From 9ffaf4028778ebdbdfa813cfdfac8cd12fe858ff Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 5 Jun 2026 09:00:21 +0000 Subject: [PATCH] chore: sync model metadata from OpenRouter --- packages/ai-openrouter/src/model-meta.ts | 240 +++++++++++++++----- scripts/.sync-models-last-run | 2 +- scripts/openrouter.models.json | 269 ++++++++++++++++++----- 3 files changed, 398 insertions(+), 113 deletions(-) diff --git a/packages/ai-openrouter/src/model-meta.ts b/packages/ai-openrouter/src/model-meta.ts index 42122cd2c..90001d7b3 100644 --- a/packages/ai-openrouter/src/model-meta.ts +++ b/packages/ai-openrouter/src/model-meta.ts @@ -3478,7 +3478,7 @@ const META_LLAMA_LLAMA_3_1_8B_INSTRUCT = { cached: 0, }, output: { - normal: 0.05, + normal: 0.03, }, }, image: 0, @@ -5437,6 +5437,100 @@ const NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE = { image: 0, }, } as const +const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B = { + id: 'nvidia/nemotron-3-ultra-550b-a55b', + name: 'NVIDIA: Nemotron 3 Ultra', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.5, + cached: 0.15, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const +const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE = { + id: 'nvidia/nemotron-3-ultra-550b-a55b:free', + name: 'NVIDIA: Nemotron 3 Ultra (free)', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'seed', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const +const NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE = { + id: 'nvidia/nemotron-3.5-content-safety:free', + name: 'NVIDIA: Nemotron 3.5 Content Safety (free)', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'seed', + 'temperature', + 'topP', + ], + }, + context_window: 128000, + max_output_tokens: 8192, + pricing: { + text: { + input: { + normal: 0, + cached: 0, + }, + output: { + normal: 0, + }, + }, + image: 0, + }, +} as const const NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE = { id: 'nvidia/nemotron-nano-12b-v2-vl:free', name: 'NVIDIA: Nemotron Nano 12B 2 VL (free)', @@ -5713,42 +5807,6 @@ const OPENAI_GPT_4 = { image: 0, }, } as const -const OPENAI_GPT_4_0314 = { - id: 'openai/gpt-4-0314', - name: 'OpenAI: GPT-4 (older v0314)', - supports: { - input: ['text'], - output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - '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, - }, - }, - image: 0, - }, -} as const const OPENAI_GPT_4_1106_PREVIEW = { id: 'openai/gpt-4-1106-preview', name: 'OpenAI: GPT-4 Turbo (older v1106)', @@ -8275,11 +8333,11 @@ const QWEN_QWEN3_30B_A3B_INSTRUCT_2507 = { pricing: { text: { input: { - normal: 0.0428, + normal: 0.04815, cached: 0, }, output: { - normal: 0.1716, + normal: 0.19305, }, }, image: 0, @@ -9467,6 +9525,40 @@ const QWEN_QWEN3_7_MAX = { image: 0, }, } as const +const QWEN_QWEN3_7_PLUS = { + id: 'qwen/qwen3.7-plus', + name: 'Qwen: Qwen3.7 Plus', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.4, + cached: 0.58, + }, + output: { + normal: 1.6, + }, + }, + image: 0, + }, +} as const const REKAAI_REKA_EDGE = { id: 'rekaai/reka-edge', name: 'Reka Edge', @@ -12818,6 +12910,36 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'seed' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'reasoning' | 'seed' | 'temperature' | 'topP' + > [NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -12935,22 +13057,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4_0314.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topLogprobs' - | 'topP' - > [OPENAI_GPT_4_1106_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -14364,6 +14470,20 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [QWEN_QWEN3_7_PLUS.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > [REKAAI_REKA_EDGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15112,6 +15232,9 @@ export type OpenRouterModelInputModalitiesByName = { > [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_FREE.id]: ReadonlyArray<'text' | 'image'> [NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id]: ReadonlyArray< 'image' | 'text' | 'video' > @@ -15122,7 +15245,6 @@ export type OpenRouterModelInputModalitiesByName = { [OPENAI_GPT_3_5_TURBO_16K.id]: ReadonlyArray<'text'> [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: ReadonlyArray<'text'> [OPENAI_GPT_4.id]: ReadonlyArray<'text'> - [OPENAI_GPT_4_0314.id]: ReadonlyArray<'text'> [OPENAI_GPT_4_1106_PREVIEW.id]: ReadonlyArray<'text'> [OPENAI_GPT_4_TURBO.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_4_TURBO_PREVIEW.id]: ReadonlyArray<'text'> @@ -15243,6 +15365,7 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN3_6_MAX_PREVIEW.id]: ReadonlyArray<'text'> [QWEN_QWEN3_6_PLUS.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_7_MAX.id]: ReadonlyArray<'text'> + [QWEN_QWEN3_7_PLUS.id]: ReadonlyArray<'text' | 'image'> [REKAAI_REKA_EDGE.id]: ReadonlyArray<'image' | 'text' | 'video'> [REKAAI_REKA_FLASH_3.id]: ReadonlyArray<'text'> [RELACE_RELACE_APPLY_3.id]: ReadonlyArray<'text'> @@ -15460,6 +15583,9 @@ export const OPENROUTER_CHAT_MODELS = [ 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_FREE.id, NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id, NVIDIA_NEMOTRON_NANO_9B_V2.id, NVIDIA_NEMOTRON_NANO_9B_V2_FREE.id, @@ -15468,7 +15594,6 @@ export const OPENROUTER_CHAT_MODELS = [ OPENAI_GPT_3_5_TURBO_16K.id, OPENAI_GPT_3_5_TURBO_INSTRUCT.id, OPENAI_GPT_4.id, - OPENAI_GPT_4_0314.id, OPENAI_GPT_4_1106_PREVIEW.id, OPENAI_GPT_4_TURBO.id, OPENAI_GPT_4_TURBO_PREVIEW.id, @@ -15585,6 +15710,7 @@ export const OPENROUTER_CHAT_MODELS = [ QWEN_QWEN3_6_MAX_PREVIEW.id, QWEN_QWEN3_6_PLUS.id, QWEN_QWEN3_7_MAX.id, + QWEN_QWEN3_7_PLUS.id, REKAAI_REKA_EDGE.id, REKAAI_REKA_FLASH_3.id, RELACE_RELACE_APPLY_3.id, diff --git a/scripts/.sync-models-last-run b/scripts/.sync-models-last-run index be7a0996a..11b0146e5 100644 --- a/scripts/.sync-models-last-run +++ b/scripts/.sync-models-last-run @@ -1 +1 @@ -1780482493 +1780650007 diff --git a/scripts/openrouter.models.json b/scripts/openrouter.models.json index bcc2eeacd..f4d1a2863 100644 --- a/scripts/openrouter.models.json +++ b/scripts/openrouter.models.json @@ -3016,7 +3016,7 @@ "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2024-07-31", - "expiration_date": null, + "expiration_date": "2026-06-11", "links": { "details": "/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints" } @@ -5683,10 +5683,10 @@ }, "pricing": { "prompt": "0.00000002", - "completion": "0.00000005" + "completion": "0.00000003" }, "top_provider": { - "context_length": 16384, + "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false }, @@ -8763,6 +8763,164 @@ "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" } }, + { + "id": "nvidia/nemotron-3-ultra-550b-a55b", + "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "name": "NVIDIA: Nemotron 3 Ultra", + "created": 1780551208, + "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", + "context_length": 1000000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000005", + "completion": "0.0000025", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "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-ultra-550b-a55b-20260604/endpoints" + } + }, + { + "id": "nvidia/nemotron-3-ultra-550b-a55b:free", + "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "name": "NVIDIA: Nemotron 3 Ultra (free)", + "created": 1780551208, + "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", + "context_length": 1000000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "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-ultra-550b-a55b-20260604/endpoints" + } + }, + { + "id": "nvidia/nemotron-3.5-content-safety:free", + "canonical_slug": "nvidia/nemotron-3.5-content-safety-20260604", + "hugging_face_id": "nvidia/Nemotron-3.5-Content-Safety", + "name": "NVIDIA: Nemotron 3.5 Content Safety (free)", + "created": 1780581864, + "description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...", + "context_length": 128000, + "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": 128000, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "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": null, + "links": { + "details": "/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints" + } + }, { "id": "nvidia/nemotron-nano-12b-v2-vl:free", "canonical_slug": "nvidia/nemotron-nano-12b-v2-vl", @@ -8860,7 +9018,7 @@ }, "supported_voices": null, "knowledge_cutoff": "2025-03-31", - "expiration_date": null, + "expiration_date": "2026-06-11", "links": { "details": "/api/v1/models/nvidia/nemotron-nano-9b-v2/endpoints" } @@ -9159,55 +9317,6 @@ "details": "/api/v1/models/openai/gpt-4/endpoints" } }, - { - "id": "openai/gpt-4-0314", - "canonical_slug": "openai/gpt-4-0314", - "hugging_face_id": null, - "name": "OpenAI: GPT-4 (older v0314)", - "created": 1685232000, - "description": "GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.", - "context_length": 8191, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00003", - "completion": "0.00006" - }, - "top_provider": { - "context_length": 8191, - "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-4-0314/endpoints" - } - }, { "id": "openai/gpt-4-1106-preview", "canonical_slug": "openai/gpt-4-1106-preview", @@ -13237,8 +13346,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000000428", - "completion": "0.0000001716" + "prompt": "0.00000004815", + "completion": "0.00000019305" }, "top_provider": { "context_length": 128000, @@ -15140,6 +15249,56 @@ "details": "/api/v1/models/qwen/qwen3.7-max-20260520/endpoints" } }, + { + "id": "qwen/qwen3.7-plus", + "canonical_slug": "qwen/qwen3.7-plus-20260602", + "hugging_face_id": null, + "name": "Qwen: Qwen3.7 Plus", + "created": 1780491783, + "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...", + "context_length": 1000000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Qwen", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000004", + "completion": "0.0000016", + "input_cache_read": "0.00000008", + "input_cache_write": "0.0000005" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "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/qwen/qwen3.7-plus-20260602/endpoints" + } + }, { "id": "rekaai/reka-edge", "canonical_slug": "rekaai/reka-edge-2603",