From 7e726235fdb34c17d848243849e5d976a4e5322f Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Sat, 30 May 2026 08:12:45 +0000 Subject: [PATCH] chore: sync model metadata from OpenRouter --- .changeset/sync-models.md | 5 + packages/ai-anthropic/src/model-meta.ts | 99 +++ packages/ai-openrouter/src/model-meta.ts | 563 +++++++----------- scripts/.sync-models-last-run | 2 +- scripts/openrouter.models.json | 728 ++++++++++------------- 5 files changed, 647 insertions(+), 750 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 000000000..3949386d6 --- /dev/null +++ b/.changeset/sync-models.md @@ -0,0 +1,5 @@ +--- +'@tanstack/ai-anthropic': patch +--- + +Update model metadata from OpenRouter API diff --git a/packages/ai-anthropic/src/model-meta.ts b/packages/ai-anthropic/src/model-meta.ts index 4272c6136..86301ed7d 100644 --- a/packages/ai-anthropic/src/model-meta.ts +++ b/packages/ai-anthropic/src/model-meta.ts @@ -632,6 +632,84 @@ const CLAUDE_OPUS_4_7_FAST = { AnthropicSamplingOptions > +const CLAUDE_OPUS_4_8 = { + name: 'claude-opus-4.8', + id: 'claude-opus-4.8', + context_window: 1_000_000, + max_output_tokens: 128_000, + supports: { + input: ['text', 'image', 'document'], + extended_thinking: true, + priority_tier: true, + tools: [ + 'web_search', + 'web_fetch', + 'code_execution', + 'computer_use', + 'bash', + 'text_editor', + 'memory', + ], + }, + pricing: { + input: { + normal: 5, + cached: 0.5, + }, + output: { + normal: 25, + }, + }, +} as const satisfies ModelMeta< + AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions +> + +const CLAUDE_OPUS_4_8_FAST = { + name: 'claude-opus-4.8-fast', + id: 'claude-opus-4.8-fast', + context_window: 1_000_000, + max_output_tokens: 128_000, + supports: { + input: ['text', 'image', 'document'], + extended_thinking: true, + priority_tier: true, + tools: [ + 'web_search', + 'web_fetch', + 'code_execution', + 'computer_use', + 'bash', + 'text_editor', + 'memory', + ], + }, + pricing: { + input: { + normal: 10, + cached: 1, + }, + output: { + normal: 50, + }, + }, +} as const satisfies ModelMeta< + AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions +> + export const ANTHROPIC_MODELS = [ CLAUDE_OPUS_4_6.id, CLAUDE_OPUS_4_5.id, @@ -650,6 +728,9 @@ export const ANTHROPIC_MODELS = [ CLAUDE_OPUS_4_7.id, CLAUDE_OPUS_4_7_FAST.id, + + CLAUDE_OPUS_4_8.id, + CLAUDE_OPUS_4_8_FAST.id, ] as const /** @@ -794,6 +875,22 @@ export type AnthropicChatModelProviderOptionsByName = { AnthropicThinkingOptions & AnthropicToolChoiceOptions & AnthropicSamplingOptions + [CLAUDE_OPUS_4_8.id]: AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions + [CLAUDE_OPUS_4_8_FAST.id]: AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions } export type AnthropicChatModelToolCapabilitiesByName = { @@ -838,4 +935,6 @@ export type AnthropicModelInputModalitiesByName = { [CLAUDE_OPUS_4_6_FAST.id]: typeof CLAUDE_OPUS_4_6_FAST.supports.input [CLAUDE_OPUS_4_7.id]: typeof CLAUDE_OPUS_4_7.supports.input [CLAUDE_OPUS_4_7_FAST.id]: typeof CLAUDE_OPUS_4_7_FAST.supports.input + [CLAUDE_OPUS_4_8.id]: typeof CLAUDE_OPUS_4_8.supports.input + [CLAUDE_OPUS_4_8_FAST.id]: typeof CLAUDE_OPUS_4_8_FAST.supports.input } diff --git a/packages/ai-openrouter/src/model-meta.ts b/packages/ai-openrouter/src/model-meta.ts index cec4ced80..16df0a451 100644 --- a/packages/ai-openrouter/src/model-meta.ts +++ b/packages/ai-openrouter/src/model-meta.ts @@ -183,15 +183,15 @@ const _MOONSHOTAI_KIMI_LATEST = { ], }, context_window: 262144, - max_output_tokens: 262142, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.73, - cached: 0.25, + normal: 0.684, + cached: 0.144, }, output: { - normal: 3.49, + normal: 3.42, }, }, image: 0, @@ -410,41 +410,6 @@ const ALFREDPROS_CODELLAMA_7B_INSTRUCT_SOLIDITY = { image: 0, }, } as const -const ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B = { - id: 'alibaba/tongyi-deepresearch-30b-a3b', - name: 'Tongyi DeepResearch 30B A3B', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 131072, - max_output_tokens: 131072, - pricing: { - text: { - input: { - normal: 0.09, - cached: 0.09, - }, - output: { - normal: 0.45, - }, - }, - image: 0, - }, -} as const const ALLENAI_OLMO_3_32B_THINK = { id: 'allenai/olmo-3-32b-think', name: 'AllenAI: Olmo 3 32B Think', @@ -937,6 +902,64 @@ const ANTHROPIC_CLAUDE_OPUS_4_7_FAST = { image: 0, }, } as const +const ANTHROPIC_CLAUDE_OPUS_4_8 = { + id: 'anthropic/claude-opus-4.8', + name: 'Anthropic: Claude Opus 4.8', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'toolChoice', + ], + }, + context_window: 1000000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 5, + cached: 6.75, + }, + output: { + normal: 25, + }, + }, + image: 0, + }, +} as const +const ANTHROPIC_CLAUDE_OPUS_4_8_FAST = { + id: 'anthropic/claude-opus-4.8-fast', + name: 'Anthropic: Claude Opus 4.8 (Fast)', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'toolChoice', + ], + }, + context_window: 1000000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 10, + cached: 13.5, + }, + output: { + normal: 50, + }, + }, + image: 0, + }, +} as const const ANTHROPIC_CLAUDE_SONNET_4 = { id: 'anthropic/claude-sonnet-4', name: 'Anthropic: Claude Sonnet 4', @@ -1157,35 +1180,6 @@ const ARCEE_AI_TRINITY_LARGE_THINKING = { image: 0, }, } as const -const ARCEE_AI_TRINITY_LARGE_THINKING_FREE = { - id: 'arcee-ai/trinity-large-thinking:free', - name: 'Arcee AI: Trinity Large Thinking (free)', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'maxCompletionTokens', - 'reasoning', - 'temperature', - 'toolChoice', - 'topP', - ], - }, - context_window: 262144, - max_output_tokens: 80000, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, -} as const const ARCEE_AI_TRINITY_MINI = { id: 'arcee-ai/trinity-mini', name: 'Arcee AI: Trinity Mini', @@ -1250,29 +1244,6 @@ const ARCEE_AI_VIRTUOSO_LARGE = { image: 0, }, } as const -const BAIDU_COBUDDY_FREE = { - id: 'baidu/cobuddy:free', - name: 'Baidu Qianfan: CoBuddy (free)', - supports: { - input: ['text'], - output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'stop'], - }, - context_window: 131072, - max_output_tokens: 65536, - pricing: { - text: { - input: { - normal: 0, - cached: 0, - }, - output: { - normal: 0, - }, - }, - image: 0, - }, -} as const const BAIDU_ERNIE_4_5_21B_A3B = { id: 'baidu/ernie-4.5-21b-a3b', name: 'Baidu: ERNIE 4.5 21B A3B', @@ -1434,38 +1405,6 @@ const BAIDU_ERNIE_4_5_VL_424B_A47B = { image: 0, }, } as const -const BAIDU_QIANFAN_OCR_FAST = { - id: 'baidu/qianfan-ocr-fast', - name: 'Baidu: Qianfan-OCR-Fast', - supports: { - input: ['image', 'text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 65536, - max_output_tokens: 28672, - pricing: { - text: { - input: { - normal: 0.68, - cached: 0, - }, - output: { - normal: 2.81, - }, - }, - image: 0, - }, -} as const const BYTEDANCE_SEED_SEED_1_6 = { id: 'bytedance-seed/seed-1.6', name: 'ByteDance Seed: Seed 1.6', @@ -1837,16 +1776,16 @@ const DEEPSEEK_DEEPSEEK_CHAT = { 'topP', ], }, - context_window: 163840, - max_output_tokens: 16384, + context_window: 131072, + max_output_tokens: 16000, pricing: { text: { input: { - normal: 0.32, + normal: 0.2288, cached: 0, }, output: { - normal: 0.89, + normal: 0.9144, }, }, image: 0, @@ -2165,40 +2104,6 @@ const DEEPSEEK_DEEPSEEK_V3_2_EXP = { image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_V3_2_SPECIALE = { - id: 'deepseek/deepseek-v3.2-speciale', - name: 'DeepSeek: DeepSeek V3.2 Speciale', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'topP', - ], - }, - context_window: 163840, - max_output_tokens: 163840, - pricing: { - text: { - input: { - normal: 0.287, - cached: 0.058, - }, - output: { - normal: 0.431, - }, - }, - image: 0, - }, -} as const const DEEPSEEK_DEEPSEEK_V4_FLASH = { id: 'deepseek/deepseek-v4-flash', name: 'DeepSeek: DeepSeek V4 Flash', @@ -2222,14 +2127,15 @@ const DEEPSEEK_DEEPSEEK_V4_FLASH = { ], }, context_window: 1048576, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.112, - cached: 0.022, + normal: 0.0983, + cached: 0.0197, }, output: { - normal: 0.224, + normal: 0.1966, }, }, image: 0, @@ -2343,7 +2249,7 @@ const GOOGLE_GEMINI_2_0_FLASH_001 = { 'topP', ], }, - context_window: 1000000, + context_window: 1048576, max_output_tokens: 8192, pricing: { text: { @@ -3143,6 +3049,7 @@ const GOOGLE_GEMMA_4_31B_IT_FREE = { 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topP', @@ -3764,7 +3671,6 @@ const META_LLAMA_LLAMA_3_1_8B_INSTRUCT = { supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -3772,7 +3678,6 @@ const META_LLAMA_LLAMA_3_1_8B_INSTRUCT = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -5408,15 +5313,37 @@ const MOONSHOTAI_KIMI_K2_6 = { ], }, context_window: 262144, - max_output_tokens: 262142, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.73, - cached: 0.25, + normal: 0.684, + cached: 0.144, }, output: { - normal: 3.49, + normal: 3.42, + }, + }, + image: 0, + }, +} as const +const MOONSHOTAI_KIMI_K2_6_FREE = { + id: 'moonshotai/kimi-k2.6:free', + name: 'MoonshotAI: Kimi K2.6 (free)', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: ['reasoning', 'toolChoice'], + }, + context_window: 262144, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, }, }, image: 0, @@ -6540,42 +6467,6 @@ const OPENAI_GPT_4O_2024_11_20 = { image: 0, }, } as const -const OPENAI_GPT_4O_AUDIO_PREVIEW = { - id: 'openai/gpt-4o-audio-preview', - name: 'OpenAI: GPT-4o Audio', - supports: { - input: ['audio', 'text'], - output: ['text', 'audio'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], - }, - context_window: 128000, - max_output_tokens: 16384, - pricing: { - text: { - input: { - normal: 2.5, - cached: 0, - }, - output: { - normal: 10, - }, - }, - image: 0, - }, -} as const const OPENAI_GPT_4O_MINI = { id: 'openai/gpt-4o-mini', name: 'OpenAI: GPT-4o-mini', @@ -6982,12 +6873,12 @@ const OPENAI_GPT_5_1_CHAT = { ], }, context_window: 128000, - max_output_tokens: 16384, + max_output_tokens: 32000, pricing: { text: { input: { normal: 1.25, - cached: 0.125, + cached: 0.13, }, output: { normal: 10, @@ -7017,7 +6908,7 @@ const OPENAI_GPT_5_1_CODEX = { text: { input: { normal: 1.25, - cached: 0.125, + cached: 0.13, }, output: { normal: 10, @@ -7072,12 +6963,12 @@ const OPENAI_GPT_5_1_CODEX_MINI = { ], }, context_window: 400000, - max_output_tokens: 128000, + max_output_tokens: 100000, pricing: { text: { input: { normal: 0.25, - cached: 0.03, + cached: 0.025, }, output: { normal: 2, @@ -7131,7 +7022,7 @@ const OPENAI_GPT_5_2_CHAT = { ], }, context_window: 128000, - max_output_tokens: 32000, + max_output_tokens: 16384, pricing: { text: { input: { @@ -7671,11 +7562,10 @@ const OPENAI_GPT_OSS_20B = { ], }, context_window: 131072, - max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.03, + normal: 0.029, cached: 0, }, output: { @@ -8263,8 +8153,8 @@ const POOLSIDE_LAGUNA_M_1_FREE = { output: ['text'], supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], }, - context_window: 131072, - max_output_tokens: 8192, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { @@ -8286,8 +8176,8 @@ const POOLSIDE_LAGUNA_XS_2_FREE = { output: ['text'], supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], }, - context_window: 131072, - max_output_tokens: 8192, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { @@ -8486,7 +8376,7 @@ const QWEN_QWEN_PLUS_2025_07_28 = { text: { input: { normal: 0.26, - cached: 0.325, + cached: 0, }, output: { normal: 0.78, @@ -8637,7 +8527,6 @@ const QWEN_QWEN3_235B_A22B_2507 = { supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -8645,7 +8534,6 @@ const QWEN_QWEN3_235B_A22B_2507 = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -9561,11 +9449,12 @@ const QWEN_QWEN3_5_35B_A3B = { ], }, context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.139, - cached: 0, + normal: 0.14, + cached: 0.05, }, output: { normal: 1, @@ -9671,7 +9560,7 @@ const QWEN_QWEN3_5_FLASH_02_23 = { text: { input: { normal: 0.065, - cached: 0.08125, + cached: 0, }, output: { normal: 0.26, @@ -9703,7 +9592,7 @@ const QWEN_QWEN3_5_PLUS_02_15 = { text: { input: { normal: 0.26, - cached: 0.325, + cached: 0, }, output: { normal: 1.56, @@ -9735,7 +9624,7 @@ const QWEN_QWEN3_5_PLUS_20260420 = { text: { input: { normal: 0.3, - cached: 0, + cached: 0.375, }, output: { normal: 1.8, @@ -9767,11 +9656,11 @@ const QWEN_QWEN3_6_27B = { ], }, context_window: 262144, - max_output_tokens: 262144, + max_output_tokens: 262140, pricing: { text: { input: { - normal: 0.3, + normal: 0.29, cached: 0, }, output: { @@ -9804,12 +9693,12 @@ const QWEN_QWEN3_6_35B_A3B = { ], }, context_window: 262144, - max_output_tokens: 262144, + max_output_tokens: 262140, pricing: { text: { input: { - normal: 0.15, - cached: 0.05, + normal: 0.14, + cached: 0, }, output: { normal: 1, @@ -9840,11 +9729,11 @@ const QWEN_QWEN3_6_FLASH = { pricing: { text: { input: { - normal: 0.12375, - cached: 0.1545, + normal: 0.1875, + cached: 0.234375, }, output: { - normal: 0.7425, + normal: 1.125, }, }, image: 0, @@ -9906,11 +9795,11 @@ const QWEN_QWEN3_6_PLUS = { pricing: { text: { input: { - normal: 0.1794, - cached: 0.2236, + normal: 0.325, + cached: 0.40625, }, output: { - normal: 1.07315, + normal: 1.95, }, }, image: 0, @@ -9940,11 +9829,11 @@ const QWEN_QWEN3_7_MAX = { pricing: { text: { input: { - normal: 2.5, - cached: 3.125, + normal: 1.25, + cached: 1.8125, }, output: { - normal: 7.5, + normal: 3.75, }, }, image: 0, @@ -10266,6 +10155,39 @@ const STEPFUN_STEP_3_5_FLASH = { image: 0, }, } as const +const STEPFUN_STEP_3_7_FLASH = { + id: 'stepfun/step-3.7-flash', + name: 'StepFun: Step 3.7 Flash', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 256000, + max_output_tokens: 256000, + pricing: { + text: { + input: { + normal: 0.2, + cached: 0.04, + }, + output: { + normal: 1.15, + }, + }, + image: 0, + }, +} as const const SWITCHPOINT_ROUTER = { id: 'switchpoint/router', name: 'Switchpoint Router', @@ -10336,6 +10258,7 @@ const TENCENT_HY3_PREVIEW = { 'maxCompletionTokens', 'presencePenalty', 'reasoning', + 'seed', 'stop', 'temperature', 'toolChoice', @@ -10343,15 +10266,14 @@ const TENCENT_HY3_PREVIEW = { ], }, context_window: 262144, - max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.066, - cached: 0.029, + normal: 0.063, + cached: 0.021, }, output: { - normal: 0.26, + normal: 0.21, }, }, image: 0, @@ -10834,11 +10756,11 @@ const XIAOMI_MIMO_V2_5 = { pricing: { text: { input: { - normal: 0.4, - cached: 0.08, + normal: 0.14, + cached: 0.0028, }, output: { - normal: 2, + normal: 0.28, }, }, image: 0, @@ -10865,15 +10787,15 @@ const XIAOMI_MIMO_V2_5_PRO = { ], }, context_window: 1048576, - max_output_tokens: 16384, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 1, - cached: 0.2, + normal: 0.435, + cached: 0.0036, }, output: { - normal: 3, + normal: 0.87, }, }, image: 0, @@ -10946,6 +10868,7 @@ const Z_AI_GLM_4_5_AIR = { 'maxCompletionTokens', 'presencePenalty', 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', @@ -10954,12 +10877,12 @@ const Z_AI_GLM_4_5_AIR = { ], }, context_window: 131072, - max_output_tokens: 98304, + max_output_tokens: 131070, pricing: { text: { input: { - normal: 0.13, - cached: 0.025, + normal: 0.125, + cached: 0.06, }, output: { normal: 0.85, @@ -11442,21 +11365,6 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'reasoning' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [ALLENAI_OLMO_3_32B_THINK.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -11609,6 +11517,24 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'toolChoice' > + [ANTHROPIC_CLAUDE_OPUS_4_8.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > [ANTHROPIC_CLAUDE_SONNET_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -11690,15 +11616,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [ARCEE_AI_TRINITY_LARGE_THINKING_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'maxCompletionTokens' - | 'reasoning' - | 'temperature' - | 'toolChoice' - | 'topP' - > [ARCEE_AI_TRINITY_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -11723,8 +11640,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [BAIDU_COBUDDY_FREE.id]: OpenRouterCommonOptions & - Pick [BAIDU_ERNIE_4_5_21B_A3B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -11786,18 +11701,6 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [BAIDU_QIANFAN_OCR_FAST.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'reasoning' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > [BYTEDANCE_SEED_SEED_1_6.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -12079,20 +11982,6 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [DEEPSEEK_DEEPSEEK_V3_2_SPECIALE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'reasoning' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > [DEEPSEEK_DEEPSEEK_V4_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -12456,6 +12345,7 @@ export type OpenRouterModelOptionsByName = { | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -12676,7 +12566,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -12684,7 +12573,6 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT.id]: OpenRouterCommonOptions & @@ -13338,6 +13226,8 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [MOONSHOTAI_KIMI_K2_6_FREE.id]: OpenRouterCommonOptions & + Pick [MORPH_MORPH_V3_FAST.id]: OpenRouterCommonOptions & Pick [MORPH_MORPH_V3_LARGE.id]: OpenRouterCommonOptions & @@ -13781,22 +13671,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4O_AUDIO_PREVIEW.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [OPENAI_GPT_4O_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -14526,7 +14400,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -14534,7 +14407,6 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN3_235B_A22B_THINKING_2507.id]: OpenRouterCommonOptions & @@ -15182,6 +15054,19 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > + [STEPFUN_STEP_3_7_FLASH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'topLogprobs' + | 'topP' + > [SWITCHPOINT_ROUTER.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15209,6 +15094,7 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' @@ -15449,6 +15335,7 @@ export type OpenRouterModelOptionsByName = { | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' @@ -15625,7 +15512,6 @@ export type OpenRouterModelInputModalitiesByName = { [AION_LABS_AION_2_0.id]: ReadonlyArray<'text'> [AION_LABS_AION_RP_LLAMA_3_1_8B.id]: ReadonlyArray<'text'> [ALFREDPROS_CODELLAMA_7B_INSTRUCT_SOLIDITY.id]: ReadonlyArray<'text'> - [ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B.id]: ReadonlyArray<'text'> [ALLENAI_OLMO_3_32B_THINK.id]: ReadonlyArray<'text'> [AMAZON_NOVA_2_LITE_V1.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'document' @@ -15649,6 +15535,10 @@ export type OpenRouterModelInputModalitiesByName = { [ANTHROPIC_CLAUDE_OPUS_4_7_FAST.id]: ReadonlyArray< 'text' | 'image' | 'document' > + [ANTHROPIC_CLAUDE_OPUS_4_8.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_SONNET_4.id]: ReadonlyArray<'image' | 'text' | 'document'> [ANTHROPIC_CLAUDE_SONNET_4_5.id]: ReadonlyArray<'text' | 'image' | 'document'> [ANTHROPIC_CLAUDE_SONNET_4_6.id]: ReadonlyArray<'text' | 'image' | 'document'> @@ -15656,16 +15546,13 @@ export type OpenRouterModelInputModalitiesByName = { [ARCEE_AI_MAESTRO_REASONING.id]: ReadonlyArray<'text'> [ARCEE_AI_SPOTLIGHT.id]: ReadonlyArray<'image' | 'text'> [ARCEE_AI_TRINITY_LARGE_THINKING.id]: ReadonlyArray<'text'> - [ARCEE_AI_TRINITY_LARGE_THINKING_FREE.id]: ReadonlyArray<'text'> [ARCEE_AI_TRINITY_MINI.id]: ReadonlyArray<'text'> [ARCEE_AI_VIRTUOSO_LARGE.id]: ReadonlyArray<'text'> - [BAIDU_COBUDDY_FREE.id]: ReadonlyArray<'text'> [BAIDU_ERNIE_4_5_21B_A3B.id]: ReadonlyArray<'text'> [BAIDU_ERNIE_4_5_21B_A3B_THINKING.id]: ReadonlyArray<'text'> [BAIDU_ERNIE_4_5_300B_A47B.id]: ReadonlyArray<'text'> [BAIDU_ERNIE_4_5_VL_28B_A3B.id]: ReadonlyArray<'text' | 'image'> [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: ReadonlyArray<'image' | 'text'> - [BAIDU_QIANFAN_OCR_FAST.id]: ReadonlyArray<'image' | 'text'> [BYTEDANCE_SEED_SEED_1_6.id]: ReadonlyArray<'image' | 'text' | 'video'> [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: ReadonlyArray<'image' | 'text' | 'video'> [BYTEDANCE_SEED_SEED_2_0_LITE.id]: ReadonlyArray<'text' | 'image' | 'video'> @@ -15687,7 +15574,6 @@ export type OpenRouterModelInputModalitiesByName = { [DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V3_2.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V3_2_EXP.id]: ReadonlyArray<'text'> - [DEEPSEEK_DEEPSEEK_V3_2_SPECIALE.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_FLASH.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_FLASH_FREE.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_PRO.id]: ReadonlyArray<'text'> @@ -15826,6 +15712,7 @@ export type OpenRouterModelInputModalitiesByName = { [MOONSHOTAI_KIMI_K2_THINKING.id]: ReadonlyArray<'text'> [MOONSHOTAI_KIMI_K2_5.id]: ReadonlyArray<'text' | 'image'> [MOONSHOTAI_KIMI_K2_6.id]: ReadonlyArray<'text' | 'image'> + [MOONSHOTAI_KIMI_K2_6_FREE.id]: ReadonlyArray<'text' | 'image'> [MORPH_MORPH_V3_FAST.id]: ReadonlyArray<'text'> [MORPH_MORPH_V3_LARGE.id]: ReadonlyArray<'text'> [NEX_AGI_DEEPSEEK_V3_1_NEX_N1.id]: ReadonlyArray<'text'> @@ -15864,7 +15751,6 @@ export type OpenRouterModelInputModalitiesByName = { [OPENAI_GPT_4O_2024_05_13.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_4O_2024_08_06.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_4O_2024_11_20.id]: ReadonlyArray<'text' | 'image' | 'document'> - [OPENAI_GPT_4O_AUDIO_PREVIEW.id]: ReadonlyArray<'audio' | 'text'> [OPENAI_GPT_4O_MINI.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_4O_MINI_2024_07_18.id]: ReadonlyArray< 'text' | 'image' | 'document' @@ -15985,6 +15871,7 @@ export type OpenRouterModelInputModalitiesByName = { [SAO10K_L3_1_EURYALE_70B.id]: ReadonlyArray<'text'> [SAO10K_L3_3_EURYALE_70B.id]: ReadonlyArray<'text'> [STEPFUN_STEP_3_5_FLASH.id]: ReadonlyArray<'text'> + [STEPFUN_STEP_3_7_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> [SWITCHPOINT_ROUTER.id]: ReadonlyArray<'text'> [TENCENT_HUNYUAN_A13B_INSTRUCT.id]: ReadonlyArray<'text'> [TENCENT_HY3_PREVIEW.id]: ReadonlyArray<'text'> @@ -16037,7 +15924,6 @@ export const OPENROUTER_CHAT_MODELS = [ AION_LABS_AION_2_0.id, AION_LABS_AION_RP_LLAMA_3_1_8B.id, ALFREDPROS_CODELLAMA_7B_INSTRUCT_SOLIDITY.id, - ALIBABA_TONGYI_DEEPRESEARCH_30B_A3B.id, ALLENAI_OLMO_3_32B_THINK.id, AMAZON_NOVA_2_LITE_V1.id, AMAZON_NOVA_LITE_V1.id, @@ -16055,6 +15941,8 @@ export const OPENROUTER_CHAT_MODELS = [ ANTHROPIC_CLAUDE_OPUS_4_6_FAST.id, ANTHROPIC_CLAUDE_OPUS_4_7.id, ANTHROPIC_CLAUDE_OPUS_4_7_FAST.id, + ANTHROPIC_CLAUDE_OPUS_4_8.id, + ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id, ANTHROPIC_CLAUDE_SONNET_4.id, ANTHROPIC_CLAUDE_SONNET_4_5.id, ANTHROPIC_CLAUDE_SONNET_4_6.id, @@ -16062,16 +15950,13 @@ export const OPENROUTER_CHAT_MODELS = [ ARCEE_AI_MAESTRO_REASONING.id, ARCEE_AI_SPOTLIGHT.id, ARCEE_AI_TRINITY_LARGE_THINKING.id, - ARCEE_AI_TRINITY_LARGE_THINKING_FREE.id, ARCEE_AI_TRINITY_MINI.id, ARCEE_AI_VIRTUOSO_LARGE.id, - BAIDU_COBUDDY_FREE.id, BAIDU_ERNIE_4_5_21B_A3B.id, BAIDU_ERNIE_4_5_21B_A3B_THINKING.id, BAIDU_ERNIE_4_5_300B_A47B.id, BAIDU_ERNIE_4_5_VL_28B_A3B.id, BAIDU_ERNIE_4_5_VL_424B_A47B.id, - BAIDU_QIANFAN_OCR_FAST.id, BYTEDANCE_SEED_SEED_1_6.id, BYTEDANCE_SEED_SEED_1_6_FLASH.id, BYTEDANCE_SEED_SEED_2_0_LITE.id, @@ -16093,7 +15978,6 @@ export const OPENROUTER_CHAT_MODELS = [ DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id, DEEPSEEK_DEEPSEEK_V3_2.id, DEEPSEEK_DEEPSEEK_V3_2_EXP.id, - DEEPSEEK_DEEPSEEK_V3_2_SPECIALE.id, DEEPSEEK_DEEPSEEK_V4_FLASH.id, DEEPSEEK_DEEPSEEK_V4_FLASH_FREE.id, DEEPSEEK_DEEPSEEK_V4_PRO.id, @@ -16192,6 +16076,7 @@ export const OPENROUTER_CHAT_MODELS = [ MOONSHOTAI_KIMI_K2_THINKING.id, MOONSHOTAI_KIMI_K2_5.id, MOONSHOTAI_KIMI_K2_6.id, + MOONSHOTAI_KIMI_K2_6_FREE.id, MORPH_MORPH_V3_FAST.id, MORPH_MORPH_V3_LARGE.id, NEX_AGI_DEEPSEEK_V3_1_NEX_N1.id, @@ -16226,7 +16111,6 @@ export const OPENROUTER_CHAT_MODELS = [ OPENAI_GPT_4O_2024_05_13.id, OPENAI_GPT_4O_2024_08_06.id, OPENAI_GPT_4O_2024_11_20.id, - OPENAI_GPT_4O_AUDIO_PREVIEW.id, OPENAI_GPT_4O_MINI.id, OPENAI_GPT_4O_MINI_2024_07_18.id, OPENAI_GPT_4O_MINI_SEARCH_PREVIEW.id, @@ -16343,6 +16227,7 @@ export const OPENROUTER_CHAT_MODELS = [ SAO10K_L3_1_EURYALE_70B.id, SAO10K_L3_3_EURYALE_70B.id, STEPFUN_STEP_3_5_FLASH.id, + STEPFUN_STEP_3_7_FLASH.id, SWITCHPOINT_ROUTER.id, TENCENT_HUNYUAN_A13B_INSTRUCT.id, TENCENT_HY3_PREVIEW.id, diff --git a/scripts/.sync-models-last-run b/scripts/.sync-models-last-run index 1f83e39bc..682404739 100644 --- a/scripts/.sync-models-last-run +++ b/scripts/.sync-models-last-run @@ -1 +1 @@ -1779439521 +1780128752 diff --git a/scripts/openrouter.models.json b/scripts/openrouter.models.json index 9cd7a646e..e45f1c3fc 100644 --- a/scripts/openrouter.models.json +++ b/scripts/openrouter.models.json @@ -301,13 +301,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000073", - "completion": "0.00000349", - "input_cache_read": "0.00000025" + "prompt": "0.000000684", + "completion": "0.00000342", + "input_cache_read": "0.000000144" }, "top_provider": { - "context_length": 262142, - "max_completion_tokens": 262142, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -426,7 +426,7 @@ "top_provider": { "context_length": 400000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -701,63 +701,6 @@ "details": "/api/v1/models/alfredpros/codellama-7b-instruct-solidity/endpoints" } }, - { - "id": "alibaba/tongyi-deepresearch-30b-a3b", - "canonical_slug": "alibaba/tongyi-deepresearch-30b-a3b", - "hugging_face_id": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B", - "name": "Tongyi DeepResearch 30B A3B", - "created": 1758210804, - "description": "Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000009", - "completion": "0.00000045", - "input_cache_read": "0.00000009" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/alibaba/tongyi-deepresearch-30b-a3b/endpoints" - } - }, { "id": "allenai/olmo-3-32b-think", "canonical_slug": "allenai/olmo-3-32b-think-20251121", @@ -1502,7 +1445,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-06-29", "links": { "details": "/api/v1/models/anthropic/claude-4.6-opus-fast-20260407/endpoints" } @@ -1615,6 +1558,114 @@ "details": "/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints" } }, + { + "id": "anthropic/claude-opus-4.8", + "canonical_slug": "anthropic/claude-4.8-opus-20260528", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.8", + "created": 1779905091, + "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Claude", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000005", + "completion": "0.000025", + "web_search": "0.01", + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "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/anthropic/claude-4.8-opus-20260528/endpoints" + } + }, + { + "id": "anthropic/claude-opus-4.8-fast", + "canonical_slug": "anthropic/claude-4.8-opus-fast-20260528", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.8 (Fast)", + "created": 1779913703, + "description": "Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", + "context_length": 1000000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Claude", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00001", + "completion": "0.00005", + "web_search": "0.01", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "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/anthropic/claude-4.8-opus-fast-20260528/endpoints" + } + }, { "id": "anthropic/claude-sonnet-4", "canonical_slug": "anthropic/claude-4-sonnet-20250522", @@ -1977,56 +2028,6 @@ "details": "/api/v1/models/arcee-ai/trinity-large-thinking/endpoints" } }, - { - "id": "arcee-ai/trinity-large-thinking:free", - "canonical_slug": "arcee-ai/trinity-large-thinking", - "hugging_face_id": "arcee-ai/Trinity-Large-Thinking", - "name": "Arcee AI: Trinity Large Thinking (free)", - "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", - "completion": "0" - }, - "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" - } - }, { "id": "arcee-ai/trinity-mini", "canonical_slug": "arcee-ai/trinity-mini-20251201", @@ -2124,46 +2125,6 @@ "details": "/api/v1/models/arcee-ai/virtuoso-large/endpoints" } }, - { - "id": "baidu/cobuddy:free", - "canonical_slug": "baidu/cobuddy-20260430", - "hugging_face_id": null, - "name": "Baidu Qianfan: CoBuddy (free)", - "created": 1778035480, - "description": "CoBuddy is a code generation model from Baidu, optimized for coding tasks and AI Agent workflows. It features high inference throughput and low end-to-end latency, with native support for tool...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 65536, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "stop", - "tools" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/baidu/cobuddy-20260430/endpoints" - } - }, { "id": "baidu/ernie-4.5-21b-a3b", "canonical_slug": "baidu/ernie-4.5-21b-a3b", @@ -2403,58 +2364,6 @@ "details": "/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints" } }, - { - "id": "baidu/qianfan-ocr-fast", - "canonical_slug": "baidu/qianfan-ocr-fast-20260420", - "hugging_face_id": "", - "name": "Baidu: Qianfan-OCR-Fast", - "created": 1776707472, - "description": "Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.", - "context_length": 65536, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000068", - "completion": "0.00000281" - }, - "top_provider": { - "context_length": 65536, - "max_completion_tokens": 28672, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "seed", - "stop", - "temperature", - "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": "2026-05-28", - "links": { - "details": "/api/v1/models/baidu/qianfan-ocr-fast-20260420/endpoints" - } - }, { "id": "bytedance-seed/seed-1.6", "canonical_slug": "bytedance-seed/seed-1.6-20250625", @@ -2992,7 +2901,7 @@ "name": "DeepSeek: DeepSeek V3", "created": 1735241320, "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...", - "context_length": 163840, + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -3001,12 +2910,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000032", - "completion": "0.00000089" + "prompt": "0.0000002288", + "completion": "0.0000009144" }, "top_provider": { - "context_length": 163840, - "max_completion_tokens": 16384, + "context_length": 128000, + "max_completion_tokens": 16000, "is_moderated": false }, "per_request_limits": null, @@ -3525,61 +3434,6 @@ "details": "/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints" } }, - { - "id": "deepseek/deepseek-v3.2-speciale", - "canonical_slug": "deepseek/deepseek-v3.2-speciale-20251201", - "hugging_face_id": "deepseek-ai/DeepSeek-V3.2-Speciale", - "name": "DeepSeek: DeepSeek V3.2 Speciale", - "created": 1764594837, - "description": "DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...", - "context_length": 163840, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000000287", - "completion": "0.000000431", - "input_cache_read": "0.000000058" - }, - "top_provider": { - "context_length": 163840, - "max_completion_tokens": 163840, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/deepseek/deepseek-v3.2-speciale-20251201/endpoints" - } - }, { "id": "deepseek/deepseek-v4-flash", "canonical_slug": "deepseek/deepseek-v4-flash-20260423", @@ -3596,13 +3450,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000112", - "completion": "0.000000224", - "input_cache_read": "0.000000022" + "prompt": "0.0000000983", + "completion": "0.0000001966", + "input_cache_read": "0.0000000197" }, "top_provider": { - "context_length": 1048575, - "max_completion_tokens": null, + "context_length": 1048576, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -3810,7 +3664,7 @@ "name": "Google: Gemini 2.0 Flash", "created": 1738769413, "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It...", - "context_length": 1000000, + "context_length": 1048576, "architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": ["text", "image", "file", "audio", "video"], @@ -3829,7 +3683,7 @@ "input_cache_write": "0.00000008333333333333334" }, "top_provider": { - "context_length": 1000000, + "context_length": 1048576, "max_completion_tokens": 8192, "is_moderated": false }, @@ -3956,7 +3810,10 @@ "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": "2025-01-31", @@ -5190,6 +5047,7 @@ "reasoning", "response_format", "seed", + "stop", "temperature", "tool_choice", "tools", @@ -6180,7 +6038,6 @@ "supported_parameters": [ "frequency_penalty", "logit_bias", - "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -6193,7 +6050,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, @@ -8678,13 +8534,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000073", - "completion": "0.00000349", - "input_cache_read": "0.00000025" + "prompt": "0.000000684", + "completion": "0.00000342", + "input_cache_read": "0.000000144" }, "top_provider": { - "context_length": 262142, - "max_completion_tokens": 262142, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -8726,6 +8582,52 @@ "details": "/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints" } }, + { + "id": "moonshotai/kimi-k2.6:free", + "canonical_slug": "moonshotai/kimi-k2.6-20260420", + "hugging_face_id": "moonshotai/Kimi-K2.6", + "name": "MoonshotAI: Kimi K2.6 (free)", + "created": 1776699402, + "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...", + "context_length": 262144, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "reasoning", + "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": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints" + } + }, { "id": "morph/morph-v3-fast", "canonical_slug": "morph/morph-v3-fast", @@ -8891,7 +8793,7 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2023-12-31", - "expiration_date": null, + "expiration_date": "2026-06-05", "links": { "details": "/api/v1/models/nousresearch/hermes-2-pro-llama-3-8b/endpoints" } @@ -10382,60 +10284,6 @@ "details": "/api/v1/models/openai/gpt-4o-2024-11-20/endpoints" } }, - { - "id": "openai/gpt-4o-audio-preview", - "canonical_slug": "openai/gpt-4o-audio-preview", - "hugging_face_id": "", - "name": "OpenAI: GPT-4o Audio", - "created": 1755233061, - "description": "The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs...", - "context_length": 128000, - "architecture": { - "modality": "text+audio->text+audio", - "input_modalities": ["audio", "text"], - "output_modalities": ["text", "audio"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000025", - "completion": "0.00001", - "audio": "0.00004" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "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": { - "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/gpt-4o-audio-preview/endpoints" - } - }, { "id": "openai/gpt-4o-mini", "canonical_slug": "openai/gpt-4o-mini", @@ -11098,12 +10946,12 @@ "prompt": "0.00000125", "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.000000125" + "input_cache_read": "0.00000013" }, "top_provider": { "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": true + "max_completion_tokens": 32000, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -11146,12 +10994,12 @@ "prompt": "0.00000125", "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.000000125" + "input_cache_read": "0.00000013" }, "top_provider": { "context_length": 400000, "max_completion_tokens": 128000, - "is_moderated": true + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -11252,12 +11100,12 @@ "prompt": "0.00000025", "completion": "0.000002", "web_search": "0.01", - "input_cache_read": "0.00000003" + "input_cache_read": "0.000000025" }, "top_provider": { "context_length": 400000, - "max_completion_tokens": 128000, - "is_moderated": false + "max_completion_tokens": 100000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11310,7 +11158,7 @@ "top_provider": { "context_length": 400000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11362,8 +11210,8 @@ }, "top_provider": { "context_length": 128000, - "max_completion_tokens": 32000, - "is_moderated": false + "max_completion_tokens": 16384, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11382,7 +11230,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-08-10", "links": { "details": "/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints" } @@ -11411,7 +11259,7 @@ "top_provider": { "context_length": 400000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11613,7 +11461,7 @@ "top_provider": { "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11722,7 +11570,7 @@ "top_provider": { "context_length": 400000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11827,7 +11675,7 @@ "top_provider": { "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -12005,7 +11853,10 @@ "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, @@ -12245,12 +12096,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000003", + "prompt": "0.000000029", "completion": "0.00000014" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 131072, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, @@ -13213,7 +13064,7 @@ "name": "Poolside: Laguna M.1 (free)", "created": 1777388504, "description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 128K...", - "context_length": 131072, + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -13226,8 +13077,8 @@ "completion": "0" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 8192, + "context_length": 262144, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, @@ -13261,7 +13112,7 @@ "name": "Poolside: Laguna XS.2 (free)", "created": 1777389604, "description": "Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...", - "context_length": 131072, + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -13274,8 +13125,8 @@ "completion": "0" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 8192, + "context_length": 262144, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, @@ -13565,8 +13416,7 @@ }, "pricing": { "prompt": "0.00000026", - "completion": "0.00000078", - "input_cache_write": "0.000000325" + "completion": "0.00000078" }, "top_provider": { "context_length": 1000000, @@ -13822,7 +13672,6 @@ "supported_parameters": [ "frequency_penalty", "logit_bias", - "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -13835,7 +13684,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, @@ -13955,7 +13803,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-03-31", - "expiration_date": null, + "expiration_date": "2026-06-05", "links": { "details": "/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints" } @@ -15238,12 +15086,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000139", - "completion": "0.000001" + "prompt": "0.00000014", + "completion": "0.000001", + "input_cache_read": "0.00000005" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": null, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -15422,8 +15271,7 @@ }, "pricing": { "prompt": "0.000000065", - "completion": "0.00000026", - "input_cache_write": "0.00000008125" + "completion": "0.00000026" }, "top_provider": { "context_length": 1000000, @@ -15473,8 +15321,7 @@ }, "pricing": { "prompt": "0.00000026", - "completion": "0.00000156", - "input_cache_write": "0.000000325" + "completion": "0.00000156" }, "top_provider": { "context_length": 1000000, @@ -15524,7 +15371,8 @@ }, "pricing": { "prompt": "0.0000003", - "completion": "0.0000018" + "completion": "0.0000018", + "input_cache_write": "0.000000375" }, "top_provider": { "context_length": 1000000, @@ -15569,12 +15417,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003", + "prompt": "0.00000029", "completion": "0.0000032" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 262140, + "max_completion_tokens": 262140, "is_moderated": false }, "per_request_limits": null, @@ -15630,13 +15478,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.000001", - "input_cache_read": "0.00000005" + "prompt": "0.00000014", + "completion": "0.000001" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 262140, + "max_completion_tokens": 262140, "is_moderated": false }, "per_request_limits": null, @@ -15689,9 +15536,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000012375", - "completion": "0.0000007425", - "input_cache_write": "0.0000001545" + "prompt": "0.0000001875", + "completion": "0.000001125", + "input_cache_write": "0.000000234375" }, "top_provider": { "context_length": 1000000, @@ -15785,9 +15632,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001794", - "completion": "0.00000107315", - "input_cache_write": "0.0000002236" + "prompt": "0.000000325", + "completion": "0.00000195", + "input_cache_write": "0.00000040625" }, "top_provider": { "context_length": 1000000, @@ -15839,9 +15686,10 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.0000075", - "input_cache_write": "0.000003125" + "prompt": "0.00000125", + "completion": "0.00000375", + "input_cache_read": "0.00000025", + "input_cache_write": "0.0000015625" }, "top_provider": { "context_length": 1000000, @@ -16109,7 +15957,7 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2023-12-31", - "expiration_date": null, + "expiration_date": "2026-06-05", "links": { "details": "/api/v1/models/sao10k/l3-euryale-70b/endpoints" } @@ -16352,7 +16200,10 @@ "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, @@ -16361,6 +16212,61 @@ "details": "/api/v1/models/stepfun/step-3.5-flash/endpoints" } }, + { + "id": "stepfun/step-3.7-flash", + "canonical_slug": "stepfun/step-3.7-flash-20260528", + "hugging_face_id": null, + "name": "StepFun: Step 3.7 Flash", + "created": 1779985069, + "description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...", + "context_length": 256000, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.00000115", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 256000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints" + } + }, { "id": "switchpoint/router", "canonical_slug": "switchpoint/router", @@ -16464,13 +16370,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000066", - "completion": "0.00000026", - "input_cache_read": "0.000000029" + "prompt": "0.000000063", + "completion": "0.00000021", + "input_cache_read": "0.000000021" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 262144, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, @@ -16480,6 +16386,7 @@ "max_tokens", "presence_penalty", "reasoning", + "seed", "stop", "temperature", "tool_choice", @@ -17176,7 +17083,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-05-31", "links": { "details": "/api/v1/models/xiaomi/mimo-v2-omni-20260318/endpoints" } @@ -17230,7 +17137,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2026-05-31", "links": { "details": "/api/v1/models/xiaomi/mimo-v2-pro-20260318/endpoints" } @@ -17251,9 +17158,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.000002", - "input_cache_read": "0.00000008" + "prompt": "0.00000014", + "completion": "0.00000028", + "input_cache_read": "0.0000000028" }, "top_provider": { "context_length": 1048576, @@ -17305,13 +17212,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000003", - "input_cache_read": "0.0000002" + "prompt": "0.000000435", + "completion": "0.00000087", + "input_cache_read": "0.0000000036" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 16384, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -17463,13 +17370,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000013", + "prompt": "0.000000125", "completion": "0.00000085", - "input_cache_read": "0.000000025" + "input_cache_read": "0.00000006" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 98304, + "context_length": 131070, + "max_completion_tokens": 131070, "is_moderated": false }, "per_request_limits": null, @@ -17480,6 +17387,7 @@ "presence_penalty", "reasoning", "repetition_penalty", + "response_format", "seed", "stop", "temperature",