From 9b794558c627cebc39db29016bfc639f194172d2 Mon Sep 17 00:00:00 2001 From: Mario Zechner Date: Sat, 14 Mar 2026 03:10:59 +0100 Subject: [PATCH] chore(ai): refresh generated models --- packages/ai/src/models.generated.ts | 920 +++++++++++++++++----------- 1 file changed, 562 insertions(+), 358 deletions(-) diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts index 25b23218..85d2fec7 100644 --- a/packages/ai/src/models.generated.ts +++ b/packages/ai/src/models.generated.ts @@ -90,40 +90,6 @@ export const MODELS = { contextWindow: 300000, maxTokens: 8192, } satisfies Model<"bedrock-converse-stream">, - "amazon.titan-text-express-v1": { - id: "amazon.titan-text-express-v1", - name: "Titan Text G1 - Express", - api: "bedrock-converse-stream", - provider: "amazon-bedrock", - baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", - reasoning: false, - input: ["text"], - cost: { - input: 0.2, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 128000, - maxTokens: 4096, - } satisfies Model<"bedrock-converse-stream">, - "amazon.titan-text-express-v1:0:8k": { - id: "amazon.titan-text-express-v1:0:8k", - name: "Titan Text G1 - Express", - api: "bedrock-converse-stream", - provider: "amazon-bedrock", - baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", - reasoning: false, - input: ["text"], - cost: { - input: 0.2, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 128000, - maxTokens: 4096, - } satisfies Model<"bedrock-converse-stream">, "anthropic.claude-3-5-haiku-20241022-v1:0": { id: "anthropic.claude-3-5-haiku-20241022-v1:0", name: "Claude Haiku 3.5", @@ -209,40 +175,6 @@ export const MODELS = { contextWindow: 200000, maxTokens: 4096, } satisfies Model<"bedrock-converse-stream">, - "anthropic.claude-3-opus-20240229-v1:0": { - id: "anthropic.claude-3-opus-20240229-v1:0", - name: "Claude Opus 3", - api: "bedrock-converse-stream", - provider: "amazon-bedrock", - baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", - reasoning: false, - input: ["text", "image"], - cost: { - input: 15, - output: 75, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 200000, - maxTokens: 4096, - } satisfies Model<"bedrock-converse-stream">, - "anthropic.claude-3-sonnet-20240229-v1:0": { - id: "anthropic.claude-3-sonnet-20240229-v1:0", - name: "Claude Sonnet 3", - api: "bedrock-converse-stream", - provider: "amazon-bedrock", - baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", - reasoning: false, - input: ["text", "image"], - cost: { - input: 3, - output: 15, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 200000, - maxTokens: 4096, - } satisfies Model<"bedrock-converse-stream">, "anthropic.claude-haiku-4-5-20251001-v1:0": { id: "anthropic.claude-haiku-4-5-20251001-v1:0", name: "Claude Haiku 4.5", @@ -379,40 +311,6 @@ export const MODELS = { contextWindow: 200000, maxTokens: 64000, } satisfies Model<"bedrock-converse-stream">, - "cohere.command-r-plus-v1:0": { - id: "cohere.command-r-plus-v1:0", - name: "Command R+", - api: "bedrock-converse-stream", - provider: "amazon-bedrock", - baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", - reasoning: false, - input: ["text"], - cost: { - input: 3, - output: 15, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 128000, - maxTokens: 4096, - } satisfies Model<"bedrock-converse-stream">, - "cohere.command-r-v1:0": { - id: "cohere.command-r-v1:0", - name: "Command R", - api: "bedrock-converse-stream", - provider: "amazon-bedrock", - baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", - reasoning: false, - input: ["text"], - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 128000, - maxTokens: 4096, - } satisfies Model<"bedrock-converse-stream">, "deepseek.r1-v1:0": { id: "deepseek.r1-v1:0", name: "DeepSeek-R1", @@ -447,8 +345,8 @@ export const MODELS = { contextWindow: 163840, maxTokens: 81920, } satisfies Model<"bedrock-converse-stream">, - "deepseek.v3.2-v1:0": { - id: "deepseek.v3.2-v1:0", + "deepseek.v3.2": { + id: "deepseek.v3.2", name: "DeepSeek-V3.2", api: "bedrock-converse-stream", provider: "amazon-bedrock", @@ -702,6 +600,23 @@ export const MODELS = { contextWindow: 128000, maxTokens: 4096, } satisfies Model<"bedrock-converse-stream">, + "meta.llama3-1-405b-instruct-v1:0": { + id: "meta.llama3-1-405b-instruct-v1:0", + name: "Llama 3.1 405B Instruct", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: false, + input: ["text"], + cost: { + input: 2.4, + output: 2.4, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 4096, + } satisfies Model<"bedrock-converse-stream">, "meta.llama3-1-70b-instruct-v1:0": { id: "meta.llama3-1-70b-instruct-v1:0", name: "Llama 3.1 70B Instruct", @@ -889,6 +804,40 @@ export const MODELS = { contextWindow: 204800, maxTokens: 131072, } satisfies Model<"bedrock-converse-stream">, + "mistral.devstral-2-123b": { + id: "mistral.devstral-2-123b", + name: "Devstral 2 123B", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: false, + input: ["text"], + cost: { + input: 0.4, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 8192, + } satisfies Model<"bedrock-converse-stream">, + "mistral.magistral-small-2509": { + id: "mistral.magistral-small-2509", + name: "Magistral Small 1.2", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 40000, + } satisfies Model<"bedrock-converse-stream">, "mistral.ministral-3-14b-instruct": { id: "mistral.ministral-3-14b-instruct", name: "Ministral 14B 3.0", @@ -906,6 +855,23 @@ export const MODELS = { contextWindow: 128000, maxTokens: 4096, } satisfies Model<"bedrock-converse-stream">, + "mistral.ministral-3-3b-instruct": { + id: "mistral.ministral-3-3b-instruct", + name: "Ministral 3 3B", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.1, + output: 0.1, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 8192, + } satisfies Model<"bedrock-converse-stream">, "mistral.ministral-3-8b-instruct": { id: "mistral.ministral-3-8b-instruct", name: "Ministral 3 8B", @@ -923,22 +889,39 @@ export const MODELS = { contextWindow: 128000, maxTokens: 4096, } satisfies Model<"bedrock-converse-stream">, - "mistral.mistral-large-2402-v1:0": { - id: "mistral.mistral-large-2402-v1:0", - name: "Mistral Large (24.02)", + "mistral.mistral-large-3-675b-instruct": { + id: "mistral.mistral-large-3-675b-instruct", + name: "Mistral Large 3", api: "bedrock-converse-stream", provider: "amazon-bedrock", baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", reasoning: false, - input: ["text"], + input: ["text", "image"], cost: { input: 0.5, output: 1.5, cacheRead: 0, cacheWrite: 0, }, + contextWindow: 256000, + maxTokens: 8192, + } satisfies Model<"bedrock-converse-stream">, + "mistral.pixtral-large-2502-v1:0": { + id: "mistral.pixtral-large-2502-v1:0", + name: "Pixtral Large (25.02)", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: false, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0, + cacheWrite: 0, + }, contextWindow: 128000, - maxTokens: 4096, + maxTokens: 8192, } satisfies Model<"bedrock-converse-stream">, "mistral.voxtral-mini-3b-2507": { id: "mistral.voxtral-mini-3b-2507", @@ -1025,6 +1008,23 @@ export const MODELS = { contextWindow: 128000, maxTokens: 4096, } satisfies Model<"bedrock-converse-stream">, + "nvidia.nemotron-nano-3-30b": { + id: "nvidia.nemotron-nano-3-30b", + name: "NVIDIA Nemotron Nano 3 30B", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: true, + input: ["text"], + cost: { + input: 0.06, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 4096, + } satisfies Model<"bedrock-converse-stream">, "nvidia.nemotron-nano-9b-v2": { id: "nvidia.nemotron-nano-9b-v2", name: "NVIDIA Nemotron Nano 9B v2", @@ -1806,7 +1806,7 @@ export const MODELS = { cacheRead: 0.3, cacheWrite: 3.75, }, - contextWindow: 200000, + contextWindow: 1000000, maxTokens: 64000, } satisfies Model<"anthropic-messages">, }, @@ -2874,7 +2874,7 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 128000, + contextWindow: 264000, maxTokens: 64000, } satisfies Model<"openai-responses">, "gpt-5.2-codex": { @@ -2892,7 +2892,7 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 272000, + contextWindow: 400000, maxTokens: 128000, } satisfies Model<"openai-responses">, "gpt-5.3-codex": { @@ -3250,10 +3250,10 @@ export const MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0, + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 1, }, contextWindow: 1048576, maxTokens: 65536, @@ -6275,6 +6275,23 @@ export const MODELS = { contextWindow: 262144, maxTokens: 65536, } satisfies Model<"openai-completions">, + "mimo-v2-flash-free": { + id: "mimo-v2-flash-free", + name: "MiMo V2 Flash Free", + api: "openai-completions", + provider: "opencode", + baseUrl: "https://opencode.ai/zen/v1", + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 65536, + } satisfies Model<"openai-completions">, "minimax-m2.1": { id: "minimax-m2.1", name: "MiniMax M2.1", @@ -6326,6 +6343,23 @@ export const MODELS = { contextWindow: 204800, maxTokens: 131072, } satisfies Model<"anthropic-messages">, + "nemotron-3-super-free": { + id: "nemotron-3-super-free", + name: "Nemotron 3 Super Free", + api: "openai-completions", + provider: "opencode", + baseUrl: "https://opencode.ai/zen/v1", + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 128000, + } satisfies Model<"openai-completions">, }, "opencode-go": { "glm-5": { @@ -6891,6 +6925,23 @@ export const MODELS = { contextWindow: 262144, maxTokens: 32768, } satisfies Model<"openai-completions">, + "bytedance-seed/seed-2.0-lite": { + id: "bytedance-seed/seed-2.0-lite", + name: "ByteDance Seed: Seed-2.0-Lite", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.25, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 131072, + } satisfies Model<"openai-completions">, "bytedance-seed/seed-2.0-mini": { id: "bytedance-seed/seed-2.0-mini", name: "ByteDance Seed: Seed-2.0-Mini", @@ -6970,11 +7021,11 @@ export const MODELS = { cost: { input: 0.19999999999999998, output: 0.77, - cacheRead: 0.13, + cacheRead: 0.135, cacheWrite: 0, }, contextWindow: 163840, - maxTokens: 163840, + maxTokens: 4096, } satisfies Model<"openai-completions">, "deepseek/deepseek-chat-v3.1": { id: "deepseek/deepseek-chat-v3.1", @@ -7044,23 +7095,6 @@ export const MODELS = { contextWindow: 163840, maxTokens: 4096, } satisfies Model<"openai-completions">, - "deepseek/deepseek-v3.1-terminus:exacto": { - id: "deepseek/deepseek-v3.1-terminus:exacto", - name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - reasoning: true, - input: ["text"], - cost: { - input: 0.21, - output: 0.7899999999999999, - cacheRead: 0.16799999999999998, - cacheWrite: 0, - }, - contextWindow: 163840, - maxTokens: 4096, - } satisfies Model<"openai-completions">, "deepseek/deepseek-v3.2": { id: "deepseek/deepseek-v3.2", name: "DeepSeek: DeepSeek V3.2", @@ -7070,13 +7104,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.25, - output: 0.39999999999999997, - cacheRead: 0, + input: 0.26, + output: 0.38, + cacheRead: 0.13, cacheWrite: 0, }, contextWindow: 163840, - maxTokens: 65536, + maxTokens: 4096, } satisfies Model<"openai-completions">, "deepseek/deepseek-v3.2-exp": { id: "deepseek/deepseek-v3.2-exp", @@ -7342,9 +7376,9 @@ export const MODELS = { reasoning: false, input: ["text", "image"], cost: { - input: 0.04, - output: 0.15, - cacheRead: 0.02, + input: 0.03, + output: 0.11, + cacheRead: 0.015, cacheWrite: 0, }, contextWindow: 128000, @@ -7469,23 +7503,6 @@ export const MODELS = { contextWindow: 8192, maxTokens: 16384, } satisfies Model<"openai-completions">, - "meta-llama/llama-3.1-405b-instruct": { - id: "meta-llama/llama-3.1-405b-instruct", - name: "Meta: Llama 3.1 405B Instruct", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - reasoning: false, - input: ["text"], - cost: { - input: 4, - output: 4, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131000, - maxTokens: 4096, - } satisfies Model<"openai-completions">, "meta-llama/llama-3.1-70b-instruct": { id: "meta-llama/llama-3.1-70b-instruct", name: "Meta: Llama 3.1 70B Instruct", @@ -7648,13 +7665,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.295, - output: 1.2, - cacheRead: 0.03, + input: 0.27, + output: 0.95, + cacheRead: 0.0299999997, cacheWrite: 0, }, contextWindow: 196608, - maxTokens: 196608, + maxTokens: 4096, } satisfies Model<"openai-completions">, "mistralai/codestral-2508": { id: "mistralai/codestral-2508", @@ -8081,23 +8098,6 @@ export const MODELS = { contextWindow: 131072, maxTokens: 4096, } satisfies Model<"openai-completions">, - "moonshotai/kimi-k2-0905:exacto": { - id: "moonshotai/kimi-k2-0905:exacto", - name: "MoonshotAI: Kimi K2 0905 (exacto)", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - reasoning: false, - input: ["text"], - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 262144, - maxTokens: 4096, - } satisfies Model<"openai-completions">, "moonshotai/kimi-k2-thinking": { id: "moonshotai/kimi-k2-thinking", name: "MoonshotAI: Kimi K2 Thinking", @@ -8217,6 +8217,23 @@ export const MODELS = { contextWindow: 256000, maxTokens: 4096, } satisfies Model<"openai-completions">, + "nvidia/nemotron-3-super-120b-a12b:free": { + id: "nvidia/nemotron-3-super-120b-a12b:free", + name: "NVIDIA: Nemotron 3 Super (free)", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 262144, + } satisfies Model<"openai-completions">, "nvidia/nemotron-nano-12b-v2-vl:free": { id: "nvidia/nemotron-nano-12b-v2-vl:free", name: "NVIDIA: Nemotron Nano 12B 2 VL (free)", @@ -8948,23 +8965,6 @@ export const MODELS = { contextWindow: 131072, maxTokens: 4096, } satisfies Model<"openai-completions">, - "openai/gpt-oss-120b:exacto": { - id: "openai/gpt-oss-120b:exacto", - name: "OpenAI: gpt-oss-120b (exacto)", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - reasoning: true, - input: ["text"], - cost: { - input: 0.039, - output: 0.19, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131072, - maxTokens: 4096, - } satisfies Model<"openai-completions">, "openai/gpt-oss-120b:free": { id: "openai/gpt-oss-120b:free", name: "OpenAI: gpt-oss-120b (free)", @@ -9220,6 +9220,40 @@ export const MODELS = { contextWindow: 200000, maxTokens: 4096, } satisfies Model<"openai-completions">, + "openrouter/healer-alpha": { + id: "openrouter/healer-alpha", + name: "Healer Alpha", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 32000, + } satisfies Model<"openai-completions">, + "openrouter/hunter-alpha": { + id: "openrouter/hunter-alpha", + name: "Hunter Alpha", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1048576, + maxTokens: 32000, + } satisfies Model<"openai-completions">, "prime-intellect/intellect-3": { id: "prime-intellect/intellect-3", name: "Prime Intellect: INTELLECT-3", @@ -9628,23 +9662,6 @@ export const MODELS = { contextWindow: 1000000, maxTokens: 65536, } satisfies Model<"openai-completions">, - "qwen/qwen3-coder:exacto": { - id: "qwen/qwen3-coder:exacto", - name: "Qwen: Qwen3 Coder 480B A35B (exacto)", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - reasoning: false, - input: ["text"], - cost: { - input: 0.22, - output: 1.7999999999999998, - cacheRead: 0.022, - cacheWrite: 0, - }, - contextWindow: 262144, - maxTokens: 65536, - } satisfies Model<"openai-completions">, "qwen/qwen3-coder:free": { id: "qwen/qwen3-coder:free", name: "Qwen: Qwen3 Coder 480B A35B (free)", @@ -9710,7 +9727,7 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 262144, + contextWindow: 131072, maxTokens: 4096, } satisfies Model<"openai-completions">, "qwen/qwen3-next-80b-a3b-instruct:free": { @@ -9739,13 +9756,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.15, - output: 1.2, + input: 0.0975, + output: 0.78, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 128000, - maxTokens: 4096, + contextWindow: 131072, + maxTokens: 32768, } satisfies Model<"openai-completions">, "qwen/qwen3-vl-235b-a22b-instruct": { id: "qwen/qwen3-vl-235b-a22b-instruct", @@ -9773,8 +9790,8 @@ export const MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0, - output: 0, + input: 0.26, + output: 2.6, cacheRead: 0, cacheWrite: 0, }, @@ -9807,8 +9824,8 @@ export const MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0, - output: 0, + input: 0.13, + output: 1.56, cacheRead: 0, cacheWrite: 0, }, @@ -9934,6 +9951,23 @@ export const MODELS = { contextWindow: 262144, maxTokens: 65536, } satisfies Model<"openai-completions">, + "qwen/qwen3.5-9b": { + id: "qwen/qwen3.5-9b", + name: "Qwen: Qwen3.5-9B", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.049999999999999996, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 4096, + } satisfies Model<"openai-completions">, "qwen/qwen3.5-flash-02-23": { id: "qwen/qwen3.5-flash-02-23", name: "Qwen: Qwen3.5-Flash", @@ -10028,13 +10062,13 @@ export const MODELS = { reasoning: false, input: ["text"], cost: { - input: 0.65, - output: 0.75, + input: 0.85, + output: 0.85, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 32768, - maxTokens: 32768, + contextWindow: 131072, + maxTokens: 16384, } satisfies Model<"openai-completions">, "stepfun/step-3.5-flash": { id: "stepfun/step-3.5-flash", @@ -10257,6 +10291,23 @@ export const MODELS = { contextWindow: 2000000, maxTokens: 30000, } satisfies Model<"openai-completions">, + "x-ai/grok-4.20-beta": { + id: "x-ai/grok-4.20-beta", + name: "xAI: Grok 4.20 Beta", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + reasoning: true, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0.19999999999999998, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 4096, + } satisfies Model<"openai-completions">, "x-ai/grok-code-fast-1": { id: "x-ai/grok-code-fast-1", name: "xAI: Grok Code Fast 1", @@ -10393,23 +10444,6 @@ export const MODELS = { contextWindow: 204800, maxTokens: 204800, } satisfies Model<"openai-completions">, - "z-ai/glm-4.6:exacto": { - id: "z-ai/glm-4.6:exacto", - name: "Z.ai: GLM 4.6 (exacto)", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - reasoning: true, - input: ["text"], - cost: { - input: 0.44, - output: 1.76, - cacheRead: 0.11, - cacheWrite: 0, - }, - contextWindow: 204800, - maxTokens: 131072, - } satisfies Model<"openai-completions">, "z-ai/glm-4.6v": { id: "z-ai/glm-4.6v", name: "Z.ai: GLM 4.6V", @@ -10476,7 +10510,7 @@ export const MODELS = { cacheWrite: 0, }, contextWindow: 202752, - maxTokens: 4096, + maxTokens: 131072, } satisfies Model<"openai-completions">, }, "vercel-ai-gateway": { @@ -10540,13 +10574,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.09999999999999999, - output: 0.3, + input: 0.29, + output: 0.59, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 40960, - maxTokens: 16384, + contextWindow: 131072, + maxTokens: 40960, } satisfies Model<"anthropic-messages">, "alibaba/qwen3-235b-a22b-thinking": { id: "alibaba/qwen3-235b-a22b-thinking", @@ -10591,13 +10625,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.07, - output: 0.27, + input: 0.15, + output: 0.6, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 160000, - maxTokens: 32768, + contextWindow: 262144, + maxTokens: 8192, } satisfies Model<"anthropic-messages">, "alibaba/qwen3-coder-next": { id: "alibaba/qwen3-coder-next", @@ -10605,7 +10639,7 @@ export const MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text"], cost: { input: 0.5, @@ -10633,6 +10667,23 @@ export const MODELS = { contextWindow: 1000000, maxTokens: 65536, } satisfies Model<"anthropic-messages">, + "alibaba/qwen3-max": { + id: "alibaba/qwen3-max", + name: "Qwen3 Max", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text"], + cost: { + input: 1.2, + output: 6, + cacheRead: 0.24, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 32768, + } satisfies Model<"anthropic-messages">, "alibaba/qwen3-max-preview": { id: "alibaba/qwen3-max-preview", name: "Qwen3 Max Preview", @@ -10780,8 +10831,8 @@ export const MODELS = { cost: { input: 3, output: 15, - cacheRead: 0, - cacheWrite: 0, + cacheRead: 0.3, + cacheWrite: 3.75, }, contextWindow: 200000, maxTokens: 8192, @@ -10990,6 +11041,23 @@ export const MODELS = { contextWindow: 256000, maxTokens: 8000, } satisfies Model<"anthropic-messages">, + "deepseek/deepseek-r1": { + id: "deepseek/deepseek-r1", + name: "DeepSeek-R1", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text"], + cost: { + input: 1.35, + output: 5.4, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 8192, + } satisfies Model<"anthropic-messages">, "deepseek/deepseek-v3": { id: "deepseek/deepseek-v3", name: "DeepSeek V3 0324", @@ -11016,13 +11084,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.21, - output: 0.7899999999999999, + input: 0.5, + output: 1.5, cacheRead: 0, cacheWrite: 0, }, contextWindow: 163840, - maxTokens: 128000, + maxTokens: 16384, } satisfies Model<"anthropic-messages">, "deepseek/deepseek-v3.1-terminus": { id: "deepseek/deepseek-v3.1-terminus", @@ -11075,6 +11143,40 @@ export const MODELS = { contextWindow: 128000, maxTokens: 64000, } satisfies Model<"anthropic-messages">, + "google/gemini-2.0-flash": { + id: "google/gemini-2.0-flash", + name: "Gemini 2.0 Flash", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1048576, + maxTokens: 8192, + } satisfies Model<"anthropic-messages">, + "google/gemini-2.0-flash-lite": { + id: "google/gemini-2.0-flash-lite", + name: "Gemini 2.0 Flash Lite", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1048576, + maxTokens: 8192, + } satisfies Model<"anthropic-messages">, "google/gemini-2.5-flash": { id: "google/gemini-2.5-flash", name: "Gemini 2.5 Flash", @@ -11082,11 +11184,11 @@ export const MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text"], + input: ["text", "image"], cost: { input: 0.3, output: 2.5, - cacheRead: 0, + cacheRead: 0.03, cacheWrite: 0, }, contextWindow: 1000000, @@ -11150,11 +11252,11 @@ export const MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text"], + input: ["text", "image"], cost: { input: 1.25, output: 10, - cacheRead: 0, + cacheRead: 0.125, cacheWrite: 0, }, contextWindow: 1048576, @@ -11175,7 +11277,7 @@ export const MODELS = { cacheWrite: 0, }, contextWindow: 1000000, - maxTokens: 64000, + maxTokens: 65000, } satisfies Model<"anthropic-messages">, "google/gemini-3-pro-preview": { id: "google/gemini-3-pro-preview", @@ -11277,7 +11379,7 @@ export const MODELS = { cacheWrite: 0, }, contextWindow: 128000, - maxTokens: 8192, + maxTokens: 100000, } satisfies Model<"anthropic-messages">, "meituan/longcat-flash-thinking": { id: "meituan/longcat-flash-thinking", @@ -11305,13 +11407,13 @@ export const MODELS = { reasoning: false, input: ["text"], cost: { - input: 0.39999999999999997, - output: 0.39999999999999997, + input: 0.72, + output: 0.72, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 16384, + contextWindow: 128000, + maxTokens: 8192, } satisfies Model<"anthropic-messages">, "meta/llama-3.1-8b": { id: "meta/llama-3.1-8b", @@ -11322,12 +11424,12 @@ export const MODELS = { reasoning: false, input: ["text"], cost: { - input: 0.03, - output: 0.049999999999999996, + input: 0.09999999999999999, + output: 0.09999999999999999, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, + contextWindow: 128000, maxTokens: 16384, } satisfies Model<"anthropic-messages">, "meta/llama-3.2-11b": { @@ -11390,12 +11492,12 @@ export const MODELS = { reasoning: false, input: ["text", "image"], cost: { - input: 0.15, - output: 0.6, + input: 0.24, + output: 0.9700000000000001, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, + contextWindow: 128000, maxTokens: 8192, } satisfies Model<"anthropic-messages">, "meta/llama-4-scout": { @@ -11407,12 +11509,12 @@ export const MODELS = { reasoning: false, input: ["text", "image"], cost: { - input: 0.08, - output: 0.3, + input: 0.16999999999999998, + output: 0.66, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, + contextWindow: 128000, maxTokens: 8192, } satisfies Model<"anthropic-messages">, "minimax/minimax-m2": { @@ -11443,8 +11545,8 @@ export const MODELS = { cost: { input: 0.3, output: 1.2, - cacheRead: 0.15, - cacheWrite: 0, + cacheRead: 0.03, + cacheWrite: 0.375, }, contextWindow: 204800, maxTokens: 131072, @@ -11679,14 +11781,31 @@ export const MODELS = { reasoning: false, input: ["text"], cost: { - input: 0.5, - output: 2, + input: 0.6, + output: 2.5, cacheRead: 0, cacheWrite: 0, }, contextWindow: 131072, maxTokens: 16384, } satisfies Model<"anthropic-messages">, + "moonshotai/kimi-k2-0905": { + id: "moonshotai/kimi-k2-0905", + name: "Kimi K2 0905", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text"], + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 16384, + } satisfies Model<"anthropic-messages">, "moonshotai/kimi-k2-thinking": { id: "moonshotai/kimi-k2-thinking", name: "Kimi K2 Thinking", @@ -11696,13 +11815,13 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.47, - output: 2, - cacheRead: 0.14100000000000001, + input: 0.6, + output: 2.5, + cacheRead: 0.15, cacheWrite: 0, }, - contextWindow: 216144, - maxTokens: 216144, + contextWindow: 262114, + maxTokens: 262114, } satisfies Model<"anthropic-messages">, "moonshotai/kimi-k2-thinking-turbo": { id: "moonshotai/kimi-k2-thinking-turbo", @@ -11747,13 +11866,13 @@ export const MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.5, - output: 2.8, - cacheRead: 0, + input: 0.6, + output: 3, + cacheRead: 0.09999999999999999, cacheWrite: 0, }, - contextWindow: 256000, - maxTokens: 256000, + contextWindow: 262114, + maxTokens: 262114, } satisfies Model<"anthropic-messages">, "nvidia/nemotron-nano-12b-v2-vl": { id: "nvidia/nemotron-nano-12b-v2-vl", @@ -11781,31 +11900,14 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.04, - output: 0.16, + input: 0.06, + output: 0.22999999999999998, cacheRead: 0, cacheWrite: 0, }, contextWindow: 131072, maxTokens: 131072, } satisfies Model<"anthropic-messages">, - "openai/codex-mini": { - id: "openai/codex-mini", - name: "Codex Mini", - api: "anthropic-messages", - provider: "vercel-ai-gateway", - baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, - input: ["text", "image"], - cost: { - input: 1.5, - output: 6, - cacheRead: 0.375, - cacheWrite: 0, - }, - contextWindow: 200000, - maxTokens: 100000, - } satisfies Model<"anthropic-messages">, "openai/gpt-4-turbo": { id: "openai/gpt-4-turbo", name: "GPT-4 Turbo", @@ -11868,7 +11970,7 @@ export const MODELS = { cost: { input: 0.09999999999999999, output: 0.39999999999999997, - cacheRead: 0.03, + cacheRead: 0.024999999999999998, cacheWrite: 0, }, contextWindow: 1047576, @@ -11919,7 +12021,7 @@ export const MODELS = { cost: { input: 1.25, output: 10, - cacheRead: 0.13, + cacheRead: 0.125, cacheWrite: 0, }, contextWindow: 400000, @@ -11949,11 +12051,11 @@ export const MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text", "image"], + input: ["text"], cost: { input: 1.25, output: 10, - cacheRead: 0.13, + cacheRead: 0.125, cacheWrite: 0, }, contextWindow: 400000, @@ -11970,7 +12072,7 @@ export const MODELS = { cost: { input: 0.25, output: 2, - cacheRead: 0.03, + cacheRead: 0.024999999999999998, cacheWrite: 0, }, contextWindow: 400000, @@ -11987,7 +12089,7 @@ export const MODELS = { cost: { input: 0.049999999999999996, output: 0.39999999999999997, - cacheRead: 0.01, + cacheRead: 0.005, cacheWrite: 0, }, contextWindow: 400000, @@ -12021,7 +12123,7 @@ export const MODELS = { cost: { input: 1.25, output: 10, - cacheRead: 0.13, + cacheRead: 0.125, cacheWrite: 0, }, contextWindow: 400000, @@ -12072,7 +12174,7 @@ export const MODELS = { cost: { input: 1.25, output: 10, - cacheRead: 0.13, + cacheRead: 0.125, cacheWrite: 0, }, contextWindow: 128000, @@ -12089,7 +12191,7 @@ export const MODELS = { cost: { input: 1.25, output: 10, - cacheRead: 0.13, + cacheRead: 0.125, cacheWrite: 0, }, contextWindow: 400000, @@ -12106,7 +12208,7 @@ export const MODELS = { cost: { input: 1.75, output: 14, - cacheRead: 0.18, + cacheRead: 0.175, cacheWrite: 0, }, contextWindow: 400000, @@ -12211,7 +12313,7 @@ export const MODELS = { cacheRead: 0.25, cacheWrite: 0, }, - contextWindow: 200000, + contextWindow: 1050000, maxTokens: 128000, } satisfies Model<"anthropic-messages">, "openai/gpt-5.4-pro": { @@ -12228,26 +12330,9 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 200000, + contextWindow: 1050000, maxTokens: 128000, } satisfies Model<"anthropic-messages">, - "openai/gpt-oss-120b": { - id: "openai/gpt-oss-120b", - name: "gpt-oss-120b", - api: "anthropic-messages", - provider: "vercel-ai-gateway", - baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, - input: ["text"], - cost: { - input: 0.09999999999999999, - output: 0.5, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131072, - maxTokens: 131072, - } satisfies Model<"anthropic-messages">, "openai/gpt-oss-20b": { id: "openai/gpt-oss-20b", name: "gpt-oss-20b", @@ -12565,7 +12650,7 @@ export const MODELS = { cost: { input: 3, output: 15, - cacheRead: 0, + cacheRead: 0.75, cacheWrite: 0, }, contextWindow: 256000, @@ -12639,6 +12724,57 @@ export const MODELS = { contextWindow: 2000000, maxTokens: 30000, } satisfies Model<"anthropic-messages">, + "xai/grok-4.20-multi-agent-beta": { + id: "xai/grok-4.20-multi-agent-beta", + name: "Grok 4.20 Multi Agent Beta", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text"], + cost: { + input: 2, + output: 6, + cacheRead: 0.19999999999999998, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 2000000, + } satisfies Model<"anthropic-messages">, + "xai/grok-4.20-non-reasoning-beta": { + id: "xai/grok-4.20-non-reasoning-beta", + name: "Grok 4.20 Beta Non-Reasoning", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0.19999999999999998, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 2000000, + } satisfies Model<"anthropic-messages">, + "xai/grok-4.20-reasoning-beta": { + id: "xai/grok-4.20-reasoning-beta", + name: "Grok 4.20 Beta Reasoning", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0.19999999999999998, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 2000000, + } satisfies Model<"anthropic-messages">, "xai/grok-code-fast-1": { id: "xai/grok-code-fast-1", name: "Grok Code Fast 1", @@ -12665,9 +12801,9 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.09, - output: 0.29, - cacheRead: 0, + input: 0.09999999999999999, + output: 0.3, + cacheRead: 0.02, cacheWrite: 0, }, contextWindow: 262144, @@ -12684,11 +12820,11 @@ export const MODELS = { cost: { input: 0.6, output: 2.2, - cacheRead: 0, + cacheRead: 0.11, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 131072, + contextWindow: 128000, + maxTokens: 96000, } satisfies Model<"anthropic-messages">, "zai/glm-4.5-air": { id: "zai/glm-4.5-air", @@ -12713,16 +12849,16 @@ export const MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text", "image"], cost: { input: 0.6, output: 1.7999999999999998, - cacheRead: 0, + cacheRead: 0.11, cacheWrite: 0, }, - contextWindow: 65536, - maxTokens: 16384, + contextWindow: 66000, + maxTokens: 16000, } satisfies Model<"anthropic-messages">, "zai/glm-4.6": { id: "zai/glm-4.6", @@ -12784,14 +12920,31 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.43, - output: 1.75, - cacheRead: 0.08, + input: 0.6, + output: 2.2, + cacheRead: 0, cacheWrite: 0, }, - contextWindow: 202752, + contextWindow: 200000, maxTokens: 120000, } satisfies Model<"anthropic-messages">, + "zai/glm-4.7-flash": { + id: "zai/glm-4.7-flash", + name: "GLM 4.7 Flash", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text"], + cost: { + input: 0.07, + output: 0.39999999999999997, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 200000, + maxTokens: 131000, + } satisfies Model<"anthropic-messages">, "zai/glm-4.7-flashx": { id: "zai/glm-4.7-flashx", name: "GLM 4.7 FlashX", @@ -12818,9 +12971,9 @@ export const MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.7999999999999999, - output: 2.56, - cacheRead: 0.16, + input: 1, + output: 3.1999999999999997, + cacheRead: 0.19999999999999998, cacheWrite: 0, }, contextWindow: 202800, @@ -13151,6 +13304,57 @@ export const MODELS = { contextWindow: 2000000, maxTokens: 30000, } satisfies Model<"openai-completions">, + "grok-4.20-beta-latest-non-reasoning": { + id: "grok-4.20-beta-latest-non-reasoning", + name: "Grok 4.20 Beta (Non-Reasoning)", + api: "openai-completions", + provider: "xai", + baseUrl: "https://api.x.ai/v1", + reasoning: false, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 30000, + } satisfies Model<"openai-completions">, + "grok-4.20-beta-latest-reasoning": { + id: "grok-4.20-beta-latest-reasoning", + name: "Grok 4.20 Beta (Reasoning)", + api: "openai-completions", + provider: "xai", + baseUrl: "https://api.x.ai/v1", + reasoning: true, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 30000, + } satisfies Model<"openai-completions">, + "grok-4.20-multi-agent-beta-latest": { + id: "grok-4.20-multi-agent-beta-latest", + name: "Grok 4.20 Multi-Agent Beta", + api: "openai-completions", + provider: "xai", + baseUrl: "https://api.x.ai/v1", + reasoning: true, + input: ["text", "image"], + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + contextWindow: 2000000, + maxTokens: 30000, + } satisfies Model<"openai-completions">, "grok-beta": { id: "grok-beta", name: "Grok Beta",