chore(ai): update generated model catalog

This commit is contained in:
Mario Zechner
2026-04-08 18:54:56 +02:00
parent 70fb83fcff
commit da6e9ea473

View File

@@ -1212,6 +1212,23 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 65536,
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-coder-next": {
id: "qwen.qwen3-coder-next",
name: "Qwen3 Coder Next",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: true,
input: ["text"],
cost: {
input: 0.22,
output: 1.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 65536,
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-next-80b-a3b": {
id: "qwen.qwen3-next-80b-a3b",
name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
@@ -3018,7 +3035,7 @@ export const MODELS = {
} satisfies Model<"openai-responses">,
"gpt-5.4-mini": {
id: "gpt-5.4-mini",
name: "GPT-5.4 mini",
name: "GPT-5.4 Mini",
api: "openai-responses",
provider: "github-copilot",
baseUrl: "https://api.individual.githubcopilot.com",
@@ -3480,8 +3497,8 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 8192,
} satisfies Model<"google-generative-ai">,
"gemma-4-26b": {
id: "gemma-4-26b",
"gemma-4-26b-it": {
id: "gemma-4-26b-it",
name: "Gemma 4 26B",
api: "google-generative-ai",
provider: "google",
@@ -3497,8 +3514,8 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 8192,
} satisfies Model<"google-generative-ai">,
"gemma-4-31b": {
id: "gemma-4-31b",
"gemma-4-31b-it": {
id: "gemma-4-31b-it",
name: "Gemma 4 31B",
api: "google-generative-ai",
provider: "google",
@@ -4630,6 +4647,24 @@ export const MODELS = {
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"zai-org/GLM-5.1": {
id: "zai-org/GLM-5.1",
name: "GLM-5.1",
api: "openai-completions",
provider: "huggingface",
baseUrl: "https://router.huggingface.co/v1",
compat: {"supportsDeveloperRole":false},
reasoning: true,
input: ["text"],
cost: {
input: 1,
output: 3.2,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
},
"kimi-coding": {
"k2p5": {
@@ -6242,6 +6277,23 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"glm-5.1": {
id: "glm-5.1",
name: "GLM-5.1",
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
reasoning: true,
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"gpt-5": {
id: "gpt-5",
name: "GPT-5",
@@ -6548,23 +6600,6 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"qwen3.6-plus-free": {
id: "qwen3.6-plus-free",
name: "Qwen3.6 Plus 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: 1048576,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
},
"opencode-go": {
"glm-5": {
@@ -6584,6 +6619,23 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"glm-5.1": {
id: "glm-5.1",
name: "GLM-5.1",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
reasoning: true,
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"kimi-k2.5": {
id: "kimi-k2.5",
name: "Kimi K2.5",
@@ -6638,9 +6690,9 @@ export const MODELS = {
"minimax-m2.5": {
id: "minimax-m2.5",
name: "MiniMax M2.5",
api: "openai-completions",
api: "anthropic-messages",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
baseUrl: "https://opencode.ai/zen/go",
reasoning: true,
input: ["text"],
cost: {
@@ -6651,7 +6703,7 @@ export const MODELS = {
},
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
} satisfies Model<"anthropic-messages">,
"minimax-m2.7": {
id: "minimax-m2.7",
name: "MiniMax M2.7",
@@ -6960,6 +7012,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-4.6-fast": {
id: "anthropic/claude-opus-4.6-fast",
name: "Anthropic: Claude Opus 4.6 (Fast)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 30,
output: 150,
cacheRead: 3,
cacheWrite: 37.5,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"anthropic/claude-sonnet-4": {
id: "anthropic/claude-sonnet-4",
name: "Anthropic: Claude Sonnet 4",
@@ -7623,6 +7692,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"google/gemma-4-26b-a4b-it:free": {
id: "google/gemma-4-26b-a4b-it:free",
name: "Google: Gemma 4 26B A4B (free)",
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: 32768,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it": {
id: "google/gemma-4-31b-it",
name: "Google: Gemma 4 31B",
@@ -7640,6 +7726,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it:free": {
id: "google/gemma-4-31b-it:free",
name: "Google: Gemma 4 31B (free)",
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: 32768,
} satisfies Model<"openai-completions">,
"inception/mercury": {
id: "inception/mercury",
name: "Inception: Mercury",
@@ -8348,11 +8451,11 @@ export const MODELS = {
cost: {
input: 0.39999999999999997,
output: 2,
cacheRead: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 4096,
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2-thinking": {
id: "moonshotai/kimi-k2-thinking",
@@ -8363,12 +8466,12 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.47,
output: 2,
cacheRead: 0.14100000000000001,
input: 0.6,
output: 2.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.5": {
@@ -10292,17 +10395,17 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-plus:free": {
id: "qwen/qwen3.6-plus:free",
name: "Qwen: Qwen3.6 Plus (free)",
"qwen/qwen3.6-plus": {
id: "qwen/qwen3.6-plus",
name: "Qwen: Qwen3.6 Plus",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
input: 0.325,
output: 1.95,
cacheRead: 0,
cacheWrite: 0,
},
@@ -10887,6 +10990,23 @@ export const MODELS = {
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.1": {
id: "z-ai/glm-5.1",
name: "Z.ai: GLM 5.1",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text"],
cost: {
input: 1.26,
output: 3.9600000000000004,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"z-ai/glm-5v-turbo": {
id: "z-ai/glm-5v-turbo",
name: "Z.ai: GLM 5V Turbo",
@@ -10932,13 +11052,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.22,
output: 0.88,
cacheRead: 0.11,
input: 0.6,
output: 1.2,
cacheRead: 0.6,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 16384,
contextWindow: 131000,
maxTokens: 40000,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen-3-30b": {
id: "alibaba/qwen-3-30b",
@@ -11173,7 +11293,7 @@ export const MODELS = {
input: 0.5,
output: 3,
cacheRead: 0.09999999999999999,
cacheWrite: 0.625,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 64000,
@@ -11788,7 +11908,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
maxTokens: 100000,
} satisfies Model<"anthropic-messages">,
"meta/llama-3.1-70b": {
id: "meta/llama-3.1-70b",
@@ -12793,23 +12913,6 @@ export const MODELS = {
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: 0.15,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
name: "gpt-oss-20b",
@@ -12997,23 +13100,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"xai/grok-2-vision": {
id: "xai/grok-2-vision",
name: "Grok 2 Vision",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text", "image"],
cost: {
input: 2,
output: 10,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"xai/grok-3": {
id: "xai/grok-3",
name: "Grok 3 Beta",
@@ -13431,13 +13517,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.6,
output: 2.2,
cacheRead: 0.11,
input: 2.25,
output: 2.75,
cacheRead: 2.25,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 120000,
contextWindow: 131000,
maxTokens: 40000,
} satisfies Model<"anthropic-messages">,
"zai/glm-4.7-flash": {
id: "zai/glm-4.7-flash",
@@ -13507,6 +13593,23 @@ export const MODELS = {
contextWindow: 202800,
maxTokens: 131100,
} satisfies Model<"anthropic-messages">,
"zai/glm-5.1": {
id: "zai/glm-5.1",
name: "GLM 5.1",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 202800,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"zai/glm-5v-turbo": {
id: "zai/glm-5v-turbo",
name: "GLM 5V Turbo",