }, { "arena": "models", "category": "website", "elo": 1256, - "win_rate": 52.2, - "rank": 41 + "win_rate": 52.1, + "rank": 40 } ], "artificial_analysis": { - "intelligence_index": 38.4, + "intelligence_index": null, "coding_index": 74.9, "agentic_index": 36.4 } @@ -26864,10 +27855,16 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 37.3, + "intelligence_index": null, "coding_index": 71.4, "agentic_index": 42.1 } @@ -26943,6 +27940,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -27011,6 +28014,7 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": false, "default_enabled": true, @@ -27079,10 +28083,11 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 37.3, + "intelligence_index": null, "coding_index": 71.4, "agentic_index": 42.1 } @@ -27158,12 +28163,18 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 47, - "coding_index": 77.4, - "agentic_index": 50.2 + "intelligence_index": null, + "coding_index": 78.3, + "agentic_index": 47.4 } }, "reasoning": { @@ -27201,225 +28212,233 @@ "completion": "0.00003", "input_cache_read": "0.0000008", "input_cache_write": "0.00001" - } - ] - }, - "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": "2026-02-16", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-5.6-sol-pro:batch", - "canonical_slug": "openai/gpt-5.6-sol-pro-20260709", - "hugging_face_id": null, - "name": "OpenAI: GPT-5.6 Sol Pro (batch)", - "created": 1783590854, - "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-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", - "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": "0.0000002", - "input_cache_write": "0.0000025", - "overrides": [ - { - "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000015", - "input_cache_read": "0.0000004", - "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_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": "2026-02-16", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-5.6-sol:batch", - "canonical_slug": "openai/gpt-5.6-sol-20260709", - "hugging_face_id": null, - "name": "OpenAI: GPT-5.6 Sol (batch)", - "created": 1783590850, - "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...", - "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": "0.0000002", - "input_cache_write": "0.0000025", - "overrides": [ - { - "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000015", - "input_cache_read": "0.0000004", - "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_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": "2026-02-16", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 47, - "coding_index": 77.4, - "agentic_index": 50.2 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-5.6-terra", - "canonical_slug": "openai/gpt-5.6-terra-20260709", - "hugging_face_id": null, - "name": "OpenAI: GPT-5.6 Terra", - "created": 1783590857, - "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and 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": "0.000002", - "completion": "0.000012", - "web_search": "0.01", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025", - "overrides": [ - { - "min_prompt_tokens": 272000, - "prompt": "0.000004", - "completion": "0.000018", - "input_cache_read": "0.0000004", - "input_cache_write": "0.000005" + } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "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": "2026-02-16", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.6-sol-pro:batch", + "canonical_slug": "openai/gpt-5.6-sol-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Sol Pro (batch)", + "created": 1783590854, + "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-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", + "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": "0.0000002", + "input_cache_write": "0.0000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000004", + "completion": "0.000015", + "input_cache_read": "0.0000004", + "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_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": "2026-02-16", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints" + }, + "endpoints": ["/api/v1/batches"], + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.6-sol:batch", + "canonical_slug": "openai/gpt-5.6-sol-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Sol (batch)", + "created": 1783590850, + "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...", + "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": "0.0000002", + "input_cache_write": "0.0000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000004", + "completion": "0.000015", + "input_cache_read": "0.0000004", + "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_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": "2026-02-16", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints" + }, + "endpoints": ["/api/v1/batches"], + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 78.3, + "agentic_index": 47.4 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.6-terra", + "canonical_slug": "openai/gpt-5.6-terra-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Terra", + "created": 1783590857, + "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and 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": "0.000002", + "completion": "0.000012", + "web_search": "0.01", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000004", + "completion": "0.000018", + "input_cache_read": "0.0000004", + "input_cache_write": "0.000005" } ] }, @@ -27456,10 +28475,16 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 42.1, + "intelligence_index": 32.3, "coding_index": 76.7, "agentic_index": 43.2 } @@ -27535,6 +28560,12 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -27603,6 +28634,7 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": false, "default_enabled": true, @@ -27671,10 +28703,11 @@ "links": { "details": "/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 42.1, + "intelligence_index": 32.3, "coding_index": 76.7, "agentic_index": 43.2 } @@ -27743,10 +28776,16 @@ "links": { "details": "/api/v1/models/openai/gpt-6-astra-20260903/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 52.7, + "intelligence_index": 56.9, "coding_index": 76.9, "agentic_index": 51 } @@ -27815,6 +28854,12 @@ "links": { "details": "/api/v1/models/openai/gpt-6-astra-pro-20260903/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -27878,6 +28923,7 @@ "links": { "details": "/api/v1/models/openai/gpt-6-astra-pro-20260903/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true, "default_enabled": true, @@ -27941,10 +28987,11 @@ "links": { "details": "/api/v1/models/openai/gpt-6-astra-20260903/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 52.7, + "intelligence_index": 56.9, "coding_index": 76.9, "agentic_index": 51 } @@ -28020,10 +29067,16 @@ "links": { "details": "/api/v1/models/openai/gpt-6-luna-20260922/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 38.1, + "intelligence_index": 27.9, "coding_index": null, "agentic_index": null } @@ -28099,6 +29152,12 @@ "links": { "details": "/api/v1/models/openai/gpt-6-luna-pro-20260922/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -28169,6 +29228,7 @@ "links": { "details": "/api/v1/models/openai/gpt-6-luna-pro-20260922/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": false, "default_enabled": true, @@ -28239,10 +29299,11 @@ "links": { "details": "/api/v1/models/openai/gpt-6-luna-20260922/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 38.1, + "intelligence_index": 27.9, "coding_index": null, "agentic_index": null } @@ -28318,10 +29379,16 @@ "links": { "details": "/api/v1/models/openai/gpt-6-sol-20260922/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 47.6, + "intelligence_index": 44.2, "coding_index": null, "agentic_index": null } @@ -28397,6 +29464,12 @@ "links": { "details": "/api/v1/models/openai/gpt-6-sol-pro-20260922/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -28467,6 +29540,7 @@ "links": { "details": "/api/v1/models/openai/gpt-6-sol-pro-20260922/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": false, "default_enabled": true, @@ -28537,10 +29611,11 @@ "links": { "details": "/api/v1/models/openai/gpt-6-sol-20260922/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 47.6, + "intelligence_index": 44.2, "coding_index": null, "agentic_index": null } @@ -28609,74 +29684,101 @@ "links": { "details": "/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1297, + "win_rate": 69.3, + "rank": 2 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1189, + "win_rate": 52.9, + "rank": 6 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1212, - "win_rate": 49.2, - "rank": 16 + "elo": 1231, + "win_rate": 52.7, + "rank": 11 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1133, + "win_rate": 41.4, + "rank": 24 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1235, - "win_rate": 52.3, - "rank": 7 + "elo": 1297, + "win_rate": 53, + "rank": 4 }, { "arena": "agents", "category": "webapps", - "elo": 1306, - "win_rate": 60.3, - "rank": 4 + "elo": 1280, + "win_rate": 57.8, + "rank": 8 }, { "arena": "models", "category": "3d", - "elo": 1463, - "win_rate": 70.6, - "rank": 2 + "elo": 1435, + "win_rate": 58.3, + "rank": 4 }, { "arena": "models", "category": "codecategories", - "elo": 1345, - "win_rate": 58.4, - "rank": 6 + "elo": 1359, + "win_rate": 56.4, + "rank": 3 }, { "arena": "models", "category": "dataviz", - "elo": 1284, - "win_rate": 51.4, + "elo": 1285, + "win_rate": 53.3, "rank": 18 }, { "arena": "models", "category": "gamedev", - "elo": 1390, - "win_rate": 63.9, - "rank": 3 + "elo": 1414, + "win_rate": 60.3, + "rank": 2 }, { "arena": "models", "category": "uicomponent", - "elo": 1322, - "win_rate": 54.9, - "rank": 11 + "elo": 1341, + "win_rate": 58.3, + "rank": 7 }, { "arena": "models", "category": "website", - "elo": 1321, - "win_rate": 55.8, - "rank": 6 + "elo": 1314, + "win_rate": 53.6, + "rank": 8 } ], "artificial_analysis": { - "intelligence_index": 51.8, + "intelligence_index": 54.6, "coding_index": null, "agentic_index": null } @@ -28752,6 +29854,12 @@ "links": { "details": "/api/v1/models/openai/gpt-6.1-sol-pro-20260929/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -28822,6 +29930,7 @@ "links": { "details": "/api/v1/models/openai/gpt-6.1-sol-pro-20260929/endpoints" }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true, "default_enabled": true, @@ -28885,74 +29994,96 @@ "links": { "details": "/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1297, + "win_rate": 69.3, + "rank": 2 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1189, + "win_rate": 52.9, + "rank": 6 + }, { "arena": "agents", "category": "mobileapps", - "elo": 1212, - "win_rate": 49.2, - "rank": 16 + "elo": 1231, + "win_rate": 52.7, + "rank": 11 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1133, + "win_rate": 41.4, + "rank": 24 }, { "arena": "agents", "category": "spreadsheet", - "elo": 1235, - "win_rate": 52.3, - "rank": 7 + "elo": 1297, + "win_rate": 53, + "rank": 4 }, { "arena": "agents", "category": "webapps", - "elo": 1306, - "win_rate": 60.3, - "rank": 4 + "elo": 1280, + "win_rate": 57.8, + "rank": 8 }, { "arena": "models", "category": "3d", - "elo": 1463, - "win_rate": 70.6, - "rank": 2 + "elo": 1435, + "win_rate": 58.3, + "rank": 4 }, { "arena": "models", "category": "codecategories", - "elo": 1345, - "win_rate": 58.4, - "rank": 6 + "elo": 1359, + "win_rate": 56.4, + "rank": 3 }, { "arena": "models", "category": "dataviz", - "elo": 1284, - "win_rate": 51.4, + "elo": 1285, + "win_rate": 53.3, "rank": 18 }, { "arena": "models", "category": "gamedev", - "elo": 1390, - "win_rate": 63.9, - "rank": 3 + "elo": 1414, + "win_rate": 60.3, + "rank": 2 }, { "arena": "models", "category": "uicomponent", - "elo": 1322, - "win_rate": 54.9, - "rank": 11 + "elo": 1341, + "win_rate": 58.3, + "rank": 7 }, { "arena": "models", "category": "website", - "elo": 1321, - "win_rate": 55.8, - "rank": 6 + "elo": 1314, + "win_rate": 53.6, + "rank": 8 } ], "artificial_analysis": { - "intelligence_index": 51.8, + "intelligence_index": 54.6, "coding_index": null, "agentic_index": null } @@ -28964,6 +30095,304 @@ "default_effort": "medium" } }, + { + "id": "openai/gpt-6.1-terra", + "canonical_slug": "openai/gpt-6.1-terra-20261026", + "hugging_face_id": null, + "name": "OpenAI: GPT-6.1 Terra", + "created": 1793038409, + "description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000005", + "web_search": "0.01", + "input_cache_read": "0.00000005", + "input_cache_write": "0.00000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000002", + "completion": "0.0000075", + "input_cache_read": "0.0000001", + "input_cache_write": "0.0000025" + } + ] + }, + "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, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-6.1-terra-20261026/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 51.3, + "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-terra-pro", + "canonical_slug": "openai/gpt-6.1-terra-pro-20261026", + "hugging_face_id": null, + "name": "OpenAI: GPT-6.1 Terra Pro", + "created": 1793038556, + "description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), 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": "0.000001", + "completion": "0.000005", + "web_search": "0.01", + "input_cache_read": "0.00000005", + "input_cache_write": "0.00000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000002", + "completion": "0.0000075", + "input_cache_read": "0.0000001", + "input_cache_write": "0.0000025" + } + ] + }, + "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-terra-pro-20261026/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-6.1-terra-pro:batch", + "canonical_slug": "openai/gpt-6.1-terra-pro-20261026", + "hugging_face_id": null, + "name": "OpenAI: GPT-6.1 Terra Pro (batch)", + "created": 1793038556, + "description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), 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": "0.0000005", + "completion": "0.0000025", + "web_search": "0.01", + "input_cache_read": "0.000000025", + "input_cache_write": "0.000000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000001", + "completion": "0.00000375", + "input_cache_read": "0.00000005", + "input_cache_write": "0.00000125" + } + ] + }, + "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-6.1-terra-pro-20261026/endpoints" + }, + "endpoints": ["/api/v1/batches"], + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-6.1-terra:batch", + "canonical_slug": "openai/gpt-6.1-terra-20261026", + "hugging_face_id": null, + "name": "OpenAI: GPT-6.1 Terra (batch)", + "created": 1793038409, + "description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000005", + "completion": "0.0000025", + "web_search": "0.01", + "input_cache_read": "0.000000025", + "input_cache_write": "0.000000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000001", + "completion": "0.00000375", + "input_cache_read": "0.00000005", + "input_cache_write": "0.00000125" + } + ] + }, + "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": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-6.1-terra-20261026/endpoints" + }, + "endpoints": ["/api/v1/batches"], + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 51.3, + "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-audio", "canonical_slug": "openai/gpt-audio", @@ -29020,7 +30449,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-audio/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-audio-mini", @@ -29075,7 +30510,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-audio-mini/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-chat-latest", @@ -29125,7 +30566,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/openai/gpt-chat-latest-20260505/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "openai/gpt-oss-120b", @@ -29143,9 +30590,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "input_cache_read": "0.000000075" + "prompt": "0.000000025", + "completion": "0.000000092", + "input_cache_read": "0.000000022" }, "top_provider": { "context_length": 131072, @@ -29187,53 +30634,59 @@ "links": { "details": "/api/v1/models/openai/gpt-oss-120b/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 901, + "elo": 898, "win_rate": 29.4, - "rank": 120 + "rank": 123 }, { "arena": "models", "category": "codecategories", - "elo": 963, + "elo": 961, "win_rate": 33.4, - "rank": 131 + "rank": 135 }, { "arena": "models", "category": "dataviz", "elo": 987, "win_rate": 43.6, - "rank": 118 + "rank": 119 }, { "arena": "models", "category": "gamedev", "elo": 992, "win_rate": 40.5, - "rank": 123 + "rank": 124 }, { "arena": "models", "category": "uicomponent", - "elo": 927, + "elo": 921, "win_rate": 35.7, - "rank": 124 + "rank": 128 }, { "arena": "models", "category": "website", - "elo": 968, + "elo": 966, "win_rate": 32.5, - "rank": 135 + "rank": 137 } ], "artificial_analysis": { - "intelligence_index": 11.6, + "intelligence_index": null, "coding_index": 30.4, "agentic_index": 3.7 } @@ -29300,53 +30753,54 @@ "links": { "details": "/api/v1/models/openai/gpt-oss-120b/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 901, + "elo": 898, "win_rate": 29.4, - "rank": 120 + "rank": 123 }, { "arena": "models", "category": "codecategories", - "elo": 963, + "elo": 961, "win_rate": 33.4, - "rank": 131 + "rank": 135 }, { "arena": "models", "category": "dataviz", "elo": 987, "win_rate": 43.6, - "rank": 118 + "rank": 119 }, { "arena": "models", "category": "gamedev", "elo": 992, "win_rate": 40.5, - "rank": 123 + "rank": 124 }, { "arena": "models", "category": "uicomponent", - "elo": 927, + "elo": 921, "win_rate": 35.7, - "rank": 124 + "rank": 128 }, { "arena": "models", "category": "website", - "elo": 968, + "elo": 966, "win_rate": 32.5, - "rank": 135 + "rank": 137 } ], "artificial_analysis": { - "intelligence_index": 11.6, + "intelligence_index": null, "coding_index": 30.4, "agentic_index": 3.7 } @@ -29373,13 +30827,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000018", - "completion": "0.00000009", - "input_cache_read": "0.000000009" + "prompt": "0.00000003", + "completion": "0.00000013", + "input_cache_read": "0.00000003" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 32768, + "max_completion_tokens": 117964, "is_moderated": false }, "per_request_limits": null, @@ -29416,6 +30870,12 @@ "links": { "details": "/api/v1/models/openai/gpt-oss-20b/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -29423,20 +30883,20 @@ "category": "dataviz", "elo": 933, "win_rate": 39.7, - "rank": 124 + "rank": 125 }, { "arena": "models", "category": "website", "elo": 852, "win_rate": 27.9, - "rank": 141 + "rank": 143 } ], "artificial_analysis": { - "intelligence_index": 10, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 20.7, + "agentic_index": 1.2 } }, "reasoning": { @@ -29501,6 +30961,7 @@ "links": { "details": "/api/v1/models/openai/gpt-oss-20b/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { @@ -29508,20 +30969,20 @@ "category": "dataviz", "elo": 933, "win_rate": 39.7, - "rank": 124 + "rank": 125 }, { "arena": "models", "category": "website", "elo": 852, "win_rate": 27.9, - "rank": 141 + "rank": 143 } ], "artificial_analysis": { - "intelligence_index": 10, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 20.7, + "agentic_index": 1.2 } }, "reasoning": { @@ -29576,122 +31037,12 @@ "links": { "details": "/api/v1/models/openai/gpt-oss-safeguard-20b/endpoints" }, - "reasoning": { - "mandatory": true - } - }, - { - "id": "openai/o1", - "canonical_slug": "openai/o1-2024-12-17", - "hugging_face_id": "", - "name": "OpenAI: o1", - "created": 1734459999, - "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...", - "context_length": 200000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000015", - "completion": "0.00006", - "web_search": "0.01", - "input_cache_read": "0.0000075" - }, - "top_provider": { - "context_length": 200000, - "max_completion_tokens": 100000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2023-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/o1-2024-12-17/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 15.2, - "coding_index": 39.7, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": true - } - }, - { - "id": "openai/o1-pro", - "canonical_slug": "openai/o1-pro", - "hugging_face_id": "", - "name": "OpenAI: o1-pro", - "created": 1742423211, - "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...", - "context_length": 200000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00015", - "completion": "0.0006", - "web_search": "0.01" - }, - "top_provider": { - "context_length": 200000, - "max_completion_tokens": 100000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/o1-pro/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 12.4, - "coding_index": null, - "agentic_index": null - } - }, "reasoning": { "mandatory": true } @@ -29740,180 +31091,55 @@ "links": { "details": "/api/v1/models/openai/o3-2025-04-16/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1020, + "elo": 1018, "win_rate": 51.9, - "rank": 122 + "rank": 126 }, { "arena": "models", "category": "dataviz", "elo": 1200, "win_rate": 48.1, - "rank": 61 + "rank": 62 }, { "arena": "models", "category": "gamedev", "elo": 1034, "win_rate": 56.9, - "rank": 117 + "rank": 118 }, { "arena": "models", "category": "uicomponent", - "elo": 1017, + "elo": 1011, "win_rate": 53.3, - "rank": 114 + "rank": 118 }, { "arena": "models", "category": "website", "elo": 1036, "win_rate": 53.8, - "rank": 124 + "rank": 126 } - ], - "artificial_analysis": { - "intelligence_index": 20.2, - "coding_index": null, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": true - } - }, - { - "id": "openai/o3-mini", - "canonical_slug": "openai/o3-mini-2025-01-31", - "hugging_face_id": "", - "name": "OpenAI: o3 Mini", - "created": 1738351721, - "description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...", - "context_length": 200000, - "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", - "web_search": "0.01", - "input_cache_read": "0.00000055" - }, - "top_provider": { - "context_length": 200000, - "max_completion_tokens": 100000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2023-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/o3-mini-2025-01-31/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 12.5, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true } }, - { - "id": "openai/o3-mini-high", - "canonical_slug": "openai/o3-mini-high-2025-01-31", - "hugging_face_id": "", - "name": "OpenAI: o3 Mini High", - "created": 1739372611, - "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...", - "context_length": 200000, - "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", - "web_search": "0.01", - "input_cache_read": "0.00000055" - }, - "top_provider": { - "context_length": 200000, - "max_completion_tokens": 100000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "reasoning_effort", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2023-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11, - "coding_index": 16.3, - "agentic_index": 0.9 - } - }, - "reasoning": { - "mandatory": true, - "supported_efforts": ["high"], - "default_effort": "high" - } - }, { "id": "openai/o3-mini:batch", "canonical_slug": "openai/o3-mini-2025-01-31", @@ -29965,14 +31191,7 @@ "links": { "details": "/api/v1/models/openai/o3-mini-2025-01-31/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 12.5, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": ["/api/v1/batches"], "reasoning": { "mandatory": true } @@ -30024,14 +31243,12 @@ "links": { "details": "/api/v1/models/openai/o3-pro-2025-06-10/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 21.9, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -30080,59 +31297,55 @@ "links": { "details": "/api/v1/models/openai/o3-2025-04-16/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1020, + "elo": 1018, "win_rate": 51.9, - "rank": 122 + "rank": 126 }, { "arena": "models", "category": "dataviz", "elo": 1200, "win_rate": 48.1, - "rank": 61 + "rank": 62 }, { "arena": "models", "category": "gamedev", "elo": 1034, "win_rate": 56.9, - "rank": 117 + "rank": 118 }, { "arena": "models", "category": "uicomponent", - "elo": 1017, + "elo": 1011, "win_rate": 53.3, - "rank": 114 + "rank": 118 }, { "arena": "models", "category": "website", "elo": 1036, "win_rate": 53.8, - "rank": 124 + "rank": 126 } - ], - "artificial_analysis": { - "intelligence_index": 20.2, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true } }, { - "id": "openai/o4-mini", + "id": "openai/o4-mini:batch", "canonical_slug": "openai/o4-mini-2025-04-16", "hugging_face_id": "", - "name": "OpenAI: o4 Mini", + "name": "OpenAI: o4 Mini (batch)", "created": 1744820942, "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...", "context_length": 200000, @@ -30144,10 +31357,10 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", + "prompt": "0.00000055", + "completion": "0.0000022", "web_search": "0.01", - "input_cache_read": "0.000000275" + "input_cache_read": "0.0000001375" }, "top_provider": { "context_length": 200000, @@ -30172,213 +31385,130 @@ "links": { "details": "/api/v1/models/openai/o4-mini-2025-04-16/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 854, + "elo": 851, "win_rate": 34, - "rank": 124 + "rank": 127 }, { "arena": "models", "category": "codecategories", - "elo": 976, + "elo": 974, "win_rate": 46.4, - "rank": 129 + "rank": 133 }, { "arena": "models", "category": "dataviz", "elo": 991, "win_rate": 50, - "rank": 117 + "rank": 118 }, { "arena": "models", "category": "gamedev", "elo": 1003, "win_rate": 50, - "rank": 122 + "rank": 123 }, { "arena": "models", "category": "uicomponent", - "elo": 983, + "elo": 978, "win_rate": 46.9, - "rank": 117 + "rank": 121 }, { "arena": "models", "category": "website", "elo": 985, "win_rate": 47.1, - "rank": 131 + "rank": 133 } - ], - "artificial_analysis": { - "intelligence_index": 16.7, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": true } }, { - "id": "openai/o4-mini-high", - "canonical_slug": "openai/o4-mini-high-2025-04-16", - "hugging_face_id": "", - "name": "OpenAI: o4 Mini High", - "created": 1744824212, - "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...", - "context_length": 200000, + "id": "particle-ai/particle-1", + "canonical_slug": "particle-ai/particle-1-20261027", + "hugging_face_id": null, + "name": "Particle AI: Particle-1", + "created": 1793207893, + "description": "Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...", + "context_length": 1048576, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "GPT", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", - "web_search": "0.01", - "input_cache_read": "0.000000275" + "prompt": "0.00000005", + "completion": "0.0000005", + "input_cache_read": "0.000000003" }, "top_provider": { - "context_length": 200000, - "max_completion_tokens": 100000, - "is_moderated": true + "context_length": 1048576, + "max_completion_tokens": 131072, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logprobs", "max_tokens", + "min_p", + "presence_penalty", "reasoning", "reasoning_effort", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", + "temperature", "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2024-06-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints" - }, - "reasoning": { - "mandatory": true, - "supported_efforts": ["high"], - "default_effort": "high" - } - }, - { - "id": "openai/o4-mini:batch", - "canonical_slug": "openai/o4-mini-2025-04-16", - "hugging_face_id": "", - "name": "OpenAI: o4 Mini (batch)", - "created": 1744820942, - "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...", - "context_length": 200000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000055", - "completion": "0.0000022", - "web_search": "0.01", - "input_cache_read": "0.0000001375" - }, - "top_provider": { - "context_length": 200000, - "max_completion_tokens": 100000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" + "tools", + "top_k", + "top_logprobs", + "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/o4-mini-2025-04-16/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 854, - "win_rate": 34, - "rank": 124 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 976, - "win_rate": 46.4, - "rank": 129 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 991, - "win_rate": 50, - "rank": 117 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1003, - "win_rate": 50, - "rank": 122 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 983, - "win_rate": 46.9, - "rank": 117 - }, - { - "arena": "models", - "category": "website", - "elo": 985, - "win_rate": 47.1, - "rank": 131 - } - ], - "artificial_analysis": { - "intelligence_index": 16.7, - "coding_index": null, - "agentic_index": null - } + "details": "/api/v1/models/particle-ai/particle-1-20261027/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": true, + "supported_efforts": [ + "max", + "xhigh", + "high", + "medium", + "low", + "minimal", + "none" + ], + "default_effort": "high" } }, { @@ -30431,6 +31561,12 @@ "links": { "details": "/api/v1/models/perceptron/perceptron-mk1-20260512/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -30481,6 +31617,12 @@ "links": { "details": "/api/v1/models/perceptron/perceptron-mk1.5-20260925/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "supported_efforts": ["high", "medium", "low", "minimal", "none"], @@ -30529,14 +31671,12 @@ "links": { "details": "/api/v1/models/perplexity/sonar/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "perplexity/sonar-deep-research", @@ -30583,6 +31723,12 @@ "links": { "details": "/api/v1/models/perplexity/sonar-deep-research/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -30629,14 +31775,12 @@ "links": { "details": "/api/v1/models/perplexity/sonar-pro/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.6, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "perplexity/sonar-pro-search", @@ -30687,6 +31831,12 @@ "links": { "details": "/api/v1/models/perplexity/sonar-pro-search/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -30735,207 +31885,93 @@ "links": { "details": "/api/v1/models/perplexity/sonar-reasoning-pro/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.8, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } }, { - "id": "poolside/laguna-s-2.1", - "canonical_slug": "poolside/laguna-s-2.1-20260720", - "hugging_face_id": "poolside/Laguna-S-2.1", - "name": "Poolside: Laguna S 2.1", - "created": 1784652683, - "description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...", - "context_length": 1048576, + "id": "prism-ml/ternary-bonsai-2-27b", + "canonical_slug": "prism-ml/ternary-bonsai-2-27b-20260918", + "hugging_face_id": "prism-ml/Ternary-Bonsai-2-27B-gguf", + "name": "PrismML: Ternary Bonsai 2 27B", + "created": 1789754046, + "description": "Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.00000018", - "input_cache_read": "0.000000009" + "prompt": "0.000000075", + "completion": "0.0000005", + "input_cache_read": "0.0000000375" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 131072, + "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", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", "temperature", "tool_choice", - "tools" + "tools", + "top_k", + "top_logprobs", + "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": 20 + }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-10-31", + "expiration_date": null, "links": { - "details": "/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints" + "details": "/api/v1/models/prism-ml/ternary-bonsai-2-27b-20260918/endpoints" }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, - { - "id": "poolside/laguna-s-2.1:free", - "canonical_slug": "poolside/laguna-s-2.1-20260720", - "hugging_face_id": "poolside/Laguna-S-2.1", - "name": "Poolside: Laguna S 2.1 (free)", - "created": 1784652683, - "description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...", - "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": [ - "include_reasoning", - "max_tokens", - "reasoning", - "temperature", - "tool_choice", - "tools" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-31", - "links": { - "details": "/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, - { - "id": "poolside/laguna-xs-2.1", - "canonical_slug": "poolside/laguna-xs-2.1-20260625", - "hugging_face_id": "poolside/Laguna-XS-2.1", - "name": "Poolside: Laguna XS 2.1", - "created": 1783002429, - "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000006", - "completion": "0.00000012", - "input_cache_read": "0.00000003" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "temperature", - "tool_choice", - "tools" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-31", - "links": { - "details": "/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, - { - "id": "poolside/laguna-xs-2.1:free", - "canonical_slug": "poolside/laguna-xs-2.1-20260625", - "hugging_face_id": "poolside/Laguna-XS-2.1", - "name": "Poolside: Laguna XS 2.1 (free)", - "created": 1783002429, - "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...", - "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": [ - "include_reasoning", - "max_tokens", - "reasoning", - "temperature", - "tool_choice", - "tools" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-10-31", - "links": { - "details": "/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints" - }, "reasoning": { "mandatory": false, - "default_enabled": true + "default_enabled": true, + "supported_efforts": ["xhigh", "medium", "none"], + "default_effort": "xhigh" } }, { - "id": "prism-ml/ternary-bonsai-2-27b", - "canonical_slug": "prism-ml/ternary-bonsai-2-27b-20260918", - "hugging_face_id": "prism-ml/Ternary-Bonsai-2-27B-gguf", - "name": "PrismML: Ternary Bonsai 2 27B", - "created": 1789754046, - "description": "Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...", + "id": "prism-ml/ternary-bonsai-2-9b", + "canonical_slug": "prism-ml/ternary-bonsai-2-9b-20261015", + "hugging_face_id": "prism-ml/Ternary-Bonsai-2-9B-gguf", + "name": "PrismML: Ternary Bonsai 2 9B", + "created": 1792130995, + "description": "Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...", "context_length": 262144, "architecture": { "modality": "text+image->text", @@ -30945,13 +31981,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000075", - "completion": "0.0000005", - "input_cache_read": "0.0000000375" + "prompt": "0.00000008", + "completion": "0.00000013", + "input_cache_read": "0.00000004" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 32768, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -30962,7 +31998,6 @@ "max_tokens", "presence_penalty", "reasoning", - "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -30984,13 +32019,17 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/prism-ml/ternary-bonsai-2-27b-20260918/endpoints" + "details": "/api/v1/models/prism-ml/ternary-bonsai-2-9b-20261015/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, - "default_enabled": true, - "supported_efforts": ["xhigh", "medium", "none"], - "default_effort": "xhigh" + "default_enabled": true } }, { @@ -31042,14 +32081,12 @@ "links": { "details": "/api/v1/models/qwen/qwen-2.5-72b-instruct/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen-2.5-7b-instruct", @@ -31102,7 +32139,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen-2.5-7b-instruct/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen-2.5-coder-32b-instruct", @@ -31150,14 +32193,12 @@ "links": { "details": "/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.7, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen-plus", @@ -31217,7 +32258,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen2.5-vl-72b-instruct", @@ -31267,7 +32314,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3-14b", @@ -31322,12 +32375,18 @@ "links": { "details": "/api/v1/models/qwen/qwen3-14b-04-28/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 6.7, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 13.8, + "agentic_index": 0.9 } }, "reasoning": { @@ -31350,12 +32409,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.00000055" + "prompt": "0.00000014", + "completion": "0.0000008", + "input_cache_read": "0.00000005" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, + "context_length": 131072, + "max_completion_tokens": 117964, "is_moderated": false }, "per_request_limits": null, @@ -31385,56 +32445,57 @@ "links": { "details": "/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 994, + "elo": 991, "win_rate": 41.1, - "rank": 112 + "rank": 115 }, { "arena": "models", "category": "codecategories", - "elo": 1039, + "elo": 1037, "win_rate": 42.6, - "rank": 116 + "rank": 120 }, { "arena": "models", "category": "dataviz", "elo": 1070, "win_rate": 49, - "rank": 108 + "rank": 109 }, { "arena": "models", "category": "gamedev", - "elo": 952, + "elo": 950, "win_rate": 35, - "rank": 131 + "rank": 132 }, { "arena": "models", "category": "uicomponent", - "elo": 965, + "elo": 960, "win_rate": 38.4, - "rank": 118 + "rank": 122 }, { "arena": "models", "category": "website", - "elo": 1058, + "elo": 1056, "win_rate": 43.6, - "rank": 118 + "rank": 121 } - ], - "artificial_analysis": { - "intelligence_index": 12, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -31486,53 +32547,59 @@ "links": { "details": "/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 998, + "elo": 995, "win_rate": 40.4, - "rank": 111 + "rank": 114 }, { "arena": "models", "category": "codecategories", - "elo": 1033, + "elo": 1031, "win_rate": 40.8, - "rank": 118 + "rank": 122 }, { "arena": "models", "category": "dataviz", "elo": 950, "win_rate": 32.6, - "rank": 121 + "rank": 122 }, { "arena": "models", "category": "gamedev", "elo": 957, "win_rate": 34.2, - "rank": 129 + "rank": 130 }, { "arena": "models", "category": "uicomponent", - "elo": 945, + "elo": 940, "win_rate": 34, - "rank": 122 + "rank": 126 }, { "arena": "models", "category": "website", - "elo": 1053, + "elo": 1051, "win_rate": 42, - "rank": 120 + "rank": 122 } ], "artificial_analysis": { - "intelligence_index": 12.7, + "intelligence_index": null, "coding_index": 22.1, "agentic_index": 1.3 } @@ -31596,49 +32663,50 @@ "links": { "details": "/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 942, + "elo": 940, "win_rate": 37.5, - "rank": 132 + "rank": 136 }, { "arena": "models", "category": "dataviz", "elo": 967, "win_rate": 39, - "rank": 120 + "rank": 121 }, { "arena": "models", "category": "gamedev", - "elo": 899, + "elo": 897, "win_rate": 33.9, - "rank": 136 + "rank": 137 }, { "arena": "models", "category": "uicomponent", - "elo": 946, + "elo": 940, "win_rate": 42.4, - "rank": 121 + "rank": 127 }, { "arena": "models", "category": "website", - "elo": 955, + "elo": 953, "win_rate": 37.7, - "rank": 136 + "rank": 138 } - ], - "artificial_analysis": { - "intelligence_index": 7.6, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -31661,8 +32729,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.0000003" + "prompt": "0.0000001", + "completion": "0.0000003", + "input_cache_read": "0.0000001" }, "top_provider": { "context_length": 262144, @@ -31695,14 +32764,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.5, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3-32b", @@ -31758,12 +32825,18 @@ "links": { "details": "/api/v1/models/qwen/qwen3-32b-04-28/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 7.3, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 15.3, + "agentic_index": 0.9 } }, "reasoning": { @@ -31799,7 +32872,6 @@ "supported_parameters": [ "frequency_penalty", "logit_bias", - "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -31812,7 +32884,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, @@ -31822,49 +32893,50 @@ "links": { "details": "/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 1143, + "elo": 1141, "win_rate": 61.2, - "rank": 89 + "rank": 93 }, { "arena": "models", "category": "dataviz", "elo": 1084, "win_rate": 54.9, - "rank": 105 + "rank": 106 }, { "arena": "models", "category": "gamedev", "elo": 1099, "win_rate": 58.7, - "rank": 96 + "rank": 97 }, { "arena": "models", "category": "uicomponent", - "elo": 1113, + "elo": 1107, "win_rate": 61.4, - "rank": 90 + "rank": 94 }, { "arena": "models", "category": "website", - "elo": 1159, + "elo": 1157, "win_rate": 61.7, - "rank": 89 + "rank": 92 } - ], - "artificial_analysis": { - "intelligence_index": 11.9, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -31883,13 +32955,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000007", - "completion": "0.00000028" + "prompt": "0.00000015", + "completion": "0.0000006" }, "top_provider": { "context_length": 262144, "max_completion_tokens": 235929, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -31911,6 +32983,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -31918,28 +32996,23 @@ "category": "dataviz", "elo": 1085, "win_rate": 54.7, - "rank": 104 + "rank": 105 }, { "arena": "models", "category": "uicomponent", - "elo": 1046, + "elo": 1041, "win_rate": 54.1, - "rank": 105 + "rank": 110 }, { "arena": "models", "category": "website", "elo": 1087, "win_rate": 57.1, - "rank": 112 + "rank": 114 } - ], - "artificial_analysis": { - "intelligence_index": 9.6, - "coding_index": null, - "agentic_index": null - } + ] } }, { @@ -32010,7 +33083,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/qwen/qwen3-coder-flash/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3-coder-next", @@ -32067,10 +33146,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3-coder-next-2025-02-03/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 9.2, + "intelligence_index": null, "coding_index": 36.2, "agentic_index": 0.9 } @@ -32092,12 +33177,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.0000011" + "prompt": "0.0000001", + "completion": "0.0000011", + "input_cache_read": "0.00000007" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 16384, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -32127,81 +33213,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 9.6, - "coding_index": null, - "agentic_index": null - } - } - }, - { - "id": "qwen/qwen3-next-80b-a3b-thinking", - "canonical_slug": "qwen/qwen3-next-80b-a3b-thinking-2509", - "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", - "name": "Qwen: Qwen3 Next 80B A3B Thinking", - "created": 1757612284, - "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000015", - "completion": "0.0000012" - }, - "top_provider": { - "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", - "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, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-09-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.2, - "coding_index": 17.4, - "agentic_index": null - } - }, - "reasoning": { - "mandatory": true - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3-vl-235b-a22b-instruct", @@ -32259,14 +33276,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 9.9, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3-vl-30b-a3b-instruct", @@ -32326,14 +33341,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.9, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3-vl-30b-a3b-thinking", @@ -32387,14 +33400,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 9.5, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -32454,14 +33465,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.3, - "coding_index": null, - "agentic_index": null - } - } + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "qwen/qwen3.5-122b-a10b", @@ -32479,8 +33488,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.0000032" + "prompt": "0.00000026", + "completion": "0.00000208" }, "top_provider": { "context_length": 262144, @@ -32523,12 +33532,18 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 17.7, - "coding_index": 43.3, - "agentic_index": null + "intelligence_index": null, + "coding_index": 45.7, + "agentic_index": 7.6 } }, "reasoning": { @@ -32551,13 +33566,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000027", - "completion": "0.00000216", - "input_cache_read": "0.00000027" + "prompt": "0.00000026", + "completion": "0.0000026" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 65536, + "max_completion_tokens": 81920, "is_moderated": false }, "per_request_limits": null, @@ -32596,14 +33610,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-27b-20260224/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 22.9, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -32669,11 +33681,17 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 19.3, - "coding_index": null, + "intelligence_index": null, + "coding_index": 37, "agentic_index": null } }, @@ -32742,28 +33760,34 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1161, + "elo": 1158, "win_rate": 56.7, - "rank": 65 + "rank": 66 }, { "arena": "models", "category": "codecategories", - "elo": 1180, + "elo": 1178, "win_rate": 52.6, - "rank": 67 + "rank": 70 }, { "arena": "models", "category": "dataviz", "elo": 1175, "win_rate": 53.2, - "rank": 69 + "rank": 70 }, { "arena": "models", @@ -32775,29 +33799,29 @@ { "arena": "models", "category": "svg", - "elo": 1140, + "elo": 1136, "win_rate": 56.1, - "rank": 50 + "rank": 56 }, { "arena": "models", "category": "uicomponent", - "elo": 1163, + "elo": 1158, "win_rate": 51.4, - "rank": 75 + "rank": 78 }, { "arena": "models", "category": "website", - "elo": 1191, + "elo": 1189, "win_rate": 52.5, - "rank": 69 + "rank": 70 } ], "artificial_analysis": { - "intelligence_index": 21.4, - "coding_index": null, - "agentic_index": null + "intelligence_index": null, + "coding_index": 48.2, + "agentic_index": 8.3 } }, "reasoning": { @@ -32820,13 +33844,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000008", - "completion": "0.00000013", - "input_cache_read": "0.00000004" + "prompt": "0.00000017", + "completion": "0.00000025" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 65536, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -32835,6 +33858,7 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", @@ -32865,12 +33889,18 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-9b-20260310/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 13.3, - "coding_index": 23.5, - "agentic_index": null + "intelligence_index": null, + "coding_index": 28.7, + "agentic_index": 1.2 } }, "reasoning": { @@ -32929,6 +33959,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -32994,63 +34030,69 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1119, + "elo": 1116, "win_rate": 47.7, - "rank": 85 + "rank": 87 }, { "arena": "models", "category": "asciiart", - "elo": 1094, + "elo": 1091, "win_rate": 43.2, - "rank": 62 + "rank": 66 }, { "arena": "models", "category": "codecategories", - "elo": 1167, + "elo": 1165, "win_rate": 48.4, - "rank": 76 + "rank": 79 }, { "arena": "models", "category": "dataviz", "elo": 1135, "win_rate": 44.8, - "rank": 88 + "rank": 89 }, { "arena": "models", "category": "gamedev", "elo": 1105, "win_rate": 42.6, - "rank": 95 + "rank": 96 }, { "arena": "models", "category": "svg", - "elo": 1108, + "elo": 1104, "win_rate": 48.9, - "rank": 59 + "rank": 65 }, { "arena": "models", "category": "uicomponent", - "elo": 1178, + "elo": 1172, "win_rate": 52.2, - "rank": 67 + "rank": 70 }, { "arena": "models", "category": "website", "elo": 1187, "win_rate": 50, - "rank": 73 + "rank": 72 } ] }, @@ -33117,6 +34159,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -33137,9 +34185,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.000002", - "input_cache_read": "0.000000025" + "prompt": "0.00000045", + "completion": "0.0000027" }, "top_provider": { "context_length": 262144, @@ -33182,10 +34229,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3.6-27b-20260422/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 21.4, + "intelligence_index": null, "coding_index": 53.7, "agentic_index": 18.5 } @@ -33212,8 +34265,8 @@ }, "pricing": { "prompt": "0.0000001", - "completion": "0.00000095", - "input_cache_read": "0.00000005" + "completion": "0.0000009", + "input_cache_read": "0.000000025" }, "top_provider": { "context_length": 262144, @@ -33253,10 +34306,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 18.2, + "intelligence_index": null, "coding_index": 41.9, "agentic_index": 13.1 } @@ -33325,6 +34384,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.6-flash/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -33395,67 +34460,73 @@ "links": { "details": "/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1202, - "win_rate": 50.5, - "rank": 49 + "elo": 1199, + "win_rate": 50.4, + "rank": 51 }, { "arena": "models", "category": "asciiart", "elo": 1113, - "win_rate": 40.9, - "rank": 57 + "win_rate": 41.2, + "rank": 60 }, { "arena": "models", "category": "codecategories", - "elo": 1236, - "win_rate": 50.2, - "rank": 48 + "elo": 1234, + "win_rate": 50, + "rank": 49 }, { "arena": "models", "category": "dataviz", "elo": 1228, - "win_rate": 50.8, - "rank": 47 + "win_rate": 50.7, + "rank": 48 }, { "arena": "models", "category": "gamedev", "elo": 1211, - "win_rate": 48.5, + "win_rate": 48.4, "rank": 51 }, { "arena": "models", "category": "svg", - "elo": 1162, - "win_rate": 50.3, - "rank": 40 + "elo": 1158, + "win_rate": 50.1, + "rank": 45 }, { "arena": "models", "category": "uicomponent", - "elo": 1233, - "win_rate": 50.5, - "rank": 49 + "elo": 1227, + "win_rate": 50.3, + "rank": 51 }, { "arena": "models", "category": "website", - "elo": 1243, - "win_rate": 50.1, + "elo": 1241, + "win_rate": 49.9, "rank": 49 } ], "artificial_analysis": { - "intelligence_index": 27, + "intelligence_index": null, "coding_index": 54.5, "agentic_index": null } @@ -33535,6 +34606,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.7-flash-20260727/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -33600,20 +34677,33 @@ "links": { "details": "/api/v1/models/qwen/qwen3.7-max-20260520/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1161, - "win_rate": 46.2, - "rank": 18 + "elo": 1107, + "win_rate": 45.9, + "rank": 20 }, { "arena": "agents", "category": "androidnative", - "elo": 1159, - "win_rate": 48.5, + "elo": 1154, + "win_rate": 48, + "rank": 25 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 980, + "win_rate": 32.9, "rank": 23 }, { @@ -33633,90 +34723,104 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1158, - "win_rate": 43.6, - "rank": 15 + "elo": 1055, + "win_rate": 43.4, + "rank": 17 }, { "arena": "agents", "category": "mobileapps", - "elo": 1155, - "win_rate": 45.2, - "rank": 29 + "elo": 1156, + "win_rate": 45.1, + "rank": 30 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1149, + "win_rate": 44.4, + "rank": 21 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1194, - "win_rate": 47.7, - "rank": 16 + "elo": 1149, + "win_rate": 47.4, + "rank": 20 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1043, + "win_rate": 40, + "rank": 25 }, { "arena": "agents", "category": "webapps", - "elo": 1208, - "win_rate": 48.8, - "rank": 20 + "elo": 1195, + "win_rate": 48.7, + "rank": 21 }, { "arena": "models", "category": "3d", - "elo": 1266, - "win_rate": 54.5, - "rank": 27 + "elo": 1263, + "win_rate": 54.3, + "rank": 29 }, { "arena": "models", "category": "asciiart", - "elo": 1211, - "win_rate": 53.2, - "rank": 20 + "elo": 1208, + "win_rate": 53, + "rank": 24 }, { "arena": "models", "category": "codecategories", - "elo": 1275, - "win_rate": 54, - "rank": 27 + "elo": 1274, + "win_rate": 53.9, + "rank": 29 }, { "arena": "models", "category": "dataviz", - "elo": 1275, + "elo": 1276, "win_rate": 52.9, - "rank": 25 + "rank": 23 }, { "arena": "models", "category": "gamedev", "elo": 1265, - "win_rate": 53, + "win_rate": 52.7, "rank": 29 }, { "arena": "models", "category": "svg", - "elo": 1217, - "win_rate": 55.4, - "rank": 20 + "elo": 1213, + "win_rate": 55, + "rank": 24 }, { "arena": "models", "category": "uicomponent", - "elo": 1270, - "win_rate": 53.3, - "rank": 33 + "elo": 1265, + "win_rate": 53.2, + "rank": 35 }, { "arena": "models", "category": "website", "elo": 1274, - "win_rate": 54.4, - "rank": 27 + "win_rate": 54.5, + "rank": 26 } ], "artificial_analysis": { - "intelligence_index": 29.5, + "intelligence_index": null, "coding_index": 66, "agentic_index": 22.5 } @@ -33787,67 +34891,73 @@ "links": { "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1239, - "win_rate": 48.5, - "rank": 38 + "elo": 1236, + "win_rate": 48.4, + "rank": 40 }, { "arena": "models", "category": "asciiart", - "elo": 1143, - "win_rate": 41.8, - "rank": 46 + "elo": 1138, + "win_rate": 41.3, + "rank": 52 }, { "arena": "models", "category": "codecategories", - "elo": 1269, - "win_rate": 50.3, - "rank": 31 + "elo": 1267, + "win_rate": 50.1, + "rank": 34 }, { "arena": "models", "category": "dataviz", "elo": 1276, - "win_rate": 51.1, - "rank": 23 + "win_rate": 51, + "rank": 24 }, { "arena": "models", "category": "gamedev", "elo": 1262, - "win_rate": 49.5, - "rank": 35 + "win_rate": 49.4, + "rank": 34 }, { "arena": "models", "category": "svg", - "elo": 1208, - "win_rate": 46.7, - "rank": 23 + "elo": 1207, + "win_rate": 47, + "rank": 27 }, { "arena": "models", "category": "uicomponent", - "elo": 1261, - "win_rate": 48.9, + "elo": 1258, + "win_rate": 49, "rank": 37 }, { "arena": "models", "category": "website", - "elo": 1269, - "win_rate": 50.5, - "rank": 31 + "elo": 1267, + "win_rate": 50.3, + "rank": 34 } ], "artificial_analysis": { - "intelligence_index": 25.2, + "intelligence_index": null, "coding_index": 55.9, "agentic_index": 17.5 } @@ -33907,67 +35017,68 @@ "links": { "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1239, - "win_rate": 48.5, - "rank": 38 + "elo": 1236, + "win_rate": 48.4, + "rank": 40 }, { "arena": "models", "category": "asciiart", - "elo": 1143, - "win_rate": 41.8, - "rank": 46 + "elo": 1138, + "win_rate": 41.3, + "rank": 52 }, { "arena": "models", "category": "codecategories", - "elo": 1269, - "win_rate": 50.3, - "rank": 31 + "elo": 1267, + "win_rate": 50.1, + "rank": 34 }, { "arena": "models", "category": "dataviz", "elo": 1276, - "win_rate": 51.1, - "rank": 23 + "win_rate": 51, + "rank": 24 }, { "arena": "models", "category": "gamedev", "elo": 1262, - "win_rate": 49.5, - "rank": 35 + "win_rate": 49.4, + "rank": 34 }, { "arena": "models", "category": "svg", - "elo": 1208, - "win_rate": 46.7, - "rank": 23 + "elo": 1207, + "win_rate": 47, + "rank": 27 }, { "arena": "models", "category": "uicomponent", - "elo": 1261, - "win_rate": 48.9, + "elo": 1258, + "win_rate": 49, "rank": 37 }, { "arena": "models", "category": "website", - "elo": 1269, - "win_rate": 50.5, - "rank": 31 + "elo": 1267, + "win_rate": 50.3, + "rank": 34 } ], "artificial_analysis": { - "intelligence_index": 25.2, + "intelligence_index": null, "coding_index": 55.9, "agentic_index": 17.5 } @@ -33998,8 +35109,8 @@ "input_cache_read": "0.00000025" }, "top_provider": { - "context_length": 1010000, - "max_completion_tokens": 909000, + "context_length": 1000000, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -34036,10 +35147,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3.8-2.4t-a95b-20260812/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 39.9, + "intelligence_index": null, "coding_index": 71.9, "agentic_index": 50.1 } @@ -34058,7 +35175,7 @@ "name": "Qwen: Qwen3.8 27B", "created": 1786722910, "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...", - "context_length": 1000000, + "context_length": 1024000, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -34067,13 +35184,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000004", - "completion": "0.00000135", - "input_cache_read": "0.000000018" + "prompt": "0.00000015", + "completion": "0.000001875", + "input_cache_read": "0.0000000375" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 65536, + "max_completion_tokens": 235929, "is_moderated": false }, "per_request_limits": null, @@ -34111,10 +35228,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3.8-27b-20260814/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 33.7, + "intelligence_index": 20.1, "coding_index": 68.1, "agentic_index": 45.8 } @@ -34177,6 +35300,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.8-flash-20260826/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -34235,10 +35364,16 @@ "links": { "details": "/api/v1/models/qwen/qwen3.8-max-20260902/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 45.4, + "intelligence_index": 33.7, "coding_index": 76.2, "agentic_index": 56 } @@ -34302,6 +35437,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.8-max-prime-20260923/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -34360,6 +35501,12 @@ "links": { "details": "/api/v1/models/qwen/qwen3.8-omni-flash-20260918/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -34411,6 +35558,12 @@ "links": { "details": "/api/v1/models/recursive/flint-v1.0-20261021/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -34431,13 +35584,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003", + "prompt": "0.00000025", "completion": "0.000001", - "input_cache_read": "0.00000004" + "input_cache_read": "0.00000005" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 943718, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -34470,23 +35623,41 @@ "links": { "details": "/api/v1/models/reflection/beam-1.0-501b-a23b-20261016/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1226, + "win_rate": 44.3, + "rank": 54 + }, { "arena": "models", "category": "gamedev", - "elo": 1224, - "win_rate": 44, - "rank": 47 + "elo": 1206, + "win_rate": 42.1, + "rank": 54 }, { "arena": "models", "category": "website", - "elo": 1250, - "win_rate": 46.1, - "rank": 44 + "elo": 1234, + "win_rate": 45.5, + "rank": 52 } - ] + ], + "artificial_analysis": { + "intelligence_index": 17.7, + "coding_index": null, + "agentic_index": null + } }, "reasoning": { "mandatory": true, @@ -34548,6 +35719,12 @@ "links": { "details": "/api/v1/models/rekaai/reka-edge-2603/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -34606,14 +35783,12 @@ "links": { "details": "/api/v1/models/rekaai/reka-flash-3/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 6.4, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -34654,7 +35829,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/relace/relace-apply-3/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "relace/relace-search", @@ -34701,7 +35882,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/relace/relace-search-20251208/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "sakana/fugu-max", @@ -34753,6 +35940,12 @@ "links": { "details": "/api/v1/models/sakana/fugu-max-20260911/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -34818,6 +36011,12 @@ "links": { "details": "/api/v1/models/sakana/fugu-ultra-20260615/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -34883,6 +36082,12 @@ "links": { "details": "/api/v1/models/sakana/fugu-ultra-v2-20260911/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -34933,6 +36138,12 @@ "links": { "details": "/api/v1/models/sakana/namazu-20260811/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -34988,7 +36199,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/sao10k/l3-lunaris-8b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "sao10k/l3.1-euryale-70b", @@ -35035,7 +36252,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/sao10k/l3.1-euryale-70b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "scaledown/extract", @@ -35069,7 +36292,14 @@ "expiration_date": null, "links": { "details": "/api/v1/models/scaledown/extract-20260928/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses", + "/api/alpha/extractions" + ] }, { "id": "scaledown/summarize", @@ -35103,6 +36333,68 @@ "expiration_date": null, "links": { "details": "/api/v1/models/scaledown/summarize-20260928/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] + }, + { + "id": "stealth/crouton-alpha", + "canonical_slug": "stealth/crouton-alpha", + "hugging_face_id": null, + "name": "Crouton Alpha", + "created": 1793669930, + "description": "Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool use, and document analysis in high-volume, repeated work. 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", + "completion": "0" + }, + "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", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/stealth/crouton-alpha/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "reasoning": { + "mandatory": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "minimal"], + "default_effort": "max" } }, { @@ -35155,14 +36447,12 @@ "links": { "details": "/api/v1/models/stepfun/step-3.5-flash/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 17, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true } @@ -35227,67 +36517,73 @@ "links": { "details": "/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1129, - "win_rate": 40.4, - "rank": 79 + "elo": 1126, + "win_rate": 39.9, + "rank": 83 }, { "arena": "models", "category": "asciiart", - "elo": 1153, - "win_rate": 45, - "rank": 41 + "elo": 1148, + "win_rate": 44.6, + "rank": 46 }, { "arena": "models", "category": "codecategories", - "elo": 1182, - "win_rate": 42.3, - "rank": 66 + "elo": 1180, + "win_rate": 42, + "rank": 69 }, { "arena": "models", "category": "dataviz", - "elo": 1172, - "win_rate": 42.9, + "elo": 1174, + "win_rate": 43, "rank": 71 }, { "arena": "models", "category": "gamedev", - "elo": 1158, - "win_rate": 38.4, + "elo": 1157, + "win_rate": 37.8, "rank": 74 }, { "arena": "models", "category": "svg", - "elo": 1085, - "win_rate": 37.3, - "rank": 64 + "elo": 1081, + "win_rate": 36.7, + "rank": 70 }, { "arena": "models", "category": "uicomponent", - "elo": 1179, + "elo": 1175, "win_rate": 41.9, - "rank": 66 + "rank": 68 }, { "arena": "models", "category": "website", - "elo": 1196, + "elo": 1195, "win_rate": 43.9, "rank": 66 } ], "artificial_analysis": { - "intelligence_index": 19.5, + "intelligence_index": null, "coding_index": 39.6, "agentic_index": null } @@ -35327,7 +36623,6 @@ "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", "min_p", @@ -35360,10 +36655,16 @@ "links": { "details": "/api/v1/models/stepfun/step-5-preview-20261008/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 43.7, + "intelligence_index": 28.5, "coding_index": null, "agentic_index": null } @@ -35417,6 +36718,12 @@ "links": { "details": "/api/v1/models/tencent/hunyuan-a13b-instruct/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -35458,7 +36765,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/tencent/hy-mt2-1.8b-20260521/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "tencent/hy-mt2-30b-a3b", @@ -35499,7 +36812,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/tencent/hy-mt2-30b-a3b-20260521/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "tencent/hy-mt2-7b", @@ -35540,7 +36859,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/tencent/hy-mt2-7b-20260521/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "tencent/hy3", @@ -35619,49 +36944,55 @@ "links": { "details": "/api/v1/models/tencent/hy3-20260706/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1176, - "win_rate": 44, - "rank": 58 + "elo": 1172, + "win_rate": 43.8, + "rank": 61 }, { "arena": "models", "category": "codecategories", - "elo": 1177, - "win_rate": 41.2, - "rank": 69 + "elo": 1175, + "win_rate": 41.1, + "rank": 72 }, { "arena": "models", "category": "dataviz", "elo": 1125, "win_rate": 36.1, - "rank": 93 + "rank": 95 }, { "arena": "models", "category": "gamedev", - "elo": 1136, + "elo": 1134, "win_rate": 38.6, - "rank": 83 + "rank": 84 }, { "arena": "models", "category": "uicomponent", - "elo": 1164, + "elo": 1158, "win_rate": 40.2, - "rank": 74 + "rank": 77 }, { "arena": "models", "category": "website", - "elo": 1182, + "elo": 1180, "win_rate": 41.3, - "rank": 75 + "rank": 76 } ] }, @@ -35723,10 +37054,16 @@ "links": { "details": "/api/v1/models/tencent/hy3-preview-20260421/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 25.3, + "intelligence_index": null, "coding_index": 58.8, "agentic_index": 24.1 } @@ -35738,6 +37075,65 @@ "default_effort": "high" } }, + { + "id": "tencent/hy4", + "canonical_slug": "tencent/hy4-20261104", + "hugging_face_id": "tencent/Hy4", + "name": "Tencent: Hy4", + "created": 1793766031, + "description": "The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000417", + "completion": "0.0000012505", + "input_cache_read": "0.000000021" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/tencent/hy4-20261104/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "low", "none"], + "default_effort": "high" + } + }, { "id": "tencent/hy4-preview", "canonical_slug": "tencent/hy4-preview-20260827", @@ -35784,9 +37180,11 @@ "frequency_penalty", "include_reasoning", "logit_bias", + "logprobs", "max_completion_tokens", "max_tokens", "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", @@ -35799,6 +37197,7 @@ "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -35808,6 +37207,12 @@ "links": { "details": "/api/v1/models/tencent/hy4-preview-20260827/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true, @@ -35867,7 +37272,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "thedrummer/skyfall-36b-v2", @@ -35917,7 +37328,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/thedrummer/skyfall-36b-v2/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "thedrummer/unslopnemo-12b", @@ -35965,7 +37382,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/thedrummer/unslopnemo-12b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "thinkingmachines/inkling", @@ -36003,7 +37426,6 @@ "reasoning", "reasoning_effort", "repetition_penalty", - "seed", "stop", "temperature", "tool_choice", @@ -36025,74 +37447,80 @@ "links": { "details": "/api/v1/models/thinkingmachines/inkling-20260715/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "webapps", - "elo": 1196, + "elo": 1182, "win_rate": 48.6, - "rank": 26 + "rank": 27 }, { "arena": "models", "category": "3d", - "elo": 1161, - "win_rate": 40, - "rank": 64 + "elo": 1155, + "win_rate": 39.7, + "rank": 68 }, { "arena": "models", "category": "asciiart", - "elo": 1089, - "win_rate": 33.6, - "rank": 64 + "elo": 1092, + "win_rate": 34.1, + "rank": 65 }, { "arena": "models", "category": "codecategories", - "elo": 1206, + "elo": 1204, "win_rate": 42.2, - "rank": 58 + "rank": 63 }, { "arena": "models", "category": "dataviz", - "elo": 1159, - "win_rate": 37.5, - "rank": 78 + "elo": 1158, + "win_rate": 37.7, + "rank": 80 }, { "arena": "models", "category": "gamedev", "elo": 1166, - "win_rate": 38, - "rank": 71 + "win_rate": 37.9, + "rank": 72 }, { "arena": "models", "category": "svg", - "elo": 1110, - "win_rate": 34.6, - "rank": 57 + "elo": 1109, + "win_rate": 34.7, + "rank": 63 }, { "arena": "models", "category": "uicomponent", - "elo": 1201, + "elo": 1197, "win_rate": 40.5, - "rank": 58 + "rank": 61 }, { "arena": "models", "category": "website", - "elo": 1224, + "elo": 1223, "win_rate": 44.6, - "rank": 57 + "rank": 58 } ], "artificial_analysis": { - "intelligence_index": 25, + "intelligence_index": 12.5, "coding_index": 52.1, "agentic_index": 22.5 } @@ -36162,77 +37590,16 @@ "links": { "details": "/api/v1/models/thinkingmachines/inkling-small-20260730/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 25.7, - "coding_index": 52.9, - "agentic_index": 23.5 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "high", "medium", "low", "minimal", "none"], - "default_effort": "high" - } - }, - { - "id": "thinkingmachines/inkling-small:free", - "canonical_slug": "thinkingmachines/inkling-small-20260730", - "hugging_face_id": "thinkingmachines/Inkling-Small", - "name": "Thinking Machines: Inkling Small (free)", - "created": 1785443117, - "description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+audio->text", - "input_modalities": ["text", "image", "audio"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 262144, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "reasoning_effort", - "seed", - "stop", - "temperature", - "tools", - "top_p" + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" ], - "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/thinkingmachines/inkling-small-20260730/endpoints" - }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 25.7, + "intelligence_index": 12.9, "coding_index": 52.9, "agentic_index": 23.5 } @@ -36244,137 +37611,6 @@ "default_effort": "high" } }, - { - "id": "thinkingmachines/inkling:free", - "canonical_slug": "thinkingmachines/inkling-20260715", - "hugging_face_id": "thinkingmachines/Inkling", - "name": "Thinking Machines: Inkling (free)", - "created": 1784325956, - "description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+audio->text", - "input_modalities": ["text", "image", "audio"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 262144, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "reasoning_effort", - "seed", - "stop", - "temperature", - "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/thinkingmachines/inkling-20260715/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "webapps", - "elo": 1196, - "win_rate": 48.6, - "rank": 26 - }, - { - "arena": "models", - "category": "3d", - "elo": 1161, - "win_rate": 40, - "rank": 64 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1089, - "win_rate": 33.6, - "rank": 64 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1206, - "win_rate": 42.2, - "rank": 58 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1159, - "win_rate": 37.5, - "rank": 78 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1166, - "win_rate": 38, - "rank": 71 - }, - { - "arena": "models", - "category": "svg", - "elo": 1110, - "win_rate": 34.6, - "rank": 57 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1201, - "win_rate": 40.5, - "rank": 58 - }, - { - "arena": "models", - "category": "website", - "elo": 1224, - "win_rate": 44.6, - "rank": 57 - } - ], - "artificial_analysis": { - "intelligence_index": 25, - "coding_index": 52.1, - "agentic_index": 22.5 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["max", "high", "medium", "low", "minimal", "none"], - "default_effort": "high" - } - }, { "id": "unbiased/pareto-26.10", "canonical_slug": "unbiased/pareto-26.10-20261015", @@ -36414,7 +37650,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/unbiased/pareto-26.10-20261015/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "unbiased/pareto-26.9", @@ -36456,7 +37698,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/unbiased/pareto-26.9-20260917/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "undi95/remm-slerp-l2-13b", @@ -36507,7 +37755,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/undi95/remm-slerp-l2-13b/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "upstage/solar-mini4", @@ -36557,35 +37811,50 @@ "links": { "details": "/api/v1/models/upstage/solar-mini4-20260922/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1080, + "win_rate": 22.8, + "rank": 95 + }, { "arena": "models", "category": "codecategories", - "elo": 1151, - "win_rate": 32, - "rank": 85 + "elo": 1136, + "win_rate": 30.7, + "rank": 97 }, { "arena": "models", "category": "gamedev", - "elo": 1110, - "win_rate": 28.4, - "rank": 94 + "elo": 1114, + "win_rate": 28.7, + "rank": 92 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1088, + "win_rate": 26.6, + "rank": 102 }, { "arena": "models", "category": "website", - "elo": 1159, - "win_rate": 33.3, - "rank": 90 + "elo": 1149, + "win_rate": 32.8, + "rank": 94 } - ], - "artificial_analysis": { - "intelligence_index": 24.1, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -36602,76 +37871,6 @@ "default_effort": "medium" } }, - { - "id": "upstage/solar-pro-3", - "canonical_slug": "upstage/solar-pro-3", - "hugging_face_id": "", - "name": "Upstage: Solar Pro 3", - "created": 1769481200, - "description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "input_cache_read": "0.000000015" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 117964, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "parallel_tool_calls", - "presence_penalty", - "reasoning", - "reasoning_effort", - "response_format", - "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/upstage/solar-pro-3/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.8, - "coding_index": 16.2, - "agentic_index": 1.4 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": false, - "supported_efforts": ["high", "medium", "low", "minimal", "none"], - "default_effort": "medium" - } - }, { "id": "upstage/solar-pro4", "canonical_slug": "upstage/solar-pro4-20260810", @@ -36720,49 +37919,55 @@ "links": { "details": "/api/v1/models/upstage/solar-pro4-20260810/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "webapps", - "elo": 1105, + "elo": 1091, "win_rate": 30, - "rank": 38 + "rank": 39 }, { "arena": "models", "category": "3d", - "elo": 1178, + "elo": 1175, "win_rate": 46.4, - "rank": 57 + "rank": 59 }, { "arena": "models", "category": "codecategories", - "elo": 1182, + "elo": 1180, "win_rate": 39, - "rank": 65 + "rank": 68 }, { "arena": "models", "category": "dataviz", "elo": 1177, "win_rate": 41.3, - "rank": 68 + "rank": 69 }, { "arena": "models", "category": "gamedev", "elo": 1170, "win_rate": 39.9, - "rank": 68 + "rank": 69 }, { "arena": "models", "category": "uicomponent", - "elo": 1150, + "elo": 1145, "win_rate": 35.5, - "rank": 77 + "rank": 80 }, { "arena": "models", @@ -36835,7 +38040,13 @@ "expiration_date": null, "links": { "details": "/api/v1/models/writer/palmyra-x5-20250428/endpoints" - } + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ] }, { "id": "x-ai/grok-4.20", @@ -36900,14 +38111,20 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.20-20260309/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1045, + "elo": 1043, "win_rate": 35, - "rank": 36 + "rank": 38 }, { "arena": "agents", @@ -36928,84 +38145,79 @@ "category": "htmlslides", "elo": 1180, "win_rate": 45.7, - "rank": 11 + "rank": 3 }, { "arena": "agents", "category": "mobileapps", - "elo": 1090, + "elo": 1088, "win_rate": 45.4, - "rank": 43 + "rank": 45 }, { "arena": "agents", "category": "webapps", - "elo": 1144, + "elo": 1131, "win_rate": 49.7, - "rank": 31 + "rank": 32 }, { "arena": "models", "category": "3d", - "elo": 1193, + "elo": 1190, "win_rate": 52.1, - "rank": 52 + "rank": 55 }, { "arena": "models", "category": "asciiart", - "elo": 1175, + "elo": 1172, "win_rate": 48.2, - "rank": 30 + "rank": 33 }, { "arena": "models", "category": "codecategories", - "elo": 1221, + "elo": 1219, "win_rate": 51.8, - "rank": 54 + "rank": 57 }, { "arena": "models", "category": "dataviz", "elo": 1217, "win_rate": 52, - "rank": 53 + "rank": 54 }, { "arena": "models", "category": "gamedev", - "elo": 1193, + "elo": 1191, "win_rate": 50.1, - "rank": 60 + "rank": 61 }, { "arena": "models", "category": "svg", - "elo": 1165, + "elo": 1161, "win_rate": 52.4, - "rank": 38 + "rank": 44 }, { "arena": "models", "category": "uicomponent", - "elo": 1200, + "elo": 1194, "win_rate": 49, - "rank": 59 + "rank": 64 }, { "arena": "models", "category": "website", - "elo": 1229, + "elo": 1228, "win_rate": 51.8, - "rank": 55 + "rank": 56 } - ], - "artificial_analysis": { - "intelligence_index": 25.7, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -37074,6 +38286,12 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -37145,14 +38363,20 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.3-20260430/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1007, - "win_rate": 28.7, - "rank": 24 + "elo": 955, + "win_rate": 28.8, + "rank": 25 }, { "arena": "agents", @@ -37186,8 +38410,15 @@ "arena": "agents", "category": "androidnative", "elo": 962, - "win_rate": 22.7, - "rank": 38 + "win_rate": 22.9, + "rank": 40 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 807, + "win_rate": 15.5, + "rank": 25 }, { "arena": "agents", @@ -37199,23 +38430,30 @@ { "arena": "agents", "category": "godotgamedev", - "elo": 914, - "win_rate": 20.7, + "elo": 925, + "win_rate": 21.6, "rank": 36 }, { "arena": "agents", "category": "htmlslides", - "elo": 1009, + "elo": 905, "win_rate": 28.4, - "rank": 23 + "rank": 25 }, { "arena": "agents", "category": "mobileapps", - "elo": 1059, - "win_rate": 33.6, - "rank": 45 + "elo": 1057, + "win_rate": 33.2, + "rank": 47 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 953, + "win_rate": 21.6, + "rank": 26 }, { "arena": "agents", @@ -37229,74 +38467,81 @@ "category": "python-pptxslides", "elo": 1072, "win_rate": 30.8, - "rank": 26 + "rank": 27 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 966, + "win_rate": 31.4, + "rank": 27 }, { "arena": "agents", "category": "webapps", - "elo": 1126, - "win_rate": 42.8, - "rank": 33 + "elo": 1113, + "win_rate": 42.7, + "rank": 35 }, { "arena": "models", "category": "3d", - "elo": 1125, + "elo": 1121, "win_rate": 40.8, - "rank": 82 + "rank": 84 }, { "arena": "models", "category": "asciiart", - "elo": 1125, - "win_rate": 42.6, - "rank": 54 + "elo": 1123, + "win_rate": 42.4, + "rank": 56 }, { "arena": "models", "category": "codecategories", - "elo": 1187, - "win_rate": 43.7, - "rank": 63 + "elo": 1185, + "win_rate": 43.5, + "rank": 66 }, { "arena": "models", "category": "dataviz", - "elo": 1179, + "elo": 1180, "win_rate": 45, - "rank": 66 + "rank": 67 }, { "arena": "models", "category": "gamedev", - "elo": 1174, - "win_rate": 43.1, - "rank": 65 + "elo": 1170, + "win_rate": 42.6, + "rank": 68 }, { "arena": "models", "category": "svg", - "elo": 1081, - "win_rate": 37, - "rank": 65 + "elo": 1079, + "win_rate": 36.9, + "rank": 71 }, { "arena": "models", "category": "uicomponent", - "elo": 1193, + "elo": 1188, "win_rate": 44.9, - "rank": 62 + "rank": 65 }, { "arena": "models", "category": "website", - "elo": 1196, - "win_rate": 44.1, + "elo": 1195, + "win_rate": 44, "rank": 65 } ], "artificial_analysis": { - "intelligence_index": 24.9, + "intelligence_index": null, "coding_index": 42.2, "agentic_index": 15.5 } @@ -37372,14 +38617,15 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.3-20260430/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1007, - "win_rate": 28.7, - "rank": 24 + "elo": 955, + "win_rate": 28.8, + "rank": 25 }, { "arena": "agents", @@ -37413,8 +38659,15 @@ "arena": "agents", "category": "androidnative", "elo": 962, - "win_rate": 22.7, - "rank": 38 + "win_rate": 22.9, + "rank": 40 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 807, + "win_rate": 15.5, + "rank": 25 }, { "arena": "agents", @@ -37426,23 +38679,30 @@ { "arena": "agents", "category": "godotgamedev", - "elo": 914, - "win_rate": 20.7, + "elo": 925, + "win_rate": 21.6, "rank": 36 }, { "arena": "agents", "category": "htmlslides", - "elo": 1009, + "elo": 905, "win_rate": 28.4, - "rank": 23 + "rank": 25 }, { "arena": "agents", "category": "mobileapps", - "elo": 1059, - "win_rate": 33.6, - "rank": 45 + "elo": 1057, + "win_rate": 33.2, + "rank": 47 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 953, + "win_rate": 21.6, + "rank": 26 }, { "arena": "agents", @@ -37456,74 +38716,81 @@ "category": "python-pptxslides", "elo": 1072, "win_rate": 30.8, - "rank": 26 + "rank": 27 + }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 966, + "win_rate": 31.4, + "rank": 27 }, { "arena": "agents", "category": "webapps", - "elo": 1126, - "win_rate": 42.8, - "rank": 33 + "elo": 1113, + "win_rate": 42.7, + "rank": 35 }, { "arena": "models", "category": "3d", - "elo": 1125, + "elo": 1121, "win_rate": 40.8, - "rank": 82 + "rank": 84 }, { "arena": "models", "category": "asciiart", - "elo": 1125, - "win_rate": 42.6, - "rank": 54 + "elo": 1123, + "win_rate": 42.4, + "rank": 56 }, { "arena": "models", "category": "codecategories", - "elo": 1187, - "win_rate": 43.7, - "rank": 63 + "elo": 1185, + "win_rate": 43.5, + "rank": 66 }, { "arena": "models", "category": "dataviz", - "elo": 1179, + "elo": 1180, "win_rate": 45, - "rank": 66 + "rank": 67 }, { "arena": "models", "category": "gamedev", - "elo": 1174, - "win_rate": 43.1, - "rank": 65 + "elo": 1170, + "win_rate": 42.6, + "rank": 68 }, { "arena": "models", "category": "svg", - "elo": 1081, - "win_rate": 37, - "rank": 65 + "elo": 1079, + "win_rate": 36.9, + "rank": 71 }, { "arena": "models", "category": "uicomponent", - "elo": 1193, + "elo": 1188, "win_rate": 44.9, - "rank": 62 + "rank": 65 }, { "arena": "models", "category": "website", - "elo": 1196, - "win_rate": 44.1, + "elo": 1195, + "win_rate": 44, "rank": 65 } ], "artificial_analysis": { - "intelligence_index": 24.9, + "intelligence_index": null, "coding_index": 42.2, "agentic_index": 15.5 } @@ -37592,20 +38859,40 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.5-20260708/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1236, - "win_rate": 56, - "rank": 5 + "elo": 1182, + "win_rate": 55.8, + "rank": 6 }, { "arena": "agents", "category": "androidnative", - "elo": 1236, - "win_rate": 63.8, + "elo": 1231, + "win_rate": 63.3, + "rank": 9 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1053, + "win_rate": 45.3, + "rank": 17 + }, + { + "arena": "agents", + "category": "codetovideo", + "elo": 1173, + "win_rate": 49.5, "rank": 7 }, { @@ -37625,90 +38912,104 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1205, + "elo": 1101, "win_rate": 52.5, - "rank": 6 + "rank": 10 }, { "arena": "agents", "category": "mobileapps", - "elo": 1220, - "win_rate": 52.8, - "rank": 12 + "elo": 1215, + "win_rate": 51.9, + "rank": 16 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1154, + "win_rate": 45.2, + "rank": 19 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1230, + "elo": 1187, "win_rate": 54.2, "rank": 12 }, + { + "arena": "agents", + "category": "spreadsheet", + "elo": 1129, + "win_rate": 50, + "rank": 15 + }, { "arena": "agents", "category": "webapps", - "elo": 1218, - "win_rate": 53.4, - "rank": 19 + "elo": 1204, + "win_rate": 53.3, + "rank": 20 }, { "arena": "models", "category": "3d", - "elo": 1257, + "elo": 1254, "win_rate": 50.2, - "rank": 30 + "rank": 32 }, { "arena": "models", "category": "asciiart", "elo": 1256, - "win_rate": 54.4, - "rank": 14 + "win_rate": 54.1, + "rank": 16 }, { "arena": "models", "category": "codecategories", - "elo": 1275, + "elo": 1274, "win_rate": 50.9, - "rank": 28 + "rank": 30 }, { "arena": "models", "category": "dataviz", - "elo": 1266, - "win_rate": 49.7, + "elo": 1268, + "win_rate": 49.8, "rank": 28 }, { "arena": "models", "category": "gamedev", - "elo": 1264, - "win_rate": 49.4, - "rank": 31 + "elo": 1262, + "win_rate": 49.3, + "rank": 35 }, { "arena": "models", "category": "svg", - "elo": 1215, - "win_rate": 48.1, - "rank": 22 + "elo": 1208, + "win_rate": 47.6, + "rank": 26 }, { "arena": "models", "category": "uicomponent", - "elo": 1280, - "win_rate": 51.5, + "elo": 1276, + "win_rate": 51.6, "rank": 28 }, { "arena": "models", "category": "website", - "elo": 1281, + "elo": 1280, "win_rate": 52.4, - "rank": 24 + "rank": 25 } ], "artificial_analysis": { - "intelligence_index": 38.8, + "intelligence_index": null, "coding_index": 72.4, "agentic_index": 41.2 } @@ -37779,22 +39080,35 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.6-20260810/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1209, - "win_rate": 46.8, + "elo": 1156, + "win_rate": 46.9, "rank": 9 }, { "arena": "agents", "category": "androidnative", - "elo": 1291, - "win_rate": 61.4, + "elo": 1294, + "win_rate": 62, "rank": 1 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1150, + "win_rate": 49.2, + "rank": 10 + }, { "arena": "agents", "category": "fullstack", @@ -37812,90 +39126,297 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1250, + "elo": 1146, "win_rate": 60.1, - "rank": 3 + "rank": 6 }, { "arena": "agents", "category": "mobileapps", - "elo": 1234, - "win_rate": 55.6, - "rank": 8 + "elo": 1232, + "win_rate": 55.3, + "rank": 10 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1269, + "win_rate": 61.8, + "rank": 5 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1237, - "win_rate": 52.6, + "elo": 1197, + "win_rate": 52.9, "rank": 11 }, { "arena": "agents", "category": "webapps", - "elo": 1248, - "win_rate": 55.8, - "rank": 12 + "elo": 1235, + "win_rate": 55.7, + "rank": 13 }, { "arena": "models", "category": "3d", - "elo": 1277, + "elo": 1273, "win_rate": 52.4, - "rank": 22 + "rank": 23 }, { "arena": "models", "category": "asciiart", - "elo": 1279, - "win_rate": 58.3, - "rank": 7 + "elo": 1272, + "win_rate": 57.1, + "rank": 11 }, { "arena": "models", "category": "codecategories", - "elo": 1292, + "elo": 1290, "win_rate": 52.5, - "rank": 18 + "rank": 20 }, { "arena": "models", "category": "dataviz", - "elo": 1282, + "elo": 1283, "win_rate": 51.4, "rank": 19 }, { "arena": "models", "category": "gamedev", - "elo": 1296, + "elo": 1294, "win_rate": 54, "rank": 20 }, { "arena": "models", "category": "svg", - "elo": 1240, - "win_rate": 48.8, - "rank": 14 + "elo": 1233, + "win_rate": 48.6, + "rank": 18 }, { "arena": "models", "category": "uicomponent", + "elo": 1290, + "win_rate": 53.1, + "rank": 24 + }, + { + "arena": "models", + "category": "website", + "elo": 1287, + "win_rate": 52.2, + "rank": 22 + } + ], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 76.8, + "agentic_index": 53 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "high" + } + }, + { + "id": "x-ai/grok-4.6:batch", + "canonical_slug": "x-ai/grok-4.6-20260810", + "hugging_face_id": null, + "name": "SpaceXAI: Grok 4.6 (batch)", + "created": 1786548957, + "description": "Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).", + "context_length": 500000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Grok", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000016", + "completion": "0.0000048", + "web_search": "0.005", + "input_cache_read": "0.0000004", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000032", + "completion": "0.0000096", + "input_cache_read": "0.0000008" + } + ] + }, + "top_provider": { + "context_length": 500000, + "max_completion_tokens": 450000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/x-ai/grok-4.6-20260810/endpoints" + }, + "endpoints": ["/api/v1/batches"], + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1156, + "win_rate": 46.9, + "rank": 9 + }, + { + "arena": "agents", + "category": "androidnative", "elo": 1294, - "win_rate": 53.3, - "rank": 21 + "win_rate": 62, + "rank": 1 + }, + { + "arena": "agents", + "category": "blender3d", + "elo": 1150, + "win_rate": 49.2, + "rank": 10 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1264, + "win_rate": 54.9, + "rank": 7 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1276, + "win_rate": 53, + "rank": 4 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1146, + "win_rate": 60.1, + "rank": 6 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1232, + "win_rate": 55.3, + "rank": 10 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1269, + "win_rate": 61.8, + "rank": 5 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1197, + "win_rate": 52.9, + "rank": 11 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1235, + "win_rate": 55.7, + "rank": 13 + }, + { + "arena": "models", + "category": "3d", + "elo": 1273, + "win_rate": 52.4, + "rank": 23 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1272, + "win_rate": 57.1, + "rank": 11 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1290, + "win_rate": 52.5, + "rank": 20 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1283, + "win_rate": 51.4, + "rank": 19 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1294, + "win_rate": 54, + "rank": 20 + }, + { + "arena": "models", + "category": "svg", + "elo": 1233, + "win_rate": 48.6, + "rank": 18 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1290, + "win_rate": 53.1, + "rank": 24 }, { "arena": "models", "category": "website", - "elo": 1289, + "elo": 1287, "win_rate": 52.2, - "rank": 21 + "rank": 22 } ], "artificial_analysis": { - "intelligence_index": 44.3, + "intelligence_index": null, "coding_index": 76.8, "agentic_index": 53 } @@ -37950,10 +39471,12 @@ "reasoning_effort", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], @@ -37967,53 +39490,220 @@ "links": { "details": "/api/v1/models/x-ai/grok-4.7-20260916/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1163, + "win_rate": 60, + "rank": 9 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1267, + "win_rate": 57.3, + "rank": 5 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1189, + "win_rate": 50, + "rank": 15 + }, { "arena": "models", "category": "3d", - "elo": 1271, - "win_rate": 47.7, - "rank": 25 + "elo": 1263, + "win_rate": 47.5, + "rank": 28 }, { "arena": "models", "category": "codecategories", "elo": 1271, - "win_rate": 47.7, - "rank": 30 + "win_rate": 47.8, + "rank": 31 }, { "arena": "models", "category": "dataviz", - "elo": 1235, - "win_rate": 45.7, - "rank": 43 + "elo": 1242, + "win_rate": 46.5, + "rank": 39 }, { "arena": "models", "category": "gamedev", - "elo": 1313, - "win_rate": 52.6, + "elo": 1316, + "win_rate": 51.6, + "rank": 14 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1268, + "win_rate": 48.2, + "rank": 32 + }, + { + "arena": "models", + "category": "website", + "elo": 1248, + "win_rate": 45.7, + "rank": 44 + } + ], + "artificial_analysis": { + "intelligence_index": 35.5, + "coding_index": null, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "high" + } + }, + { + "id": "x-ai/grok-4.7:batch", + "canonical_slug": "x-ai/grok-4.7-20260916", + "hugging_face_id": null, + "name": "SpaceXAI: Grok 4.7 (batch)", + "created": 1790007541, + "description": "Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...", + "context_length": 500000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Grok", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000016", + "completion": "0.0000048", + "web_search": "0.005", + "input_cache_read": "0.0000004", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000032", + "completion": "0.0000096", + "input_cache_read": "0.0000008" + } + ] + }, + "top_provider": { + "context_length": 500000, + "max_completion_tokens": 450000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 0.7, + "top_p": 0.95 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/x-ai/grok-4.7-20260916/endpoints" + }, + "endpoints": ["/api/v1/batches"], + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "blender3d", + "elo": 1163, + "win_rate": 60, + "rank": 9 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1267, + "win_rate": 57.3, + "rank": 5 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1189, + "win_rate": 50, "rank": 15 }, + { + "arena": "models", + "category": "3d", + "elo": 1263, + "win_rate": 47.5, + "rank": 28 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1271, + "win_rate": 47.8, + "rank": 31 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1242, + "win_rate": 46.5, + "rank": 39 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1316, + "win_rate": 51.6, + "rank": 14 + }, { "arena": "models", "category": "uicomponent", - "elo": 1276, - "win_rate": 48.9, - "rank": 29 + "elo": 1268, + "win_rate": 48.2, + "rank": 32 }, { "arena": "models", "category": "website", - "elo": 1254, - "win_rate": 45.9, - "rank": 42 + "elo": 1248, + "win_rate": 45.7, + "rank": 44 } ], "artificial_analysis": { - "intelligence_index": 46.4, + "intelligence_index": 35.5, "coding_index": null, "agentic_index": null } @@ -38088,10 +39778,16 @@ "links": { "details": "/api/v1/models/x-ai/grok-build-0.1-20260520/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 27.2, + "intelligence_index": null, "coding_index": 51.5, "agentic_index": null } @@ -38107,7 +39803,7 @@ "name": "Xiaomi: MiMo-V2.5", "created": 1776874269, "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...", - "context_length": 1050000, + "context_length": 1000000, "architecture": { "modality": "text+image+audio+video->text", "input_modalities": ["text", "audio", "image", "video"], @@ -38116,13 +39812,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000119", - "completion": "0.000000238", - "input_cache_read": "0.00000000255" + "prompt": "0.0000004", + "completion": "0.000002", + "input_cache_read": "0.00000008" }, "top_provider": { - "context_length": 1050000, - "max_completion_tokens": 945000, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -38132,9 +39828,7 @@ "max_tokens", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", @@ -38157,41 +39851,47 @@ "links": { "details": "/api/v1/models/xiaomi/mimo-v2.5-20260422/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1216, - "win_rate": 50.8, - "rank": 43 + "elo": 1213, + "win_rate": 50.7, + "rank": 45 }, { "arena": "models", "category": "asciiart", "elo": 1140, - "win_rate": 44.8, - "rank": 50 + "win_rate": 45.2, + "rank": 49 }, { "arena": "models", "category": "codecategories", - "elo": 1260, + "elo": 1259, "win_rate": 53.5, - "rank": 37 + "rank": 39 }, { "arena": "models", "category": "dataviz", - "elo": 1249, - "win_rate": 53.6, + "elo": 1251, + "win_rate": 53.7, "rank": 36 }, { "arena": "models", "category": "gamedev", - "elo": 1249, - "win_rate": 52.6, + "elo": 1251, + "win_rate": 52.5, "rank": 38 }, { @@ -38199,25 +39899,25 @@ "category": "svg", "elo": 1179, "win_rate": 50.1, - "rank": 35 + "rank": 38 }, { "arena": "models", "category": "uicomponent", - "elo": 1258, - "win_rate": 53.7, - "rank": 40 + "elo": 1253, + "win_rate": 53.6, + "rank": 42 }, { "arena": "models", "category": "website", - "elo": 1266, - "win_rate": 53.5, - "rank": 34 + "elo": 1265, + "win_rate": 53.6, + "rank": 35 } ], "artificial_analysis": { - "intelligence_index": 21.8, + "intelligence_index": null, "coding_index": 56.8, "agentic_index": 15.8 } @@ -38242,32 +39942,27 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003045", - "completion": "0.000000609", - "input_cache_read": "0.0000000028" + "prompt": "0.00000048", + "completion": "0.0000018", + "input_cache_read": "0.000000096" }, "top_provider": { - "context_length": 1050000, - "max_completion_tokens": 945000, + "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", - "repetition_penalty", "response_format", "seed", - "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", "top_logprobs", "top_p" ], @@ -38285,67 +39980,73 @@ "links": { "details": "/api/v1/models/xiaomi/mimo-v2.5-pro-20260422/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1244, - "win_rate": 53.5, - "rank": 36 + "elo": 1242, + "win_rate": 53.7, + "rank": 37 }, { "arena": "models", "category": "asciiart", - "elo": 1156, - "win_rate": 46.2, - "rank": 38 + "elo": 1159, + "win_rate": 46.8, + "rank": 40 }, { "arena": "models", "category": "codecategories", "elo": 1266, - "win_rate": 51.5, - "rank": 34 + "win_rate": 51.7, + "rank": 35 }, { "arena": "models", "category": "dataviz", - "elo": 1257, - "win_rate": 50.5, - "rank": 33 + "elo": 1258, + "win_rate": 50.6, + "rank": 34 }, { "arena": "models", "category": "gamedev", - "elo": 1262, - "win_rate": 53, - "rank": 34 + "elo": 1267, + "win_rate": 53.6, + "rank": 28 }, { "arena": "models", "category": "svg", - "elo": 1181, - "win_rate": 48, - "rank": 34 + "elo": 1186, + "win_rate": 48.5, + "rank": 35 }, { "arena": "models", "category": "uicomponent", - "elo": 1249, + "elo": 1245, "win_rate": 50.7, - "rank": 42 + "rank": 43 }, { "arena": "models", "category": "website", "elo": 1267, - "win_rate": 50.8, + "win_rate": 50.9, "rank": 33 } ], "artificial_analysis": { - "intelligence_index": 26, + "intelligence_index": null, "coding_index": 60.2, "agentic_index": 21.3 } @@ -38387,6 +40088,7 @@ "logprobs", "max_tokens", "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", @@ -38412,10 +40114,16 @@ "links": { "details": "/api/v1/models/xiaomi/mimo-v2.6-flash-20260921/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 37.9, + "intelligence_index": 26.7, "coding_index": null, "agentic_index": null } @@ -38480,60 +40188,73 @@ "links": { "details": "/api/v1/models/xiaomi/mimo-v2.6-pro-20260921/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "webapps", - "elo": 1290, + "elo": 1277, "win_rate": 58.3, - "rank": 8 + "rank": 9 }, { "arena": "models", "category": "3d", - "elo": 1330, - "win_rate": 56.8, + "elo": 1333, + "win_rate": 57.6, "rank": 15 }, { "arena": "models", "category": "codecategories", - "elo": 1317, - "win_rate": 52.5, + "elo": 1315, + "win_rate": 52.6, "rank": 11 }, { "arena": "models", "category": "dataviz", - "elo": 1336, - "win_rate": 58.8, + "elo": 1337, + "win_rate": 58.6, "rank": 7 }, { "arena": "models", "category": "gamedev", - "elo": 1314, + "elo": 1315, "win_rate": 53.1, - "rank": 14 + "rank": 15 + }, + { + "arena": "models", + "category": "svg", + "elo": 1305, + "win_rate": 55.4, + "rank": 6 }, { "arena": "models", "category": "uicomponent", - "elo": 1340, - "win_rate": 59.3, - "rank": 7 + "elo": 1336, + "win_rate": 58.3, + "rank": 9 }, { "arena": "models", "category": "website", - "elo": 1308, - "win_rate": 50.7, - "rank": 13 + "elo": 1307, + "win_rate": 50.8, + "rank": 12 } ], "artificial_analysis": { - "intelligence_index": 46.3, + "intelligence_index": 29.9, "coding_index": null, "agentic_index": null } @@ -38593,6 +40314,12 @@ "links": { "details": "/api/v1/models/xiaomi/mimo-v2.6-pro-ultraspeed-20260921/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -38651,6 +40378,12 @@ "links": { "details": "/api/v1/models/xingchen-agi/xing4.0-29b-a4b-20261015/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false, "default_enabled": true @@ -38704,28 +40437,34 @@ "links": { "details": "/api/v1/models/z-ai/glm-4.5/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1170, + "elo": 1167, "win_rate": 59.7, - "rank": 61 + "rank": 63 }, { "arena": "models", "category": "codecategories", - "elo": 1165, + "elo": 1163, "win_rate": 54.4, - "rank": 78 + "rank": 81 }, { "arena": "models", "category": "dataviz", "elo": 1159, "win_rate": 53.3, - "rank": 77 + "rank": 78 }, { "arena": "models", @@ -38737,30 +40476,25 @@ { "arena": "models", "category": "svg", - "elo": 1096, + "elo": 1093, "win_rate": 50.8, - "rank": 61 + "rank": 67 }, { "arena": "models", "category": "uicomponent", - "elo": 1144, + "elo": 1139, "win_rate": 55, - "rank": 80 + "rank": 83 }, { "arena": "models", "category": "website", - "elo": 1170, + "elo": 1168, "win_rate": 53.7, "rank": 82 } - ], - "artificial_analysis": { - "intelligence_index": 12.8, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -38818,63 +40552,64 @@ "links": { "details": "/api/v1/models/z-ai/glm-4.5-air/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1122, + "elo": 1120, "win_rate": 54.1, - "rank": 83 + "rank": 85 }, { "arena": "models", "category": "codecategories", - "elo": 1137, + "elo": 1135, "win_rate": 51.4, - "rank": 94 + "rank": 98 }, { "arena": "models", "category": "dataviz", "elo": 1186, "win_rate": 58.5, - "rank": 63 + "rank": 64 }, { "arena": "models", "category": "gamedev", "elo": 1094, "win_rate": 48.4, - "rank": 99 + "rank": 100 }, { "arena": "models", "category": "svg", - "elo": 1072, + "elo": 1068, "win_rate": 50.8, - "rank": 68 + "rank": 74 }, { "arena": "models", "category": "uicomponent", - "elo": 1123, + "elo": 1118, "win_rate": 54.4, - "rank": 89 + "rank": 92 }, { "arena": "models", "category": "website", - "elo": 1147, + "elo": 1145, "win_rate": 51.3, - "rank": 93 + "rank": 96 } - ], - "artificial_analysis": { - "intelligence_index": 11.1, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false @@ -38929,18 +40664,16 @@ }, "supported_voices": null, "knowledge_cutoff": "2024-12-31", - "expiration_date": null, + "expiration_date": "2026-12-31", "links": { "details": "/api/v1/models/z-ai/glm-4.5v/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.6, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -38961,12 +40694,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000055", - "completion": "0.0000022", - "input_cache_read": "0.00000011" + "prompt": "0.0000005", + "completion": "0.000002", + "input_cache_read": "0.0000001" }, "top_provider": { - "context_length": 204800, + "context_length": 202752, "max_completion_tokens": 131072, "is_moderated": false }, @@ -39004,14 +40737,20 @@ "links": { "details": "/api/v1/models/z-ai/glm-4.6/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1084, + "elo": 1080, "win_rate": 52.6, - "rank": 30 + "rank": 34 }, { "arena": "agents", @@ -39032,49 +40771,49 @@ "category": "mobileapps", "elo": 1096, "win_rate": 47.2, - "rank": 38 + "rank": 40 }, { "arena": "models", "category": "3d", - "elo": 1129, + "elo": 1126, "win_rate": 54.2, - "rank": 77 + "rank": 82 }, { "arena": "models", "category": "codecategories", - "elo": 1166, + "elo": 1164, "win_rate": 54.3, - "rank": 77 + "rank": 80 }, { "arena": "models", "category": "dataviz", "elo": 1161, "win_rate": 52.6, - "rank": 76 + "rank": 77 }, { "arena": "models", "category": "gamedev", - "elo": 1151, + "elo": 1149, "win_rate": 54.8, "rank": 75 }, { "arena": "models", "category": "svg", - "elo": 1109, + "elo": 1105, "win_rate": 52.1, - "rank": 58 + "rank": 64 }, { "arena": "models", "category": "uicomponent", - "elo": 1148, + "elo": 1142, "win_rate": 52.5, - "rank": 79 + "rank": 82 }, { "arena": "models", @@ -39085,7 +40824,7 @@ } ], "artificial_analysis": { - "intelligence_index": 18.5, + "intelligence_index": null, "coding_index": 45.8, "agentic_index": null } @@ -39147,14 +40886,12 @@ "links": { "details": "/api/v1/models/z-ai/glm-4.6-20251208/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.2, - "coding_index": null, - "agentic_index": null - } - }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": false } @@ -39175,12 +40912,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000054", - "completion": "0.00000198", - "input_cache_read": "0.000000099" + "prompt": "0.0000006", + "completion": "0.0000022", + "input_cache_read": "0.00000011" }, "top_provider": { - "context_length": 204800, + "context_length": 202752, "max_completion_tokens": 131072, "is_moderated": false }, @@ -39215,18 +40952,24 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-12-31", "links": { "details": "/api/v1/models/z-ai/glm-4.7-20251222/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1112, + "elo": 1108, "win_rate": 56.1, - "rank": 29 + "rank": 31 }, { "arena": "agents", @@ -39247,67 +40990,67 @@ "category": "mobileapps", "elo": 1105, "win_rate": 48.9, - "rank": 37 + "rank": 39 }, { "arena": "models", "category": "3d", - "elo": 1191, + "elo": 1187, "win_rate": 54.3, - "rank": 54 + "rank": 56 }, { "arena": "models", "category": "asciiart", - "elo": 1165, + "elo": 1162, "win_rate": 48.2, - "rank": 34 + "rank": 37 }, { "arena": "models", "category": "codecategories", - "elo": 1217, + "elo": 1215, "win_rate": 54.8, - "rank": 55 + "rank": 58 }, { "arena": "models", "category": "dataviz", "elo": 1195, "win_rate": 51.2, - "rank": 62 + "rank": 63 }, { "arena": "models", "category": "gamedev", - "elo": 1189, + "elo": 1187, "win_rate": 55.2, - "rank": 61 + "rank": 62 }, { "arena": "models", "category": "svg", - "elo": 1143, + "elo": 1139, "win_rate": 54.3, - "rank": 48 + "rank": 54 }, { "arena": "models", "category": "uicomponent", - "elo": 1199, + "elo": 1194, "win_rate": 51.1, - "rank": 60 + "rank": 63 }, { "arena": "models", "category": "website", - "elo": 1226, + "elo": 1224, "win_rate": 55.3, - "rank": 56 + "rank": 57 } ], "artificial_analysis": { - "intelligence_index": 22.2, + "intelligence_index": null, "coding_index": 45.3, "agentic_index": null } @@ -39374,63 +41117,64 @@ "links": { "details": "/api/v1/models/z-ai/glm-4.7-flash-20260119/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1121, + "elo": 1118, "win_rate": 51.2, - "rank": 84 + "rank": 86 }, { "arena": "models", "category": "codecategories", - "elo": 1178, + "elo": 1176, "win_rate": 53.1, - "rank": 68 + "rank": 71 }, { "arena": "models", "category": "dataviz", "elo": 1123, "win_rate": 45.3, - "rank": 96 + "rank": 97 }, { "arena": "models", "category": "gamedev", "elo": 1135, "win_rate": 49.7, - "rank": 84 + "rank": 83 }, { "arena": "models", "category": "svg", - "elo": 1038, + "elo": 1034, "win_rate": 44.2, - "rank": 76 + "rank": 82 }, { "arena": "models", "category": "uicomponent", - "elo": 1208, + "elo": 1202, "win_rate": 57.6, - "rank": 56 + "rank": 60 }, { "arena": "models", "category": "website", - "elo": 1194, + "elo": 1192, "win_rate": 54, - "rank": 68 + "rank": 69 } - ], - "artificial_analysis": { - "intelligence_index": 14.9, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -39493,14 +41237,20 @@ "links": { "details": "/api/v1/models/z-ai/glm-5-20260211/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "androidnative", - "elo": 1146, + "elo": 1144, "win_rate": 55.2, - "rank": 25 + "rank": 27 }, { "arena": "agents", @@ -39519,79 +41269,74 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1148, + "elo": 1044, "win_rate": 45.1, - "rank": 18 + "rank": 20 }, { "arena": "agents", "category": "mobileapps", "elo": 1136, - "win_rate": 51.6, - "rank": 34 + "win_rate": 51.7, + "rank": 36 }, { "arena": "models", "category": "3d", - "elo": 1229, + "elo": 1226, "win_rate": 56.3, - "rank": 41 + "rank": 43 }, { "arena": "models", "category": "asciiart", - "elo": 1147, + "elo": 1144, "win_rate": 47.9, - "rank": 45 + "rank": 48 }, { "arena": "models", "category": "codecategories", - "elo": 1246, + "elo": 1244, "win_rate": 55.5, - "rank": 42 + "rank": 44 }, { "arena": "models", "category": "dataviz", "elo": 1228, "win_rate": 53, - "rank": 46 + "rank": 47 }, { "arena": "models", "category": "gamedev", "elo": 1234, "win_rate": 57.4, - "rank": 41 + "rank": 42 }, { "arena": "models", "category": "svg", - "elo": 1169, + "elo": 1165, "win_rate": 54.4, - "rank": 37 + "rank": 43 }, { "arena": "models", "category": "uicomponent", - "elo": 1230, + "elo": 1225, "win_rate": 53.6, - "rank": 50 + "rank": 52 }, { "arena": "models", "category": "website", - "elo": 1247, + "elo": 1246, "win_rate": 55, - "rank": 47 + "rank": 46 } - ], - "artificial_analysis": { - "intelligence_index": 27.9, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -39649,28 +41394,34 @@ "links": { "details": "/api/v1/models/z-ai/glm-5-turbo-20260315/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1248, - "win_rate": 55.4, - "rank": 34 + "elo": 1244, + "win_rate": 55.3, + "rank": 36 }, { "arena": "models", "category": "asciiart", - "elo": 1160, - "win_rate": 48.5, - "rank": 37 + "elo": 1159, + "win_rate": 48.3, + "rank": 39 }, { "arena": "models", "category": "codecategories", - "elo": 1262, - "win_rate": 53.5, - "rank": 35 + "elo": 1259, + "win_rate": 53.2, + "rank": 37 }, { "arena": "models", @@ -39682,37 +41433,32 @@ { "arena": "models", "category": "gamedev", - "elo": 1248, - "win_rate": 52.8, - "rank": 39 + "elo": 1245, + "win_rate": 52.1, + "rank": 40 }, { "arena": "models", "category": "svg", - "elo": 1206, - "win_rate": 54.3, - "rank": 24 + "elo": 1202, + "win_rate": 53.9, + "rank": 29 }, { "arena": "models", "category": "uicomponent", - "elo": 1263, - "win_rate": 54.9, - "rank": 36 + "elo": 1257, + "win_rate": 54.7, + "rank": 38 }, { "arena": "models", "category": "website", - "elo": 1262, - "win_rate": 52.9, - "rank": 37 + "elo": 1260, + "win_rate": 52.6, + "rank": 38 } - ], - "artificial_analysis": { - "intelligence_index": 26.6, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, @@ -39780,6 +41526,12 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.1-20260406/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { @@ -39792,16 +41544,16 @@ { "arena": "models", "category": "asciiart", - "elo": 1141, + "elo": 1139, "win_rate": 44.6, - "rank": 47 + "rank": 50 }, { "arena": "models", "category": "codecategories", - "elo": 1268, - "win_rate": 53.1, - "rank": 32 + "elo": 1267, + "win_rate": 52.9, + "rank": 33 }, { "arena": "models", @@ -39813,23 +41565,23 @@ { "arena": "models", "category": "gamedev", - "elo": 1265, - "win_rate": 55.2, - "rank": 28 + "elo": 1264, + "win_rate": 54.7, + "rank": 30 }, { "arena": "models", "category": "svg", - "elo": 1218, - "win_rate": 55.4, - "rank": 19 + "elo": 1214, + "win_rate": 55.2, + "rank": 23 }, { "arena": "models", "category": "uicomponent", "elo": 1292, "win_rate": 54.9, - "rank": 23 + "rank": 22 }, { "arena": "models", @@ -39841,9 +41593,9 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1164, - "win_rate": 49.6, - "rank": 17 + "elo": 1109, + "win_rate": 49.2, + "rank": 19 }, { "arena": "agents", @@ -39877,8 +41629,8 @@ "arena": "agents", "category": "androidnative", "elo": 1181, - "win_rate": 52.1, - "rank": 16 + "win_rate": 52.4, + "rank": 17 }, { "arena": "agents", @@ -39891,22 +41643,29 @@ "arena": "agents", "category": "godotgamedev", "elo": 1053, - "win_rate": 37.8, + "win_rate": 37.6, "rank": 34 }, { "arena": "agents", "category": "htmlslides", - "elo": 1170, + "elo": 1066, "win_rate": 48.8, - "rank": 14 + "rank": 16 }, { "arena": "agents", "category": "mobileapps", - "elo": 1162, - "win_rate": 50.4, - "rank": 26 + "elo": 1160, + "win_rate": 50, + "rank": 28 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1220, + "win_rate": 55.9, + "rank": 12 }, { "arena": "agents", @@ -39920,7 +41679,7 @@ "category": "python-pptxslides", "elo": 1258, "win_rate": 54.2, - "rank": 6 + "rank": 3 }, { "arena": "agents", @@ -39932,13 +41691,13 @@ { "arena": "agents", "category": "webapps", - "elo": 1175, - "win_rate": 50.5, - "rank": 29 + "elo": 1162, + "win_rate": 50.6, + "rank": 30 } ], "artificial_analysis": { - "intelligence_index": 26.1, + "intelligence_index": null, "coding_index": 55.8, "agentic_index": 23.9 } @@ -39964,9 +41723,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000000341", - "completion": "0.000007", - "input_cache_read": "0.000000033" + "prompt": "0.000000006", + "completion": "0.0000068", + "input_cache_read": "0.000000005" }, "top_provider": { "context_length": 1048576, @@ -40011,22 +41770,35 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.2-20260616/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1206, - "win_rate": 49, + "elo": 1155, + "win_rate": 49.2, "rank": 10 }, { "arena": "agents", "category": "androidnative", - "elo": 1178, - "win_rate": 52.9, + "elo": 1177, + "win_rate": 52.8, "rank": 18 }, + { + "arena": "agents", + "category": "blender3d", + "elo": 983, + "win_rate": 36.1, + "rank": 22 + }, { "arena": "agents", "category": "fullstack", @@ -40044,90 +41816,97 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1175, + "elo": 1071, "win_rate": 49.5, - "rank": 13 + "rank": 15 }, { "arena": "agents", "category": "mobileapps", "elo": 1159, - "win_rate": 47.9, - "rank": 27 + "win_rate": 47.6, + "rank": 29 + }, + { + "arena": "agents", + "category": "pdf", + "elo": 1238, + "win_rate": 54.2, + "rank": 9 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1193, - "win_rate": 48.8, - "rank": 17 + "elo": 1149, + "win_rate": 49, + "rank": 18 }, { "arena": "agents", "category": "webapps", - "elo": 1222, + "elo": 1209, "win_rate": 55.8, "rank": 17 }, { "arena": "models", "category": "3d", - "elo": 1288, - "win_rate": 53.3, - "rank": 21 + "elo": 1283, + "win_rate": 53, + "rank": 22 }, { "arena": "models", "category": "asciiart", - "elo": 1190, + "elo": 1188, "win_rate": 46, - "rank": 29 + "rank": 31 }, { "arena": "models", "category": "codecategories", - "elo": 1288, - "win_rate": 50.4, - "rank": 21 + "elo": 1285, + "win_rate": 50.3, + "rank": 23 }, { "arena": "models", "category": "dataviz", - "elo": 1285, - "win_rate": 52, + "elo": 1286, + "win_rate": 51.9, "rank": 17 }, { "arena": "models", "category": "gamedev", - "elo": 1268, - "win_rate": 49.6, + "elo": 1267, + "win_rate": 49.5, "rank": 27 }, { "arena": "models", "category": "svg", - "elo": 1215, - "win_rate": 48.6, - "rank": 21 + "elo": 1208, + "win_rate": 48.2, + "rank": 25 }, { "arena": "models", "category": "uicomponent", - "elo": 1297, - "win_rate": 55.3, - "rank": 20 + "elo": 1290, + "win_rate": 55.2, + "rank": 23 }, { "arena": "models", "category": "website", - "elo": 1285, + "elo": 1283, "win_rate": 49.5, - "rank": 23 + "rank": 24 } ], "artificial_analysis": { - "intelligence_index": 33.7, + "intelligence_index": null, "coding_index": 68.8, "agentic_index": 38.4 } @@ -40155,9 +41934,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000079", - "completion": "0.0000014", - "input_cache_read": "0.000000078" + "prompt": "0.00000008", + "completion": "0.0000036", + "input_cache_read": "0.000000076" }, "top_provider": { "context_length": 1048576, @@ -40198,88 +41977,94 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.3-20260816/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1332, - "win_rate": 59.3, - "rank": 14 + "elo": 1326, + "win_rate": 58.9, + "rank": 16 }, { "arena": "models", "category": "asciiart", "elo": 1208, - "win_rate": 47, - "rank": 21 + "win_rate": 47.6, + "rank": 23 }, { "arena": "models", "category": "codecategories", - "elo": 1304, - "win_rate": 54, - "rank": 15 + "elo": 1296, + "win_rate": 53.3, + "rank": 17 }, { "arena": "models", "category": "dataviz", "elo": 1260, - "win_rate": 51.9, + "win_rate": 51.7, "rank": 32 }, { "arena": "models", "category": "gamedev", - "elo": 1311, - "win_rate": 52.5, - "rank": 17 + "elo": 1303, + "win_rate": 51.6, + "rank": 18 }, { "arena": "models", "category": "svg", - "elo": 1294, - "win_rate": 56.9, - "rank": 8 + "elo": 1262, + "win_rate": 52.7, + "rank": 15 }, { "arena": "models", "category": "uicomponent", - "elo": 1314, - "win_rate": 56.7, - "rank": 15 + "elo": 1293, + "win_rate": 53.5, + "rank": 21 }, { "arena": "models", "category": "website", - "elo": 1295, - "win_rate": 53.9, - "rank": 18 + "elo": 1290, + "win_rate": 53.4, + "rank": 21 }, { "arena": "agents", "category": "htmlslides", "elo": 1189, "win_rate": 39.1, - "rank": 9 + "rank": 2 }, { "arena": "agents", "category": "mobileapps", - "elo": 1194, + "elo": 1190, "win_rate": 52.2, - "rank": 19 + "rank": 22 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1251, + "elo": 1214, "win_rate": 51.2, - "rank": 8 + "rank": 9 } ], "artificial_analysis": { - "intelligence_index": 44.8, + "intelligence_index": 31.7, "coding_index": 74.8, "agentic_index": 53.1 } @@ -40307,13 +42092,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000000052", - "completion": "0.0000001985", - "input_cache_read": "0.0000000052" + "prompt": "0.0000000269", + "completion": "0.0000000996", + "input_cache_read": "0.0000000269" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 943718, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -40350,67 +42135,73 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1316, - "win_rate": 56.2, - "rank": 17 + "elo": 1313, + "win_rate": 56.1, + "rank": 18 }, { "arena": "models", "category": "asciiart", - "elo": 1267, - "win_rate": 54.6, + "elo": 1272, + "win_rate": 54.7, "rank": 12 }, { "arena": "models", "category": "codecategories", - "elo": 1282, - "win_rate": 49.3, - "rank": 22 + "elo": 1279, + "win_rate": 49.2, + "rank": 25 }, { "arena": "models", "category": "dataviz", - "elo": 1262, - "win_rate": 50.4, - "rank": 31 + "elo": 1260, + "win_rate": 50.1, + "rank": 33 }, { "arena": "models", "category": "gamedev", - "elo": 1278, - "win_rate": 47.1, + "elo": 1275, + "win_rate": 46.9, "rank": 25 }, { "arena": "models", "category": "svg", - "elo": 1285, - "win_rate": 56.7, - "rank": 11 + "elo": 1274, + "win_rate": 54.5, + "rank": 14 }, { "arena": "models", "category": "uicomponent", - "elo": 1316, - "win_rate": 54.6, - "rank": 14 + "elo": 1305, + "win_rate": 52.8, + "rank": 16 }, { "arena": "models", "category": "website", - "elo": 1272, - "win_rate": 48.4, - "rank": 28 + "elo": 1270, + "win_rate": 48.5, + "rank": 29 } ], "artificial_analysis": { - "intelligence_index": 41.8, + "intelligence_index": 27.8, "coding_index": 71.5, "agentic_index": 50.9 } @@ -40480,67 +42271,68 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1316, - "win_rate": 56.2, - "rank": 17 + "elo": 1313, + "win_rate": 56.1, + "rank": 18 }, { "arena": "models", "category": "asciiart", - "elo": 1267, - "win_rate": 54.6, + "elo": 1272, + "win_rate": 54.7, "rank": 12 }, { "arena": "models", "category": "codecategories", - "elo": 1282, - "win_rate": 49.3, - "rank": 22 + "elo": 1279, + "win_rate": 49.2, + "rank": 25 }, { "arena": "models", "category": "dataviz", - "elo": 1262, - "win_rate": 50.4, - "rank": 31 + "elo": 1260, + "win_rate": 50.1, + "rank": 33 }, { "arena": "models", "category": "gamedev", - "elo": 1278, - "win_rate": 47.1, + "elo": 1275, + "win_rate": 46.9, "rank": 25 }, { "arena": "models", "category": "svg", - "elo": 1285, - "win_rate": 56.7, - "rank": 11 + "elo": 1274, + "win_rate": 54.5, + "rank": 14 }, { "arena": "models", "category": "uicomponent", - "elo": 1316, - "win_rate": 54.6, - "rank": 14 + "elo": 1305, + "win_rate": 52.8, + "rank": 16 }, { "arena": "models", "category": "website", - "elo": 1272, - "win_rate": 48.4, - "rank": 28 + "elo": 1270, + "win_rate": 48.5, + "rank": 29 } ], "artificial_analysis": { - "intelligence_index": 41.8, + "intelligence_index": 27.8, "coding_index": 71.5, "agentic_index": 50.9 } @@ -40570,7 +42362,7 @@ "pricing": { "prompt": "0.00000037", "completion": "0.00000125", - "input_cache_read": "0.00000009" + "input_cache_read": "0.000000075" }, "top_provider": { "context_length": 1048576, @@ -40600,6 +42392,74 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.3-flashx-20260918/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["max", "high", "low"], + "default_effort": "max" + } + }, + { + "id": "z-ai/glm-5.3-flashx-legal", + "canonical_slug": "z-ai/glm-5.3-flashx-legal-20261102", + "hugging_face_id": null, + "name": "Z.ai: GLM 5.3 FlashX Legal", + "created": 1793626154, + "description": "GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000037", + "completion": "0.00000125", + "input_cache_read": "0.000000075" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/z-ai/glm-5.3-flashx-legal-20261102/endpoints" + }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -40661,6 +42521,12 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.3-prime-20260921/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "reasoning": { "mandatory": true, "default_enabled": true, @@ -40724,88 +42590,89 @@ "links": { "details": "/api/v1/models/z-ai/glm-5.3-20260816/endpoints" }, + "endpoints": ["/api/v1/batches"], "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1332, - "win_rate": 59.3, - "rank": 14 + "elo": 1326, + "win_rate": 58.9, + "rank": 16 }, { "arena": "models", "category": "asciiart", "elo": 1208, - "win_rate": 47, - "rank": 21 + "win_rate": 47.6, + "rank": 23 }, { "arena": "models", "category": "codecategories", - "elo": 1304, - "win_rate": 54, - "rank": 15 + "elo": 1296, + "win_rate": 53.3, + "rank": 17 }, { "arena": "models", "category": "dataviz", "elo": 1260, - "win_rate": 51.9, + "win_rate": 51.7, "rank": 32 }, { "arena": "models", "category": "gamedev", - "elo": 1311, - "win_rate": 52.5, - "rank": 17 + "elo": 1303, + "win_rate": 51.6, + "rank": 18 }, { "arena": "models", "category": "svg", - "elo": 1294, - "win_rate": 56.9, - "rank": 8 + "elo": 1262, + "win_rate": 52.7, + "rank": 15 }, { "arena": "models", "category": "uicomponent", - "elo": 1314, - "win_rate": 56.7, - "rank": 15 + "elo": 1293, + "win_rate": 53.5, + "rank": 21 }, { "arena": "models", "category": "website", - "elo": 1295, - "win_rate": 53.9, - "rank": 18 + "elo": 1290, + "win_rate": 53.4, + "rank": 21 }, { "arena": "agents", "category": "htmlslides", "elo": 1189, "win_rate": 39.1, - "rank": 9 + "rank": 2 }, { "arena": "agents", "category": "mobileapps", - "elo": 1194, + "elo": 1190, "win_rate": 52.2, - "rank": 19 + "rank": 22 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1251, + "elo": 1214, "win_rate": 51.2, - "rank": 8 + "rank": 9 } ], "artificial_analysis": { - "intelligence_index": 44.8, + "intelligence_index": 31.7, "coding_index": 74.8, "agentic_index": 53.1 } @@ -40868,14 +42735,20 @@ "links": { "details": "/api/v1/models/z-ai/glm-5v-turbo-20260401/endpoints" }, + "endpoints": [ + "/api/v1/chat/completions", + "/api/v1/completions", + "/api/v1/messages", + "/api/v1/responses" + ], "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1102, - "win_rate": 42.5, - "rank": 23 + "elo": 1047, + "win_rate": 42.6, + "rank": 24 }, { "arena": "agents", @@ -40910,7 +42783,7 @@ "category": "androidnative", "elo": 1267, "win_rate": 54.8, - "rank": 3 + "rank": 4 }, { "arena": "agents", @@ -40929,16 +42802,16 @@ { "arena": "agents", "category": "htmlslides", - "elo": 1121, + "elo": 1017, "win_rate": 44.6, - "rank": 21 + "rank": 23 }, { "arena": "agents", "category": "mobileapps", "elo": 1134, "win_rate": 50.4, - "rank": 35 + "rank": 37 }, { "arena": "agents", @@ -40952,77 +42825,72 @@ "category": "python-pptxslides", "elo": 1165, "win_rate": 51.9, - "rank": 20 + "rank": 15 }, { "arena": "agents", "category": "webapps", - "elo": 1124, + "elo": 1111, "win_rate": 44.7, - "rank": 35 + "rank": 36 }, { "arena": "models", "category": "3d", - "elo": 1209, - "win_rate": 52.3, - "rank": 46 + "elo": 1205, + "win_rate": 52.2, + "rank": 48 }, { "arena": "models", "category": "asciiart", - "elo": 1117, - "win_rate": 42.4, - "rank": 56 + "elo": 1115, + "win_rate": 42.5, + "rank": 59 }, { "arena": "models", "category": "codecategories", - "elo": 1228, - "win_rate": 49.6, - "rank": 52 + "elo": 1226, + "win_rate": 49.4, + "rank": 56 }, { "arena": "models", "category": "dataviz", "elo": 1202, - "win_rate": 47.7, - "rank": 59 + "win_rate": 47.6, + "rank": 60 }, { "arena": "models", "category": "gamedev", - "elo": 1219, - "win_rate": 50, - "rank": 49 + "elo": 1216, + "win_rate": 49.5, + "rank": 48 }, { "arena": "models", "category": "svg", - "elo": 1151, - "win_rate": 48.8, - "rank": 43 + "elo": 1147, + "win_rate": 48.4, + "rank": 49 }, { "arena": "models", "category": "uicomponent", - "elo": 1213, - "win_rate": 48.1, - "rank": 54 + "elo": 1207, + "win_rate": 47.8, + "rank": 56 }, { "arena": "models", "category": "website", - "elo": 1230, - "win_rate": 48.9, - "rank": 54 + "elo": 1229, + "win_rate": 48.7, + "rank": 55 } - ], - "artificial_analysis": { - "intelligence_index": 23.5, - "coding_index": null, - "agentic_index": null - } + ] }, "reasoning": { "mandatory": false, diff --git a/scripts/openrouter.video-models.json b/scripts/openrouter.video-models.json index ef83d6f38c..46064badcd 100644 --- a/scripts/openrouter.video-models.json +++ b/scripts/openrouter.video-models.json @@ -242,7 +242,7 @@ "cents_per_second_video_continuation_720p": "41", "cents_per_second_video_continuation_1080p": "53" }, - "allowed_passthrough_parameters": ["safety_tolerance", "version"] + "allowed_passthrough_parameters": ["safety_tolerance", "version", "draft"] }, { "id": "black-forest-labs/flux-video-edit", @@ -680,10 +680,13 @@ "name": "HeyGen: HeyGen Video", "created": 1790798684, "description": "HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text...", - "supported_resolutions": ["480p", "768p", "2K"], + "supported_resolutions": ["480p", "768p", "1080p", "2K"], "supported_aspect_ratios": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"], "supported_sizes": null, - "supported_durations": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], + "supported_durations": [ + 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"], "upscale_factor": null, "creativity": null, @@ -693,10 +696,16 @@ "duration_seconds_2k": "0.1", "duration_seconds_480p": "0.02", "duration_seconds_768p": "0.036", + "duration_seconds_1080p": "0.1", "reference_input_images": "0.04", + "long_duration_seconds_2k": "0.105", + "long_duration_seconds_480p": "0.045", + "long_duration_seconds_768p": "0.075", + "long_duration_seconds_1080p": "0.105", "reference_duration_seconds_2k": "0.18", "reference_duration_seconds_480p": "0.07", - "reference_duration_seconds_768p": "0.1" + "reference_duration_seconds_768p": "0.1", + "reference_duration_seconds_1080p": "0.18" }, "allowed_passthrough_parameters": ["prompt_enhancement"] }, @@ -893,6 +902,28 @@ }, "allowed_passthrough_parameters": ["contentModeration"] }, + { + "id": "tbc/mischief-1", + "canonical_slug": "tbc/mischief-1-20261023", + "hugging_face_id": null, + "name": "TBC: mischief 1", + "created": 1793319378, + "description": "TBC mischief 1 is the world's first neuron-derived video model from The Biological Computing Co. It supports image to video and is a fast and affordable way to bring ideas...", + "supported_resolutions": ["480p", "720p"], + "supported_aspect_ratios": ["16:9"], + "supported_sizes": ["854x480", "1280x720"], + "supported_durations": [3, 5], + "supported_frame_images": ["first_frame"], + "upscale_factor": null, + "creativity": null, + "generate_audio": false, + "seed": true, + "pricing_skus": { + "cents_per_video_output_second_480p": "0.5", + "cents_per_video_output_second_720p": "1" + }, + "allowed_passthrough_parameters": [] + }, { "id": "x-ai/grok-imagine-video", "canonical_slug": "x-ai/grok-imagine-video-20260512", diff --git a/scripts/vercel-gateway.models.json b/scripts/vercel-gateway.models.json index 3f0ef046df..72a33db966 100644 --- a/scripts/vercel-gateway.models.json +++ b/scripts/vercel-gateway.models.json @@ -10,7 +10,7 @@ "context_window": 40960, "max_tokens": 16384, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -73,8 +73,7 @@ "knowledge": "2025-04", "pricing": { "input": "0.00000022", - "output": "0.00000088", - "varies_by_provider": true + "output": "0.00000088" } }, { @@ -88,7 +87,7 @@ "context_window": 40960, "max_tokens": 16384, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -130,7 +129,7 @@ "context_window": 128000, "max_tokens": 8192, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -288,7 +287,7 @@ "context_window": 32768, "max_tokens": 32768, "type": "embedding", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -311,7 +310,7 @@ "context_window": 32768, "max_tokens": 32768, "type": "embedding", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -334,7 +333,7 @@ "context_window": 32768, "max_tokens": 32768, "type": "embedding", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": ["open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -450,7 +449,7 @@ "context_window": 262114, "max_tokens": 262114, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -529,7 +528,7 @@ "context_window": 262144, "max_tokens": 262144, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["implicit-caching", "tool-use", "vision", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -996,6 +995,7 @@ "explicit-caching", "structured-output" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -1031,7 +1031,15 @@ "input": "0.0000025", "output": "0.0000075", "input_cache_read": "0.0000005", - "input_cache_write": "0.000003125" + "input_cache_write": "0.000003125", + "regional": { + "us": { + "input": "0.0000025", + "output": "0.0000075", + "input_cache_read": "0.0000005", + "input_cache_write": "0.000003125" + } + } } }, { @@ -1264,6 +1272,7 @@ "explicit-caching", "structured-output" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image", "pdf"], @@ -1297,7 +1306,15 @@ "input": "0.00000015", "output": "0.00000047", "input_cache_read": "0.000000016", - "input_cache_write": "0.0000002" + "input_cache_write": "0.0000002", + "regional": { + "us": { + "input": "0.00000015", + "output": "0.00000047", + "input_cache_read": "0.000000016", + "input_cache_write": "0.0000002" + } + } } }, { @@ -1321,6 +1338,7 @@ "explicit-caching", "structured-output" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -1355,7 +1373,15 @@ "pricing": { "input": "0.000002", "output": "0.000006", - "input_cache_read": "0.00000025" + "input_cache_read": "0.00000025", + "regional": { + "us": { + "input": "0.000002", + "output": "0.000006", + "input_cache_read": "0.00000025", + "input_cache_write": "0.0000025" + } + } } }, { @@ -2240,19 +2266,19 @@ ], "knowledge": "2024-10", "pricing": { - "input": "0.0000003", - "output": "0.0000025", - "input_cache_read": "0.000000075", + "input": "0.00000033", + "output": "0.00000275", + "input_cache_read": "0.0000000825", "regional": { "eu": { - "input": "0.00000039", - "output": "0.00000327", - "input_cache_read": "0.000000075" + "input": "0.000000429", + "output": "0.000003597", + "input_cache_read": "0.0000001072" }, "us": { - "input": "0.0000003", - "output": "0.0000025", - "input_cache_read": "0.000000075" + "input": "0.00000033", + "output": "0.00000275", + "input_cache_read": "0.0000000825" } } } @@ -2291,10 +2317,12 @@ "pricing": { "input": "0.00000006", "output": "0.00000024", + "input_cache_read": "0.000000015", "regional": { "eu": { "input": "0.000000078", - "output": "0.000000312" + "output": "0.000000312", + "input_cache_read": "0.0000000195" } } } @@ -2333,10 +2361,12 @@ "pricing": { "input": "0.000000035", "output": "0.00000014", + "input_cache_read": "0.0000000087", "regional": { "eu": { "input": "0.000000046", - "output": "0.000000184" + "output": "0.000000184", + "input_cache_read": "0.0000000115" } } } @@ -2375,10 +2405,12 @@ "pricing": { "input": "0.0000008", "output": "0.0000032", + "input_cache_read": "0.0000002", "regional": { "eu": { "input": "0.00000105", - "output": "0.0000042" + "output": "0.0000042", + "input_cache_read": "0.0000002625" } } } @@ -4917,73 +4949,62 @@ } }, { - "id": "arcee-ai/trinity-large-thinking", + "id": "baseten/elephant-1", "object": "model", "created": 1755815280, - "released": 1775001600, - "owned_by": "arcee-ai", - "name": "Trinity Large Thinking", - "description": "Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. Built on Trinity-Large-Base and post-trained with extended chain-of-thought reasoning and agentic RL, Trinity-Large-Thinking delivers state-of-the-art performance on agentic benchmarks while maintaining strong general capabilities.", - "context_window": 262100, - "max_tokens": 80000, - "type": "language", - "zdr": "none", - "no_training": "none", - "tags": ["reasoning", "tool-use", "structured-output", "open-weights"], - "supported_specifications": ["v2", "v3", "v4"], + "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"], + "regions": ["us"], + "supported_specifications": ["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": "0.00000025", - "output": "0.0000008", - "input_cache_read": "0.00000006" + "input": "0.000000035", + "output": "0", + "regional": { + "us": { + "input": "0.000000035" + } + } } }, { - "id": "baseten/elephant-1", + "id": "baseten/joey-1", "object": "model", "created": 1755815280, - "released": 1792540800, + "released": 1793232000, "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.", + "name": "Joey-1", + "description": "Joey-1 is a 2B decision model from Baseten's Base Labs for classification, routing, and scoring. It evaluates text context against choice, yes/no, and ordered scoring questions, returning answer probabilities and confidence in a single forward pass without generating free-form text.", "context_window": 16384, "max_tokens": 0, "type": "evaluation", "zdr": "all", "no_training": "all", - "tags": ["open-weights"], + "regions": ["us"], "supported_specifications": ["v4"], "modalities": { "input": ["text"], "output": ["text"] }, "pricing": { - "input": "0", - "output": "0" + "input": "0.00000001", + "output": "0", + "regional": { + "us": { + "input": "0.00000001" + } + } } }, { @@ -5000,14 +5021,20 @@ "zdr": "all", "no_training": "all", "tags": ["open-weights"], + "regions": ["us"], "supported_specifications": ["v4"], "modalities": { "input": ["text"], "output": ["text"] }, "pricing": { - "input": "0", - "output": "0" + "input": "0.0000001", + "output": "0", + "regional": { + "us": { + "input": "0.0000001" + } + } } }, { @@ -6511,38 +6538,13 @@ "type": "evaluation", "zdr": "none", "no_training": "none", - "tags": ["free"], - "supported_specifications": ["v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "pricing": { - "input": "0", - "output": "0" - } - }, - { - "id": "convaiinnovations/laya-free", - "object": "model", - "created": 1755815280, - "released": 1790812800, - "owned_by": "convaiinnovations", - "name": "Laya (Free)", - "description": "Laya is Convai Innovations’ System One evaluation model for fast, structured decisions. It evaluates shared state against choice, score, and yes/no questions and returns typed answers with probabilities in a single forward pass. It supports classification, routing, guardrail checks, and rubric-based assessment without generating free-form text.", - "context_window": 8192, - "max_tokens": 0, - "type": "evaluation", - "zdr": "none", - "no_training": "none", - "tags": ["free"], "supported_specifications": ["v4"], "modalities": { "input": ["text"], "output": ["text"] }, "pricing": { - "input": "0", + "input": "0.0000000105", "output": "0" } }, @@ -6559,7 +6561,7 @@ "type": "language", "zdr": "all", "no_training": "all", - "tags": ["reasoning", "tool-use", "open-weights", "implicit-caching"], + "tags": ["reasoning", "tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -6587,8 +6589,7 @@ "knowledge": "2024-07", "pricing": { "input": "0.00000135", - "output": "0.0000054", - "varies_by_provider": true + "output": "0.0000054" } }, { @@ -6602,8 +6603,8 @@ "context_window": 163840, "max_tokens": 128000, "type": "language", - "zdr": "some", - "no_training": "some", + "zdr": "none", + "no_training": "all", "tags": [ "implicit-caching", "reasoning", @@ -6640,8 +6641,7 @@ "pricing": { "input": "0.00000025", "output": "0.00000095", - "input_cache_read": "0.00000013", - "varies_by_provider": true + "input_cache_read": "0.00000013" } }, { @@ -6655,7 +6655,7 @@ "context_window": 128000, "max_tokens": 8000, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": ["tool-use", "open-weights", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], @@ -6700,7 +6700,7 @@ "context_window": 128000, "max_tokens": 8000, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": ["tool-use", "open-weights", "implicit-caching"], "supported_specifications": ["v2", "v3", "v4"], @@ -6846,9 +6846,9 @@ ], "knowledge": "2025-05", "pricing": { - "input": "0.000000076", - "output": "0.000000153", - "input_cache_read": "0.000000014", + "input": "0.00000013", + "output": "0.00000026", + "input_cache_read": "0.000000028", "varies_by_provider": true, "regional": { "us": { @@ -6870,7 +6870,7 @@ "context_window": 1048576, "max_tokens": 1048576, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "reasoning", @@ -6920,9 +6920,9 @@ "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, + "description": "", + "context_window": 1048600, + "max_tokens": 1048600, "type": "language", "zdr": "some", "no_training": "some", @@ -6962,25 +6962,9 @@ ], "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" - }, + "input": "0.00000132", + "output": "0.00000396", + "input_cache_read": "0.000000132", "varies_by_provider": true, "regional": { "us": { @@ -7111,24 +7095,9 @@ } ], "pricing": { - "input": "0.000000075", - "output": "0.0000003", - "input_cache_read": "0.0000000015", - "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] - } - ] - }, + "input": "0.0000003", + "output": "0.0000012", + "input_cache_read": "0.000000007", "varies_by_provider": true, "fast": { "input": "0.0000006", @@ -7151,9 +7120,9 @@ "released": 1792195200, "owned_by": "deepseek", "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.", + "description": "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": 1048576, + "max_tokens": 262144, "type": "language", "zdr": "some", "no_training": "some", @@ -7193,24 +7162,9 @@ } ], "pricing": { - "input": "0.000000075", - "output": "0.0000003", - "input_cache_read": "0.0000000015", - "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] - } - ] - }, + "input": "0.0000003", + "output": "0.0000012", + "input_cache_read": "0.000000007", "varies_by_provider": true, "fast": { "input": "0.0000006", @@ -7219,9 +7173,9 @@ }, "regional": { "us": { - "input": "0.00000045", - "output": "0.0000018", - "input_cache_read": "0.000000009" + "input": "0.0000003", + "output": "0.0000012", + "input_cache_read": "0.000000007" } } } @@ -7349,56 +7303,367 @@ } }, { - "id": "elorian/glimpse", + "id": "elevenlabs/eleven-flash-v2", "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", + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Flash v2", + "description": "English-only text-to-speech optimized for ultra-low latency in real-time applications. Accepts up to 30,000 characters per request and is billed per input character.", + "type": "speech", "zdr": "none", "no_training": "none", - "tags": ["implicit-caching", "reasoning", "video-input", "vision"], - "supported_specifications": ["v2", "v3", "v4"], + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], "modalities": { - "input": ["text", "image", "video"], - "output": ["text"] + "input": ["text"], + "output": ["audio"] }, - "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" + "input": "0.00002", + "speech_input_character_cost": "0.00002" } }, { - "id": "fireworks/ember-1", + "id": "elevenlabs/eleven-flash-v2.5", "object": "model", "created": 1755815280, - "released": 1790121600, - "owned_by": "fireworks", - "name": "Ember-1", - "description": "Ember-1 is Fireworks’ research-preview reasoning model built on Kimi K3 for coding and agentic workflows. It supports image input, function calling, and a 1M-token context window. Fireworks reports approximately 40% fewer generated tokens while maintaining comparable quality across its evaluations, helping reduce the cost of workloads with extensive reasoning.", - "context_window": 1048576, - "max_tokens": 1048576, - "type": "language", - "zdr": "all", + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Flash v2.5", + "description": "Ultra-low-latency text-to-speech for real-time applications in 32 languages. Accepts up to 40,000 characters per request and is billed per input character.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00002", + "speech_input_character_cost": "0.00002" + } + }, + { + "id": "elevenlabs/eleven-multilingual-v2", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Multilingual v2", + "description": "Lifelike text-to-speech with consistent voice quality for long-form audio in 29 languages. Accepts up to 10,000 characters per request and is billed per input character.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00004", + "speech_input_character_cost": "0.00004" + } + }, + { + "id": "elevenlabs/eleven-realtime-v1-max", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Realtime v1 Max", + "description": "A speech-to-speech voice agent optimized for complex instructions, reasoning, and multi-step tool use, with speech recognition, turn-taking, and voice generation tuned as one system. Supports more than 90 languages through an OpenAI-compatible Realtime WebSocket API. Billed for connected session duration plus input and output tokens.", + "context_window": 0, + "max_tokens": 0, + "type": "realtime", + "zdr": "none", + "no_training": "none", + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text", "audio"], + "output": ["text", "audio"] + }, + "supported_parameters": ["max_tokens", "temperature", "stop"], + "temperature": true, + "pricing": { + "input": "0.0000009", + "output": "0.0000045", + "input_cache_read": "0.00000009", + "realtime_session_duration_cost_per_second": "0.0006667" + } + }, + { + "id": "elevenlabs/eleven-realtime-v1-mini", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Realtime v1 Mini", + "description": "A speech-to-speech voice agent optimized for fast, natural conversation, with speech recognition, turn-taking, interruption handling, and voice generation tuned as one system. Supports more than 90 languages through an OpenAI-compatible Realtime WebSocket API. Billed for connected session duration plus input and output tokens.", + "context_window": 0, + "max_tokens": 0, + "type": "realtime", + "zdr": "none", + "no_training": "none", + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text", "audio"], + "output": ["text", "audio"] + }, + "supported_parameters": ["max_tokens", "temperature", "stop"], + "temperature": true, + "pricing": { + "input": "0.0000001", + "output": "0.000003", + "input_cache_read": "0.00000001", + "realtime_session_duration_cost_per_second": "0.0006667" + } + }, + { + "id": "elevenlabs/eleven-v3", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven v3", + "description": "Emotionally rich text-to-speech with inline audio tags for delivery and expression, supporting more than 70 languages. Accepts up to 5,000 characters per request and is billed per input character, including audio tags.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00004", + "speech_input_character_cost": "0.00004" + } + }, + { + "id": "elevenlabs/eleven-v3-conversational", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven v3 Conversational", + "description": "A low-latency Eleven v3 variant tuned for conversational agents, with expressive audio tags and support for more than 70 languages. Accepts up to 5,000 characters per request and is billed per input character.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00002", + "speech_input_character_cost": "0.00002" + } + }, + { + "id": "elevenlabs/eleven-v4", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven v4", + "description": "ElevenLabs' expressive text-to-speech model with audio tags for emotion and delivery, multilingual speech, and multi-speaker dialogue support. Accepts up to 10,000 characters per request and is billed per input character.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00004", + "speech_input_character_cost": "0.00004" + } + }, + { + "id": "elevenlabs/eleven-v4-turbo", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven v4 Turbo", + "description": "A low-latency Eleven v4 variant for real-time and conversational applications, with expressive audio tags and multilingual speech. Accepts up to 10,000 characters per request and is billed per input character.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-speech"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "input": "0.00002", + "speech_input_character_cost": "0.00002" + } + }, + { + "id": "elevenlabs/music-v2", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Music v2", + "description": "Music generation from text prompts, billed per second of generated audio.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["music"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "speech_output_cost_per_second": "0.00125" + } + }, + { + "id": "elevenlabs/music-v2.5", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Music v2.5", + "description": "Music generation from text prompts, billed per second of generated audio.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["music"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "speech_output_cost_per_second": "0.00125" + } + }, + { + "id": "elevenlabs/scribe-v2", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Scribe v2", + "description": "Multilingual speech-to-text with speaker diarization, word-level timestamps, and audio event tagging. Supports more than 90 languages and is billed per second of input audio.", + "type": "transcription", + "zdr": "none", + "no_training": "none", + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "pricing": { + "input": "0", + "transcription_duration_cost_per_second": "0.000030556" + } + }, + { + "id": "elevenlabs/scribe-v2-realtime", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Scribe v2 Realtime", + "description": "Real-time speech-to-text over WebSocket with manual or voice-activity-based commits, optional word timestamps, and language detection. Supports PCM and mu-law audio and is billed per second of streamed audio.", + "type": "transcription", + "zdr": "none", + "no_training": "none", + "tags": ["websocket-transcription"], + "supported_specifications": ["v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "pricing": {} + }, + { + "id": "elevenlabs/sound-effects-v2", + "object": "model", + "created": 1755815280, + "released": 1793059200, + "owned_by": "elevenlabs", + "name": "Eleven Sound Effects v2", + "description": "Sound effects generation from text prompts, billed per second of generated audio.", + "type": "speech", + "zdr": "none", + "no_training": "none", + "tags": ["sound-effects"], + "supported_specifications": ["v4"], + "modalities": { + "input": ["text"], + "output": ["audio"] + }, + "pricing": { + "speech_output_cost_per_second": "0.001" + } + }, + { + "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" + } + }, + { + "id": "fireworks/ember-1", + "object": "model", + "created": 1755815280, + "released": 1790121600, + "owned_by": "fireworks", + "name": "Ember-1", + "description": "Ember-1 is Fireworks’ research-preview reasoning model built on Kimi K3 for coding and agentic workflows. It supports image input, function calling, and a 1M-token context window. Fireworks reports approximately 40% fewer generated tokens while maintaining comparable quality across its evaluations, helping reduce the cost of workloads with extensive reasoning.", + "context_window": 1048576, + "max_tokens": 1048576, + "type": "language", + "zdr": "all", "no_training": "all", "tags": ["implicit-caching", "reasoning", "tool-use", "vision"], "supported_specifications": ["v2", "v3", "v4"], @@ -10607,15 +10872,63 @@ "resolution": "2k", "mode": "reference_to_video", "cost_per_second": "0.09" - } - ] - } - }, - { - "id": "inception/mercury-2", - "object": "model", - "created": 1755815280, - "released": 1771891200, + }, + { + "duration_over_seconds": 15, + "resolution": "480p", + "mode": "text_to_video", + "cost_per_second": "0.045" + }, + { + "duration_over_seconds": 15, + "resolution": "768p", + "mode": "text_to_video", + "cost_per_second": "0.075" + }, + { + "duration_over_seconds": 15, + "resolution": "1080p", + "mode": "text_to_video", + "cost_per_second": "0.105" + }, + { + "duration_over_seconds": 15, + "resolution": "2k", + "mode": "text_to_video", + "cost_per_second": "0.105" + }, + { + "duration_over_seconds": 15, + "resolution": "480p", + "mode": "image_to_video", + "cost_per_second": "0.045" + }, + { + "duration_over_seconds": 15, + "resolution": "768p", + "mode": "image_to_video", + "cost_per_second": "0.075" + }, + { + "duration_over_seconds": 15, + "resolution": "1080p", + "mode": "image_to_video", + "cost_per_second": "0.105" + }, + { + "duration_over_seconds": 15, + "resolution": "2k", + "mode": "image_to_video", + "cost_per_second": "0.105" + } + ] + } + }, + { + "id": "inception/mercury-2", + "object": "model", + "created": 1755815280, + "released": 1771891200, "owned_by": "inception", "name": "Mercury 2", "description": "A diffusion-based reasoning LLM that generates text via parallel refinement (not token-by-token), delivering real-time latency with ~1k tokens/sec plus 128K context and built-in tool/JSON support.", @@ -10648,6 +10961,7 @@ "values": ["instant", "low", "medium", "high"] } ], + "deprecated_at": 1794719100000, "pricing": { "input": "0.00000025", "output": "0.00000075", @@ -10691,6 +11005,7 @@ "values": ["instant", "low", "medium", "high"] } ], + "deprecated_at": 1794719100000, "pricing": { "input": "0.00000004", "output": "0.00000015", @@ -10769,6 +11084,7 @@ "structured_outputs" ], "temperature": true, + "deprecated_at": 1794719100000, "pricing": { "input": "0.00000025", "output": "0.000001" @@ -10825,7 +11141,7 @@ "context_window": 256000, "max_tokens": 32000, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "implicit-caching", @@ -10991,6 +11307,50 @@ "input_cache_read": "0.00000006" } }, + { + "id": "inclusionai/ling-3.1-flash-1019", + "object": "model", + "created": 1755815280, + "released": 1793318400, + "owned_by": "inclusionai", + "name": "Ling 3.1 Flash 1019", + "description": "Ling 3.1 Flash 1019 is InclusionAI's updated hybrid reasoning language model for coding, multi-step analysis, and tool-using agents. Its mixture-of-experts architecture has 560B total parameters with 25B active per token, and its 1M-token context window supports long-document analysis and extended agentic workflows.", + "context_window": 1000000, + "max_tokens": 262144, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": ["implicit-caching", "reasoning", "tool-use", "open-weights"], + "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": "0.0000003", + "output": "0.0000009", + "input_cache_read": "0.00000006" + } + }, { "id": "inference-net/schematron-v2-small", "object": "model", @@ -11689,13 +12049,13 @@ } }, { - "id": "meituan/longcat-2.5-preview", + "id": "meituan/longcat-2.5", "object": "model", "created": 1755815280, - "released": 1790380800, + "released": 1793577600, "owned_by": "meituan", - "name": "LongCat 2.5 Preview", - "description": "LongCat-2.5-Preview is Meituan’s multimodal reasoning model for coding and agentic workflows, with a 1M-token context window and support for text and image inputs. It combines image understanding, visual question answering, and content summarization with code generation, code understanding, and automated programming, and supports tool calling and optional thinking for complex tasks.", + "name": "LongCat 2.5", + "description": "LongCat 2.5 is Meituan’s native multimodal model for coding and long-running agent workflows. It combines visual understanding with multi-step reasoning and tool use to work across complex codebases and full-project development. Its 1M-token context window supports tasks involving large documents, codebases, and text and image inputs.", "context_window": 1048576, "max_tokens": 131072, "type": "language", @@ -11704,9 +12064,9 @@ "tags": [ "implicit-caching", "reasoning", + "structured-output", "tool-use", - "vision", - "structured-output" + "vision" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -11728,6 +12088,10 @@ "reasoning_options": [ { "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high"] } ], "pricing": { @@ -11926,7 +12290,7 @@ "context_window": 128000, "max_tokens": 8192, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": ["tool-use", "vision", "open-weights", "structured-output"], "supported_specifications": ["v2", "v3", "v4"], @@ -13186,18 +13550,18 @@ "released": 1792368000, "owned_by": "minimax", "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, + "description": "MiniMax-M3.1-Flash is MiniMax’s multimodal M-series model for agent reasoning, tool use, coding, and long-context tasks. Fireworks serves the final weights with hybrid MXFP8 and NVFP4 expert precision, text and image inputs, structured outputs, and implicit prompt caching.", + "context_window": 1048576, + "max_tokens": 1048576, "type": "language", - "zdr": "none", - "no_training": "none", + "zdr": "some", + "no_training": "some", "tags": [ "implicit-caching", "reasoning", + "structured-output", "tool-use", "vision", - "structured-output", "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], @@ -13224,8 +13588,10 @@ } ], "pricing": { - "input": "0", - "output": "0" + "input": "0.00000015", + "output": "0.0000006", + "input_cache_read": "0.000000015", + "varies_by_provider": true } }, { @@ -13461,11 +13827,11 @@ "id": "mistral/mistral-large-4", "object": "model", "created": 1755815280, - "released": 1791244800, + "released": 1793232000, "owned_by": "mistral", "name": "Mistral Large 4", - "description": "Mistral Large 4 is Mistral AI's open-weight, natively multimodal model, available in public preview with 1.05 trillion total parameters and 49 billion active parameters. It leads aggregated benchmarks among open-weight models from the US and Europe, with strengths in cyber defense, manufacturing, finance, and visual grounding.", - "context_window": 524288, + "description": "Mistral Large 4 is Mistral AI's open-weight, natively multimodal model, available in public preview with 1.05 trillion total parameters and 49 billion active parameters. It leads aggregated benchmarks among open-weight models from the US and Europe, with strengths in cyber defense, manufacturing, finance, and visual grounding. This model uses the latest weights from Mistral.", + "context_window": 1048576, "max_tokens": 262144, "type": "language", "zdr": "all", @@ -13498,9 +13864,9 @@ } ], "pricing": { - "input": "0.00000136", - "output": "0.00000418", - "input_cache_read": "0.00000014" + "input": "0.0000007", + "output": "0.0000021", + "input_cache_read": "0.00000007" } }, { @@ -13560,7 +13926,7 @@ "context_window": 131072, "max_tokens": 131072, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["tool-use", "structured-output", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -14093,6 +14459,108 @@ "varies_by_provider": true } }, + { + "id": "moonshotai/kimi-k3.1-pro", + "object": "model", + "created": 1755815280, + "released": 1792713600, + "owned_by": "moonshotai", + "name": "Kimi K3.1 Pro", + "description": "Kimi K3.1 Pro is a frontier model from Moonshot AI for complex reasoning, coding, and agentic workflows, with support for vision, tool use, structured outputs, and long-context tasks.", + "context_window": 1048576, + "max_tokens": 1048576, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "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": "effort", + "values": ["low", "high", "max"] + } + ], + "pricing": { + "input": "0.000002", + "output": "0.00001", + "input_cache_read": "0.0000002", + "input_cache_write": "0.000002" + } + }, + { + "id": "moonshotai/kimi-k3.1-pro-highspeed", + "object": "model", + "created": 1755815280, + "released": 1792713600, + "owned_by": "moonshotai", + "name": "Kimi K3.1 Pro Highspeed", + "description": "Kimi K3.1 Pro Highspeed is the high-speed variant of Moonshot AI’s frontier Kimi K3.1 Pro model for complex reasoning, coding, and agentic workflows, with vision, tool use, structured outputs, and long-context support.", + "context_window": 1048576, + "max_tokens": 1048576, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "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": "effort", + "values": ["low", "high", "max"] + } + ], + "pricing": { + "input": "0.000004", + "output": "0.00002", + "input_cache_read": "0.0000002", + "input_cache_write": "0.000004" + } + }, { "id": "morph/morph-v3-fast", "object": "model", @@ -14166,7 +14634,7 @@ "context_window": 262144, "max_tokens": 262144, "type": "language", - "zdr": "all", + "zdr": "none", "no_training": "all", "tags": ["reasoning", "tool-use", "open-weights"], "supported_specifications": ["v2", "v3", "v4"], @@ -14255,7 +14723,7 @@ "context_window": 1000000, "max_tokens": 65000, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": [ "reasoning", @@ -14421,7 +14889,7 @@ "max_tokens": 1048576, "type": "language", "zdr": "some", - "no_training": "some", + "no_training": "all", "tags": [ "implicit-caching", "reasoning", @@ -14559,22 +15027,30 @@ } }, { - "id": "openai/gpt-3.5-turbo", + "id": "openai/gpt-4.1", "object": "model", "created": 1755815280, - "released": 1677628800, + "released": 1744588800, "owned_by": "openai", - "name": "GPT-3.5 Turbo", - "description": "OpenAI's most capable and cost effective model in the GPT-3.5 family optimized for chat purposes, but also works well for traditional completions tasks.", - "context_window": 16385, - "max_tokens": 4096, + "name": "GPT-4.1", + "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": "all", "no_training": "all", - "tags": ["tool-use"], + "tags": [ + "file-input", + "implicit-caching", + "tool-use", + "vision", + "web-search", + "structured-output", + "fast" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text"], + "input": ["text", "image", "pdf"], "output": ["text"] }, "supported_parameters": [ @@ -14582,110 +15058,36 @@ "temperature", "stop", "tools", - "tool_choice" + "tool_choice", + "response_format", + "structured_outputs" ], "temperature": true, - "knowledge": "2021-09-01", + "knowledge": "2024-06-01", "pricing": { - "input": "0.0000005", - "output": "0.0000015" + "input": "0.000002", + "output": "0.000008", + "input_cache_read": "0.0000005", + "web_search": "10", + "service_tiers": { + "priority": { + "input": "0.0000035", + "output": "0.000014", + "input_cache_read": "0.000000875" + } + }, + "fast": { + "input": "0.0000035", + "output": "0.000014", + "input_cache_read": "0.000000875" + } } }, { - "id": "openai/gpt-4-turbo", + "id": "openai/gpt-4.1-batch", "object": "model", "created": 1755815280, - "released": 1712620800, - "owned_by": "openai", - "name": "GPT-4 Turbo", - "description": "gpt-4-turbo from OpenAI has broad general knowledge and domain expertise allowing it to follow complex instructions in natural language and solve difficult problems accurately. It has a knowledge cutoff of April 2023 and a 128,000 token context window.", - "context_window": 128000, - "max_tokens": 4096, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": ["tool-use", "vision"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text", "image"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice" - ], - "temperature": true, - "knowledge": "2023-12-01", - "pricing": { - "input": "0.00001", - "output": "0.00003" - } - }, - { - "id": "openai/gpt-4.1", - "object": "model", - "created": 1755815280, - "released": 1744588800, - "owned_by": "openai", - "name": "GPT-4.1", - "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": "all", - "no_training": "all", - "tags": [ - "file-input", - "implicit-caching", - "tool-use", - "vision", - "web-search", - "structured-output", - "fast" - ], - "supported_specifications": ["v2", "v3", "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": "0.000002", - "output": "0.000008", - "input_cache_read": "0.0000005", - "web_search": "10", - "service_tiers": { - "priority": { - "input": "0.0000035", - "output": "0.000014", - "input_cache_read": "0.000000875" - } - }, - "fast": { - "input": "0.0000035", - "output": "0.000014", - "input_cache_read": "0.000000875" - } - } - }, - { - "id": "openai/gpt-4.1-batch", - "object": "model", - "created": 1755815280, - "released": 1744588800, + "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.", @@ -14931,8 +15333,7 @@ "tool-use", "vision", "web-search", - "structured-output", - "fast" + "structured-output" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -14953,108 +15354,8 @@ "pricing": { "input": "0.0000001", "output": "0.0000004", - "input_cache_read": "0.000000025", - "web_search": "10", - "service_tiers": { - "priority": { - "input": "0.0000002", - "output": "0.0000008", - "input_cache_read": "0.00000005" - } - }, - "varies_by_provider": true, - "fast": { - "input": "0.0000002", - "output": "0.0000008", - "input_cache_read": "0.00000005" - } - } - }, - { - "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", - "created": 1755815280, - "released": 1744588800, - "owned_by": "openai", - "name": "GPT-4.1 nano (Fast)", - "description": "GPT-4.1 nano is the fastest, most cost-effective GPT 4.1 model.", - "context_window": 1047576, - "max_tokens": 32768, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": [ - "file-input", - "implicit-caching", - "tool-use", - "vision", - "web-search", - "structured-output", - "fast" - ], - "supported_specifications": ["v2", "v3", "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", - "web_search": "10" + "input_cache_read": "0.00000003", + "web_search": "14" } }, { @@ -20982,8 +21283,9 @@ "context_window": 1050000, "max_tokens": 0, "type": "evaluation", - "zdr": "none", + "zdr": "all", "no_training": "all", + "regions": ["eu", "us"], "supported_specifications": ["v4"], "modalities": { "input": ["text"], @@ -20999,83 +21301,197 @@ } ], "pricing": { - "input": "0.0000001" - } - }, - { - "id": "openai/gpt-6-luna-fast", - "object": "model", - "created": 1755815280, - "released": 1790035200, - "owned_by": "openai", - "name": "GPT-6 Luna (Fast)", - "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": "some", - "no_training": "all", - "tags": [ - "explicit-caching", - "file-input", - "implicit-caching", - "reasoning", - "structured-output", - "tool-use", - "vision", - "web-search", - "fast" - ], - "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", "xhigh", "max"] - } - ], - "knowledge": "2026-05-18", - "pricing": { - "input": "0.0000002", + "input": "0.0000001", "input_tiers": [ { - "cost": "0.0000002", + "cost": "0.0000001", "min": 0, "max": 272001 }, { - "cost": "0.0000004", + "cost": "0.0000002", "min": 272001 } ], - "output": "0.000001", - "output_tiers": [ + "output": "0", + "input_cache_read": "0.00000001", + "input_cache_read_tiers": [ { - "cost": "0.000001", + "cost": "0.00000001", "min": 0, "max": 272001 }, { - "cost": "0.0000015", + "cost": "0.00000002", + "min": 272001 + } + ], + "input_cache_write": "0.000000125", + "input_cache_write_tiers": [ + { + "cost": "0.000000125", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000025", + "min": 272001 + } + ], + "regional": { + "eu": { + "input": "0.00000011", + "input_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000022", + "min": 272001 + } + ], + "input_cache_read": "0.000000011", + "input_cache_read_tiers": [ + { + "cost": "0.000000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000000022", + "min": 272001 + } + ], + "input_cache_write": "0.0000001375", + "input_cache_write_tiers": [ + { + "cost": "0.0000001375", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000000275", + "min": 272001 + } + ] + }, + "us": { + "input": "0.00000011", + "input_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000022", + "min": 272001 + } + ], + "input_cache_read": "0.000000011", + "input_cache_read_tiers": [ + { + "cost": "0.000000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000000022", + "min": 272001 + } + ], + "input_cache_write": "0.0000001375", + "input_cache_write_tiers": [ + { + "cost": "0.0000001375", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000000275", + "min": 272001 + } + ] + } + } + } + }, + { + "id": "openai/gpt-6-luna-fast", + "object": "model", + "created": 1755815280, + "released": 1790035200, + "owned_by": "openai", + "name": "GPT-6 Luna (Fast)", + "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": "some", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "web-search", + "fast" + ], + "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", "xhigh", "max"] + } + ], + "knowledge": "2026-05-18", + "pricing": { + "input": "0.0000002", + "input_tiers": [ + { + "cost": "0.0000002", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000004", + "min": 272001 + } + ], + "output": "0.000001", + "output_tiers": [ + { + "cost": "0.000001", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000015", "min": 272001 } ], @@ -22480,65 +22896,624 @@ } }, { - "id": "openai/gpt-image-1", - "object": "model", - "created": 1755815280, - "released": 1742860800, - "owned_by": "openai", - "name": "GPT Image 1", - "description": "GPT Image 1 is OpenAI's new state-of-the-art image generation model. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.", - "context_window": 0, - "max_tokens": 0, - "type": "image", - "zdr": "none", - "no_training": "all", - "tags": ["image-generation", "implicit-caching"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["image"] - }, - "pricing": { - "input": "0.000005", - "output": "0.00004", - "input_cache_read": "0.00000125" - } - }, - { - "id": "openai/gpt-image-1-mini", + "id": "openai/gpt-6.1-terra", "object": "model", "created": 1755815280, - "released": 1759708800, + "released": 1792972800, "owned_by": "openai", - "name": "GPT Image 1 Mini", - "description": "A cost-efficient version of GPT Image 1. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.", - "context_window": 0, - "max_tokens": 0, - "type": "image", - "zdr": "none", + "name": "GPT-6.1 Terra", + "description": "GPT-6.1 Terra is OpenAI’s model for visual reasoning, precise computer use, and natural writing. It accepts text and images and generates text, with configurable reasoning effort, structured outputs, tool calling through the Responses API, and implicit and explicit prompt caching.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "all", "no_training": "all", - "tags": ["image-generation", "implicit-caching"], + "tags": [ + "explicit-caching", + "file-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "web-search", + "fast" + ], + "regions": ["eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text"], - "output": ["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, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "medium", "high", "xhigh", "max"] + } + ], "pricing": { - "input": "0.000002", - "output": "0.000008", - "input_cache_read": "0.0000002" - } - }, - { - "id": "openai/gpt-image-1.5", - "object": "model", - "created": 1755815280, - "released": 1765843200, - "owned_by": "openai", - "name": "GPT Image 1.5", - "description": "GPT Image 1.5 is OpenAI's latest image generation model, with better instruction following and adherence to prompts.", - "context_window": 0, - "max_tokens": 0, + "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 + } + ], + "web_search": "10", + "service_tiers": { + "flex": { + "input": "0.0000005", + "output": "0.0000025", + "input_cache_read": "0.000000025", + "long_context": { + "threshold": 272001, + "input": "0.000001", + "output": "0.00000375", + "input_cache_read": "0.00000005" + } + }, + "priority": { + "input": "0.000002", + "output": "0.00001", + "input_cache_read": "0.0000001", + "long_context": { + "threshold": 272001, + "input": "0.000004", + "output": "0.000015", + "input_cache_read": "0.0000002" + } + } + }, + "fast": { + "input": "0.000002", + "input_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000004", + "min": 272001 + } + ], + "output": "0.00001", + "output_tiers": [ + { + "cost": "0.00001", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000015", + "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": "0.0000025", + "input_cache_write_tiers": [ + { + "cost": "0.0000025", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000005", + "min": 272001 + } + ] + }, + "regional": { + "eu": { + "input": "0.0000011", + "input_tiers": [ + { + "cost": "0.0000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000022", + "min": 272001 + } + ], + "output": "0.0000055", + "output_tiers": [ + { + "cost": "0.0000055", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000825", + "min": 272001 + } + ], + "input_cache_read": "0.000000055", + "input_cache_read_tiers": [ + { + "cost": "0.000000055", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000011", + "min": 272001 + } + ], + "input_cache_write": "0.000001375", + "input_cache_write_tiers": [ + { + "cost": "0.000001375", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000275", + "min": 272001 + } + ], + "fast": { + "input": "0.0000022", + "input_tiers": [ + { + "cost": "0.0000022", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000044", + "min": 272001 + } + ], + "output": "0.000011", + "output_tiers": [ + { + "cost": "0.000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000165", + "min": 272001 + } + ], + "input_cache_read": "0.00000011", + "input_cache_read_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000022", + "min": 272001 + } + ], + "input_cache_write": "0.00000275", + "input_cache_write_tiers": [ + { + "cost": "0.00000275", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000055", + "min": 272001 + } + ] + } + }, + "us": { + "input": "0.0000011", + "input_tiers": [ + { + "cost": "0.0000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000022", + "min": 272001 + } + ], + "output": "0.0000055", + "output_tiers": [ + { + "cost": "0.0000055", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000825", + "min": 272001 + } + ], + "input_cache_read": "0.000000055", + "input_cache_read_tiers": [ + { + "cost": "0.000000055", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000011", + "min": 272001 + } + ], + "input_cache_write": "0.000001375", + "input_cache_write_tiers": [ + { + "cost": "0.000001375", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000275", + "min": 272001 + } + ], + "fast": { + "input": "0.0000022", + "input_tiers": [ + { + "cost": "0.0000022", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000044", + "min": 272001 + } + ], + "output": "0.000011", + "output_tiers": [ + { + "cost": "0.000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000165", + "min": 272001 + } + ], + "input_cache_read": "0.00000011", + "input_cache_read_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000022", + "min": 272001 + } + ], + "input_cache_write": "0.00000275", + "input_cache_write_tiers": [ + { + "cost": "0.00000275", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000055", + "min": 272001 + } + ] + } + } + } + } + }, + { + "id": "openai/gpt-6.1-terra-fast", + "object": "model", + "created": 1755815280, + "released": 1792972800, + "owned_by": "openai", + "name": "GPT-6.1 Terra (Fast)", + "description": "GPT-6.1 Terra is OpenAI’s model for visual reasoning, precise computer use, and natural writing. It accepts text and images and generates text, with configurable reasoning effort, structured outputs, tool calling through the Responses API, and implicit and explicit prompt caching.", + "context_window": 1050000, + "max_tokens": 128000, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": [ + "explicit-caching", + "file-input", + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision", + "web-search", + "fast" + ], + "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", "xhigh", "max"] + } + ], + "pricing": { + "input": "0.000002", + "input_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000004", + "min": 272001 + } + ], + "output": "0.00001", + "output_tiers": [ + { + "cost": "0.00001", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000015", + "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": "0.0000025", + "input_cache_write_tiers": [ + { + "cost": "0.0000025", + "min": 0, + "max": 272001 + }, + { + "cost": "0.000005", + "min": 272001 + } + ], + "web_search": "10", + "regional": { + "eu": { + "input": "0.0000022", + "input_tiers": [ + { + "cost": "0.0000022", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000044", + "min": 272001 + } + ], + "output": "0.000011", + "output_tiers": [ + { + "cost": "0.000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000165", + "min": 272001 + } + ], + "input_cache_read": "0.00000011", + "input_cache_read_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000022", + "min": 272001 + } + ], + "input_cache_write": "0.00000275", + "input_cache_write_tiers": [ + { + "cost": "0.00000275", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000055", + "min": 272001 + } + ] + }, + "us": { + "input": "0.0000022", + "input_tiers": [ + { + "cost": "0.0000022", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000044", + "min": 272001 + } + ], + "output": "0.000011", + "output_tiers": [ + { + "cost": "0.000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000165", + "min": 272001 + } + ], + "input_cache_read": "0.00000011", + "input_cache_read_tiers": [ + { + "cost": "0.00000011", + "min": 0, + "max": 272001 + }, + { + "cost": "0.00000022", + "min": 272001 + } + ], + "input_cache_write": "0.00000275", + "input_cache_write_tiers": [ + { + "cost": "0.00000275", + "min": 0, + "max": 272001 + }, + { + "cost": "0.0000055", + "min": 272001 + } + ] + } + } + } + }, + { + "id": "openai/gpt-image-1-mini", + "object": "model", + "created": 1755815280, + "released": 1759708800, + "owned_by": "openai", + "name": "GPT Image 1 Mini", + "description": "A cost-efficient version of GPT Image 1. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.", + "context_window": 0, + "max_tokens": 0, + "type": "image", + "zdr": "none", + "no_training": "all", + "tags": ["image-generation", "implicit-caching"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["image"] + }, + "pricing": { + "input": "0.000002", + "output": "0.000008", + "input_cache_read": "0.0000002" + } + }, + { + "id": "openai/gpt-image-1.5", + "object": "model", + "created": 1755815280, + "released": 1765843200, + "owned_by": "openai", + "name": "GPT Image 1.5", + "description": "GPT Image 1.5 is OpenAI's latest image generation model, with better instruction following and adherence to prompts.", + "context_window": 0, + "max_tokens": 0, "type": "image", "zdr": "none", "no_training": "all", @@ -22656,6 +23631,28 @@ "realtime_session_duration_cost_per_second": "0.0008334" } }, + { + "id": "openai/gpt-live-transcribe", + "object": "model", + "created": 1755815280, + "released": 1785196800, + "owned_by": "openai", + "name": "GPT Live Transcribe", + "description": "GPT Live Transcribe is a low-latency streaming speech-to-text model for live audio, with tunable latency, context, keyword hints, and multiple language hints. Priced by audio duration.", + "type": "transcription", + "zdr": "none", + "no_training": "all", + "tags": ["websocket-transcription"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "pricing": { + "input": "0.0000000002", + "transcription_duration_cost_per_second": "0.00028334" + } + }, { "id": "openai/gpt-oss-120b", "object": "model", @@ -22726,7 +23723,7 @@ "context_window": 131072, "max_tokens": 8192, "type": "language", - "zdr": "all", + "zdr": "some", "no_training": "all", "tags": [ "reasoning", @@ -23025,6 +24022,28 @@ "transcription_duration_cost_per_second": "0.000284" } }, + { + "id": "openai/gpt-transcribe", + "object": "model", + "created": 1755815280, + "released": 1785196800, + "owned_by": "openai", + "name": "GPT Transcribe", + "description": "GPT Transcribe is a high-accuracy speech-to-text model for completed audio files, streamed file transcripts, and committed turns in Realtime sessions. It supports context, keyword hints, and multiple language hints. Priced by audio duration.", + "type": "transcription", + "zdr": "none", + "no_training": "all", + "tags": ["websocket-transcription"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "pricing": { + "input": "0", + "transcription_duration_cost_per_second": "0.000075" + } + }, { "id": "openai/o1", "object": "model", @@ -23072,7 +24091,8 @@ "pricing": { "input": "0.000015", "output": "0.00006", - "input_cache_read": "0.0000075" + "input_cache_read": "0.0000075", + "web_search": "14" } }, { @@ -23238,7 +24258,8 @@ "pricing": { "input": "0.0000011", "output": "0.0000044", - "input_cache_read": "0.00000055" + "input_cache_read": "0.00000055", + "web_search": "14" } }, { @@ -23312,8 +24333,7 @@ "tool-use", "vision", "web-search", - "structured-output", - "fast" + "structured-output" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -23342,77 +24362,7 @@ "input": "0.0000011", "output": "0.0000044", "input_cache_read": "0.000000275", - "web_search": "10", - "service_tiers": { - "priority": { - "input": "0.000002", - "output": "0.000008", - "input_cache_read": "0.0000005" - }, - "flex": { - "input": "0.00000055", - "output": "0.0000022", - "input_cache_read": "0.000000138" - } - }, - "fast": { - "input": "0.000002", - "output": "0.000008", - "input_cache_read": "0.0000005" - } - } - }, - { - "id": "openai/o4-mini-fast", - "object": "model", - "created": 1755815280, - "released": 1744761600, - "owned_by": "openai", - "name": "o4-mini (Fast)", - "description": "OpenAI's o4-mini delivers fast, cost-efficient reasoning with exceptional performance for its size, particularly excelling in math (best-performing on AIME benchmarks), coding, and visual tasks.", - "context_window": 200000, - "max_tokens": 100000, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": [ - "file-input", - "implicit-caching", - "reasoning", - "tool-use", - "vision", - "web-search", - "structured-output", - "fast" - ], - "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": "effort", - "values": ["low", "medium", "high"] - } - ], - "knowledge": "2024-06-01", - "pricing": { - "input": "0.000002", - "output": "0.000008", - "input_cache_read": "0.0000005", - "web_search": "10" + "web_search": "14" } }, { @@ -23543,16 +24493,77 @@ "type": "transcription", "zdr": "none", "no_training": "all", - "tags": ["open-weights"], + "tags": ["open-weights"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["audio"], + "output": ["text"] + }, + "deprecated_at": 1803600000000, + "pricing": { + "input": "0.0000000001", + "transcription_duration_cost_per_second": "0.0001" + } + }, + { + "id": "particle/particle-1", + "object": "model", + "created": 1755815280, + "released": 1793145600, + "owned_by": "particle", + "name": "Particle-1", + "description": "Particle-1 is Particle AI’s model for agentic coding and software engineering, post-trained on DeepSeek V4.1 Flash to complete tasks with fewer tokens. It supports text and image inputs, reasoning, tool use, and implicit prompt caching.", + "context_window": 1048576, + "max_tokens": 131072, + "type": "language", + "zdr": "all", + "no_training": "all", + "tags": ["implicit-caching", "reasoning", "tool-use", "vision"], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["audio"], + "input": ["text", "image"], "output": ["text"] }, - "deprecated_at": 1803600000000, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "reasoning_options": [ + { + "type": "toggle" + }, + { + "type": "effort", + "values": ["none", "low", "high", "max"] + } + ], "pricing": { - "input": "0.0000000001", - "transcription_duration_cost_per_second": "0.0001" + "input": "0.000000125", + "output": "0.0000005", + "input_cache_read": "0.000000015", + "peak_pricing": { + "multiplier": 2, + "windows": [ + { + "start_minute_utc": 480, + "end_minute_utc": 30 + } + ] + }, + "regional": { + "us": { + "input": "0.000000125", + "output": "0.0000005", + "input_cache_read": "0.000000015" + } + } } }, { @@ -23733,46 +24744,6 @@ "input_cache_read": "0.000000009" } }, - { - "id": "poolside/laguna-s-2.1-free", - "object": "model", - "created": 1755815280, - "released": 1784592000, - "owned_by": "poolside", - "name": "Laguna S 2.1 Free", - "description": "Laguna S 2.1 is Poolside's new open-weight model for agentic coding and long-horizon work.", - "context_window": 256000, - "max_tokens": 32768, - "type": "language", - "zdr": "none", - "no_training": "none", - "tags": ["reasoning", "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" - ], - "temperature": true, - "reasoning_options": [ - { - "type": "toggle" - } - ], - "deprecated_at": 1793404800000, - "pricing": { - "input": "0", - "output": "0" - } - }, { "id": "prodia/flux-fast-schnell", "object": "model", @@ -24591,111 +25562,6 @@ "output": "0" } }, - { - "id": "spacexai/grok-4.1-fast-non-reasoning", - "object": "model", - "created": 1755815280, - "released": 1763510400, - "owned_by": "spacexai", - "name": "Grok 4.1 Fast Non-Reasoning", - "description": "", - "context_window": 1000000, - "max_tokens": 1000000, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": [ - "tool-use", - "file-input", - "vision", - "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": "toggle" - }, - { - "type": "effort", - "values": ["none", "low", "medium", "high"] - } - ], - "pricing": { - "input": "0.0000002", - "output": "0.0000005", - "input_cache_read": "0.00000005" - } - }, - { - "id": "spacexai/grok-4.1-fast-reasoning", - "object": "model", - "created": 1755815280, - "released": 1763510400, - "owned_by": "spacexai", - "name": "Grok 4.1 Fast Reasoning", - "description": "", - "context_window": 1000000, - "max_tokens": 1000000, - "type": "language", - "zdr": "all", - "no_training": "all", - "tags": [ - "reasoning", - "file-input", - "vision", - "tool-use", - "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": "toggle" - }, - { - "type": "effort", - "values": ["none", "low", "medium", "high"] - } - ], - "pricing": { - "input": "0.0000002", - "output": "0.0000005", - "input_cache_read": "0.00000005" - } - }, { "id": "spacexai/grok-4.20-multi-agent", "object": "model", @@ -25808,12 +26674,13 @@ "zdr": "all", "no_training": "all", "tags": [ + "implicit-caching", "reasoning", + "structured-output", "tool-use", - "implicit-caching", - "vision", - "structured-output" + "vision" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -25888,6 +26755,46 @@ "input_cache_read": "0.000002" } } + }, + "regional": { + "us": { + "input": "0.0000022", + "input_tiers": [ + { + "cost": "0.0000022", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000044", + "min": 200001 + } + ], + "output": "0.0000066", + "output_tiers": [ + { + "cost": "0.0000066", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000132", + "min": 200001 + } + ], + "input_cache_read": "0.00000055", + "input_cache_read_tiers": [ + { + "cost": "0.00000055", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000011", + "min": 200001 + } + ] + } } } }, @@ -25905,12 +26812,13 @@ "zdr": "all", "no_training": "all", "tags": [ + "implicit-caching", "reasoning", + "structured-output", "tool-use", - "implicit-caching", - "vision", - "structured-output" + "vision" ], + "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text", "image"], @@ -25985,6 +26893,46 @@ "input_cache_read": "0.000002" } } + }, + "regional": { + "us": { + "input": "0.0000022", + "input_tiers": [ + { + "cost": "0.0000022", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000044", + "min": 200001 + } + ], + "output": "0.0000066", + "output_tiers": [ + { + "cost": "0.0000066", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000132", + "min": 200001 + } + ], + "input_cache_read": "0.00000055", + "input_cache_read_tiers": [ + { + "cost": "0.00000055", + "min": 0, + "max": 200001 + }, + { + "cost": "0.0000011", + "min": 200001 + } + ] + } } } }, @@ -26637,7 +27585,7 @@ "context_window": 1048576, "max_tokens": 1048576, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "implicit-caching", @@ -26774,17 +27722,17 @@ "created": 1755815280, "released": 1783296000, "owned_by": "tencent", - "name": "Hy3", + "name": "Tencent Hy3", "description": "Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native 256K context support, and three reasoning modes. It enhances coding, long-form comprehension, multi-turn dialogue, and agentic task execution, balancing reliability, efficiency, and cost across both high-frequency interactions and complex workflows.", "context_window": 262144, "max_tokens": 262144, "type": "language", - "zdr": "some", - "no_training": "some", + "zdr": "none", + "no_training": "none", "tags": [ - "implicit-caching", "reasoning", "tool-use", + "implicit-caching", "structured-output", "open-weights" ], @@ -26818,6 +27766,58 @@ "varies_by_provider": true } }, + { + "id": "tencent/hy4", + "object": "model", + "created": 1755815280, + "released": 1793664000, + "owned_by": "tencent", + "name": "Tencent Hy4", + "description": "Tencent Hy4 is a text model for coding, reasoning, and agentic workflows. It supports tool calling, structured outputs, and prompt caching, with a 1M-token context window for tasks such as software engineering, document analysis, and office automation.", + "context_window": 1024000, + "max_tokens": 64000, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision" + ], + "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", "high"] + } + ], + "pricing": { + "input": "0.000000417", + "output": "0.0000012505", + "input_cache_read": "0.000000021" + } + }, { "id": "tencent/hy4-preview", "object": "model", @@ -26848,6 +27848,9 @@ ], "temperature": true, "reasoning_options": [ + { + "type": "toggle" + }, { "type": "effort", "values": ["none", "high"] @@ -26873,13 +27876,12 @@ "zdr": "some", "no_training": "some", "tags": [ - "implicit-caching", "reasoning", - "structured-output", "tool-use", "vision", - "open-weights", - "file-input" + "file-input", + "structured-output", + "open-weights" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { @@ -26922,7 +27924,7 @@ "context_window": 1000000, "max_tokens": 1000000, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "reasoning", @@ -27030,12 +28032,13 @@ "released": 1789430400, "owned_by": "typesafe-ai", "name": "Jev", - "description": "TypeSafe AI System One decision model. Accepts shared state and typed questions, returning choices, scores, and boolean probabilities. Limits: 64,000 tokens total per request; 32,000 tokens for the state plus the longest question. No streaming or output-token limit.", + "description": "Jev is TypeSafe AI’s System One decision 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": "some", "no_training": "all", + "regions": ["us"], "supported_specifications": ["v4"], "modalities": { "input": ["text"], @@ -27043,7 +28046,12 @@ }, "pricing": { "input": "0.000000042", - "output": "0" + "output": "0", + "regional": { + "us": { + "input": "0.000000042" + } + } } }, { @@ -27060,6 +28068,7 @@ "zdr": "all", "no_training": "all", "tags": ["vision"], + "regions": ["us"], "supported_specifications": ["v4"], "modalities": { "input": ["text", "image"], @@ -27067,7 +28076,12 @@ }, "pricing": { "input": "0.000000042", - "output": "0" + "output": "0", + "regional": { + "us": { + "input": "0.000000042" + } + } } }, { @@ -27084,6 +28098,7 @@ "zdr": "all", "no_training": "all", "tags": ["vision"], + "regions": ["us"], "supported_specifications": ["v4"], "modalities": { "input": ["text", "image"], @@ -27091,7 +28106,12 @@ }, "pricing": { "input": "0.000000042", - "output": "0" + "output": "0", + "regional": { + "us": { + "input": "0.000000042" + } + } } }, { @@ -27402,105 +28422,6 @@ "input": "0.00000012" } }, - { - "id": "xiaomi/mimo-v2.5", - "object": "model", - "created": 1755815280, - "released": 1776816000, - "owned_by": "xiaomi", - "name": "MiMo M2.5", - "description": "A native full-modal model supporting text, image, video, and audio understanding, with powerful Agent capabilities.", - "context_window": 1050000, - "max_tokens": 131100, - "type": "language", - "zdr": "none", - "no_training": "none", - "tags": [ - "reasoning", - "tool-use", - "implicit-caching", - "vision", - "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" - } - ], - "knowledge": "2024-12", - "pricing": { - "input": "0.000000119", - "output": "0.000000238", - "input_cache_read": "0.0000000025" - } - }, - { - "id": "xiaomi/mimo-v2.5-pro", - "object": "model", - "created": 1755815280, - "released": 1776816000, - "owned_by": "xiaomi", - "name": "MiMo V2.5 Pro", - "description": "MiMo V2.5 Pro delivers significant improvements over its predecessor, MiMo-V2-Pro, in general agentic capabilities, complex software engineering, and long-horizon tasks. MiMo-V2.5-Pro is a 1.02T-parameter Mixture-of-Experts model with 42B active parameters, built on a hybrid-attention architecture with a 1M-token context window.", - "context_window": 1050000, - "max_tokens": 131000, - "type": "language", - "zdr": "none", - "no_training": "none", - "tags": [ - "reasoning", - "tool-use", - "implicit-caching", - "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" - } - ], - "knowledge": "2024-12", - "pricing": { - "input": "0.0000003045", - "output": "0.000000609", - "input_cache_read": "0.0000000028" - } - }, { "id": "xiaomi/mimo-v2.6-flash", "object": "model", @@ -27512,7 +28433,7 @@ "context_window": 1048576, "max_tokens": 131072, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "audio-input", @@ -27568,7 +28489,7 @@ "context_window": 1048576, "max_tokens": 131072, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "audio-input", @@ -27828,7 +28749,7 @@ "context_window": 200000, "max_tokens": 96000, "type": "language", - "zdr": "some", + "zdr": "none", "no_training": "some", "tags": [ "implicit-caching", @@ -28216,9 +29137,9 @@ } ], "pricing": { - "input": "0.0000008", - "output": "0.00000255", - "input_cache_read": "0.00000016", + "input": "0.0000014", + "output": "0.0000044", + "input_cache_read": "0.00000014", "varies_by_provider": true, "fast": { "input": "0.0000028", @@ -28535,6 +29456,55 @@ "input_cache_read": "0.000000075" } }, + { + "id": "zai/glm-5.3-flashx-legal", + "object": "model", + "created": 1755815280, + "released": 1793577600, + "owned_by": "zai", + "name": "GLM 5.3 FlashX Legal", + "description": "GLM 5.3 FlashX Legal is Z.ai’s model optimized for legal workflows, including contract review, evidence analysis, and compliance research. It helps teams analyze legal documents, cross-check records, and prepare structured findings for further review.", + "context_window": 1000000, + "max_tokens": 131072, + "type": "language", + "zdr": "none", + "no_training": "none", + "tags": [ + "implicit-caching", + "reasoning", + "structured-output", + "tool-use", + "vision" + ], + "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": "effort", + "values": ["low", "high", "max"] + } + ], + "pricing": { + "input": "0.00000037", + "output": "0.00000125", + "input_cache_read": "0.000000075" + } + }, { "id": "zai/glm-5v-turbo", "object": "model",