17197 lines
445 KiB
TypeScript
17197 lines
445 KiB
TypeScript
// This file is auto-generated by scripts/generate-models.ts
|
|
// Do not edit manually - run 'npm run generate-models' to update
|
|
|
|
import type { Model } from "./types.ts";
|
|
|
|
export const MODELS = {
|
|
"amazon-bedrock": {
|
|
"amazon.nova-2-lite-v1:0": {
|
|
id: "amazon.nova-2-lite-v1:0",
|
|
name: "Nova 2 Lite",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.33,
|
|
output: 2.75,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"amazon.nova-lite-v1:0": {
|
|
id: "amazon.nova-lite-v1:0",
|
|
name: "Nova Lite",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.24,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 300000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"amazon.nova-micro-v1:0": {
|
|
id: "amazon.nova-micro-v1:0",
|
|
name: "Nova Micro",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.035,
|
|
output: 0.14,
|
|
cacheRead: 0.00875,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"amazon.nova-pro-v1:0": {
|
|
id: "amazon.nova-pro-v1:0",
|
|
name: "Nova Pro",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 3.2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 300000,
|
|
maxTokens: 8192,
|
|
} 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",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-opus-4-1-20250805-v1:0": {
|
|
id: "anthropic.claude-opus-4-1-20250805-v1:0",
|
|
name: "Claude Opus 4.1",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-opus-4-5-20251101-v1:0": {
|
|
id: "anthropic.claude-opus-4-5-20251101-v1:0",
|
|
name: "Claude Opus 4.5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-opus-4-6-v1": {
|
|
id: "anthropic.claude-opus-4-6-v1",
|
|
name: "Claude Opus 4.6",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-opus-4-7": {
|
|
id: "anthropic.claude-opus-4-7",
|
|
name: "Claude Opus 4.7",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-opus-4-8": {
|
|
id: "anthropic.claude-opus-4-8",
|
|
name: "Claude Opus 4.8",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
|
id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
|
|
name: "Claude Sonnet 4.5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"anthropic.claude-sonnet-4-6": {
|
|
id: "anthropic.claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"au.anthropic.claude-haiku-4-5-20251001-v1:0": {
|
|
id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
name: "Claude Haiku 4.5 (AU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"au.anthropic.claude-opus-4-6-v1": {
|
|
id: "au.anthropic.claude-opus-4-6-v1",
|
|
name: "AU Anthropic Claude Opus 4.6",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 16.5,
|
|
output: 82.5,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"au.anthropic.claude-opus-4-8": {
|
|
id: "au.anthropic.claude-opus-4-8",
|
|
name: "Claude Opus 4.8 (AU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
|
id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
|
name: "Claude Sonnet 4.5 (AU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"au.anthropic.claude-sonnet-4-6": {
|
|
id: "au.anthropic.claude-sonnet-4-6",
|
|
name: "AU Anthropic Claude Sonnet 4.6",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3.3,
|
|
output: 16.5,
|
|
cacheRead: 0.33,
|
|
cacheWrite: 4.125,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"deepseek.r1-v1:0": {
|
|
id: "deepseek.r1-v1:0",
|
|
name: "DeepSeek-R1",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.35,
|
|
output: 5.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"deepseek.v3-v1:0": {
|
|
id: "deepseek.v3-v1:0",
|
|
name: "DeepSeek-V3.1",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.58,
|
|
output: 1.68,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 81920,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"deepseek.v3.2": {
|
|
id: "deepseek.v3.2",
|
|
name: "DeepSeek-V3.2",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.62,
|
|
output: 1.85,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 81920,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-fable-5": {
|
|
id: "eu.anthropic.claude-fable-5",
|
|
name: "Claude Fable 5 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 11,
|
|
output: 55,
|
|
cacheRead: 1.1,
|
|
cacheWrite: 13.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-haiku-4-5-20251001-v1:0": {
|
|
id: "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
name: "Claude Haiku 4.5 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-opus-4-5-20251101-v1:0": {
|
|
id: "eu.anthropic.claude-opus-4-5-20251101-v1:0",
|
|
name: "Claude Opus 4.5 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-opus-4-6-v1": {
|
|
id: "eu.anthropic.claude-opus-4-6-v1",
|
|
name: "Claude Opus 4.6 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5.5,
|
|
output: 27.5,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-opus-4-7": {
|
|
id: "eu.anthropic.claude-opus-4-7",
|
|
name: "Claude Opus 4.7 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5.5,
|
|
output: 27.5,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 6.875,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-opus-4-8": {
|
|
id: "eu.anthropic.claude-opus-4-8",
|
|
name: "Claude Opus 4.8 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5.5,
|
|
output: 27.5,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 6.875,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
|
id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
|
name: "Claude Sonnet 4.5 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3.3,
|
|
output: 16.5,
|
|
cacheRead: 0.33,
|
|
cacheWrite: 4.125,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"eu.anthropic.claude-sonnet-4-6": {
|
|
id: "eu.anthropic.claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6 (EU)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3.3,
|
|
output: 16.5,
|
|
cacheRead: 0.33,
|
|
cacheWrite: 4.125,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-fable-5": {
|
|
id: "global.anthropic.claude-fable-5",
|
|
name: "Claude Fable 5 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-haiku-4-5-20251001-v1:0": {
|
|
id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
name: "Claude Haiku 4.5 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-opus-4-5-20251101-v1:0": {
|
|
id: "global.anthropic.claude-opus-4-5-20251101-v1:0",
|
|
name: "Claude Opus 4.5 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-opus-4-6-v1": {
|
|
id: "global.anthropic.claude-opus-4-6-v1",
|
|
name: "Claude Opus 4.6 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-opus-4-7": {
|
|
id: "global.anthropic.claude-opus-4-7",
|
|
name: "Claude Opus 4.7 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-opus-4-8": {
|
|
id: "global.anthropic.claude-opus-4-8",
|
|
name: "Claude Opus 4.8 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
|
id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
|
name: "Claude Sonnet 4.5 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"global.anthropic.claude-sonnet-4-6": {
|
|
id: "global.anthropic.claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6 (Global)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"google.gemma-3-27b-it": {
|
|
id: "google.gemma-3-27b-it",
|
|
name: "Google Gemma 3 27B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.12,
|
|
output: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"google.gemma-3-4b-it": {
|
|
id: "google.gemma-3-4b-it",
|
|
name: "Gemma 3 4B IT",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.04,
|
|
output: 0.08,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"jp.anthropic.claude-opus-4-7": {
|
|
id: "jp.anthropic.claude-opus-4-7",
|
|
name: "Claude Opus 4.7 (JP)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"jp.anthropic.claude-opus-4-8": {
|
|
id: "jp.anthropic.claude-opus-4-8",
|
|
name: "Claude Opus 4.8 (JP)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
|
id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
|
name: "Claude Sonnet 4.5 (JP)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"jp.anthropic.claude-sonnet-4-6": {
|
|
id: "jp.anthropic.claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6 (JP)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} 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",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.72,
|
|
output: 0.72,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"meta.llama3-1-8b-instruct-v1:0": {
|
|
id: "meta.llama3-1-8b-instruct-v1:0",
|
|
name: "Llama 3.1 8B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 0.22,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"meta.llama3-3-70b-instruct-v1:0": {
|
|
id: "meta.llama3-3-70b-instruct-v1:0",
|
|
name: "Llama 3.3 70B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.72,
|
|
output: 0.72,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"meta.llama4-maverick-17b-instruct-v1:0": {
|
|
id: "meta.llama4-maverick-17b-instruct-v1:0",
|
|
name: "Llama 4 Maverick 17B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.24,
|
|
output: 0.97,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"meta.llama4-scout-17b-instruct-v1:0": {
|
|
id: "meta.llama4-scout-17b-instruct-v1:0",
|
|
name: "Llama 4 Scout 17B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.17,
|
|
output: 0.66,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 3500000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"minimax.minimax-m2": {
|
|
id: "minimax.minimax-m2",
|
|
name: "MiniMax M2",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204608,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"minimax.minimax-m2.1": {
|
|
id: "minimax.minimax-m2.1",
|
|
name: "MiniMax M2.1",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"minimax.minimax-m2.5": {
|
|
id: "minimax.minimax-m2.5",
|
|
name: "MiniMax M2.5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 196608,
|
|
maxTokens: 98304,
|
|
} 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",
|
|
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: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"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", "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: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"mistral.voxtral-mini-3b-2507": {
|
|
id: "mistral.voxtral-mini-3b-2507",
|
|
name: "Voxtral Mini 3B 2507",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.04,
|
|
output: 0.04,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"mistral.voxtral-small-24b-2507": {
|
|
id: "mistral.voxtral-small-24b-2507",
|
|
name: "Voxtral Small 24B 2507",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.35,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"moonshot.kimi-k2-thinking": {
|
|
id: "moonshot.kimi-k2-thinking",
|
|
name: "Kimi K2 Thinking",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262143,
|
|
maxTokens: 16000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"moonshotai.kimi-k2.5": {
|
|
id: "moonshotai.kimi-k2.5",
|
|
name: "Kimi K2.5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262143,
|
|
maxTokens: 16000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"nvidia.nemotron-nano-12b-v2": {
|
|
id: "nvidia.nemotron-nano-12b-v2",
|
|
name: "NVIDIA Nemotron Nano 12B v2 VL BF16",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.23,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"nvidia.nemotron-super-3-120b": {
|
|
id: "nvidia.nemotron-super-3-120b",
|
|
name: "NVIDIA Nemotron 3 Super 120B A12B",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.65,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-5.4": {
|
|
id: "openai.gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.75,
|
|
output: 16.5,
|
|
cacheRead: 0.275,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-5.5": {
|
|
id: "openai.gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5.5,
|
|
output: 33,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-oss-120b": {
|
|
id: "openai.gpt-oss-120b",
|
|
name: "gpt-oss-120b",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-oss-120b-1:0": {
|
|
id: "openai.gpt-oss-120b-1:0",
|
|
name: "gpt-oss-120b",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-oss-20b": {
|
|
id: "openai.gpt-oss-20b",
|
|
name: "gpt-oss-20b",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.07,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-oss-20b-1:0": {
|
|
id: "openai.gpt-oss-20b-1:0",
|
|
name: "gpt-oss-20b",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.07,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-oss-safeguard-120b": {
|
|
id: "openai.gpt-oss-safeguard-120b",
|
|
name: "GPT OSS Safeguard 120B",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"openai.gpt-oss-safeguard-20b": {
|
|
id: "openai.gpt-oss-safeguard-20b",
|
|
name: "GPT OSS Safeguard 20B",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.07,
|
|
output: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"qwen.qwen3-235b-a22b-2507-v1:0": {
|
|
id: "qwen.qwen3-235b-a22b-2507-v1:0",
|
|
name: "Qwen3 235B A22B 2507",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 0.88,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"qwen.qwen3-32b-v1:0": {
|
|
id: "qwen.qwen3-32b-v1:0",
|
|
name: "Qwen3 32B (dense)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 16384,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"qwen.qwen3-coder-30b-a3b-v1:0": {
|
|
id: "qwen.qwen3-coder-30b-a3b-v1:0",
|
|
name: "Qwen3 Coder 30B A3B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"qwen.qwen3-coder-480b-a35b-v1:0": {
|
|
id: "qwen.qwen3-coder-480b-a35b-v1:0",
|
|
name: "Qwen3 Coder 480B A35B Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 1.8,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 1.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"qwen.qwen3-vl-235b-a22b": {
|
|
id: "qwen.qwen3-vl-235b-a22b",
|
|
name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-fable-5": {
|
|
id: "us.anthropic.claude-fable-5",
|
|
name: "Claude Fable 5 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-haiku-4-5-20251001-v1:0": {
|
|
id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
name: "Claude Haiku 4.5 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-opus-4-1-20250805-v1:0": {
|
|
id: "us.anthropic.claude-opus-4-1-20250805-v1:0",
|
|
name: "Claude Opus 4.1 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-opus-4-5-20251101-v1:0": {
|
|
id: "us.anthropic.claude-opus-4-5-20251101-v1:0",
|
|
name: "Claude Opus 4.5 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-opus-4-6-v1": {
|
|
id: "us.anthropic.claude-opus-4-6-v1",
|
|
name: "Claude Opus 4.6 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-opus-4-7": {
|
|
id: "us.anthropic.claude-opus-4-7",
|
|
name: "Claude Opus 4.7 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-opus-4-8": {
|
|
id: "us.anthropic.claude-opus-4-8",
|
|
name: "Claude Opus 4.8 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
|
id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
|
name: "Claude Sonnet 4.5 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.anthropic.claude-sonnet-4-6": {
|
|
id: "us.anthropic.claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.deepseek.r1-v1:0": {
|
|
id: "us.deepseek.r1-v1:0",
|
|
name: "DeepSeek-R1 (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.35,
|
|
output: 5.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.meta.llama4-maverick-17b-instruct-v1:0": {
|
|
id: "us.meta.llama4-maverick-17b-instruct-v1:0",
|
|
name: "Llama 4 Maverick 17B Instruct (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.24,
|
|
output: 0.97,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"us.meta.llama4-scout-17b-instruct-v1:0": {
|
|
id: "us.meta.llama4-scout-17b-instruct-v1:0",
|
|
name: "Llama 4 Scout 17B Instruct (US)",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.17,
|
|
output: 0.66,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 3500000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"writer.palmyra-x4-v1:0": {
|
|
id: "writer.palmyra-x4-v1:0",
|
|
name: "Palmyra X4",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 122880,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"writer.palmyra-x5-v1:0": {
|
|
id: "writer.palmyra-x5-v1:0",
|
|
name: "Palmyra X5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1040000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"zai.glm-4.7": {
|
|
id: "zai.glm-4.7",
|
|
name: "GLM-4.7",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"zai.glm-4.7-flash": {
|
|
id: "zai.glm-4.7-flash",
|
|
name: "GLM-4.7-Flash",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.07,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
"zai.glm-5": {
|
|
id: "zai.glm-5",
|
|
name: "GLM-5",
|
|
api: "bedrock-converse-stream",
|
|
provider: "amazon-bedrock",
|
|
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 101376,
|
|
} satisfies Model<"bedrock-converse-stream">,
|
|
},
|
|
"ant-ling": {
|
|
"Ling-2.6-1T": {
|
|
id: "Ling-2.6-1T",
|
|
name: "Ling 2.6 1T",
|
|
api: "openai-completions",
|
|
provider: "ant-ling",
|
|
baseUrl: "https://api.ant-ling.com/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.25,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"Ling-2.6-flash": {
|
|
id: "Ling-2.6-flash",
|
|
name: "Ling 2.6 Flash",
|
|
api: "openai-completions",
|
|
provider: "ant-ling",
|
|
baseUrl: "https://api.ant-ling.com/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.01,
|
|
output: 0.02,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"Ring-2.6-1T": {
|
|
id: "Ring-2.6-1T",
|
|
name: "Ring 2.6 1T",
|
|
api: "openai-completions",
|
|
provider: "ant-ling",
|
|
baseUrl: "https://api.ant-ling.com/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"thinkingFormat":"ant-ling"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.25,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"anthropic": {
|
|
"claude-3-5-haiku-20241022": {
|
|
id: "claude-3-5-haiku-20241022",
|
|
name: "Claude Haiku 3.5",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 1,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-5-haiku-latest": {
|
|
id: "claude-3-5-haiku-latest",
|
|
name: "Claude Haiku 3.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 1,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-5-sonnet-20240620": {
|
|
id: "claude-3-5-sonnet-20240620",
|
|
name: "Claude Sonnet 3.5",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-5-sonnet-20241022": {
|
|
id: "claude-3-5-sonnet-20241022",
|
|
name: "Claude Sonnet 3.5 v2",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-7-sonnet-20250219": {
|
|
id: "claude-3-7-sonnet-20250219",
|
|
name: "Claude Sonnet 3.7",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-haiku-20240307": {
|
|
id: "claude-3-haiku-20240307",
|
|
name: "Claude Haiku 3",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.25,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.3,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-opus-20240229": {
|
|
id: "claude-3-opus-20240229",
|
|
name: "Claude Opus 3",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-sonnet-20240229": {
|
|
id: "claude-3-sonnet-20240229",
|
|
name: "Claude Sonnet 3",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 0.3,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-fable-5": {
|
|
id: "claude-fable-5",
|
|
name: "Claude Fable 5",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-haiku-4-5": {
|
|
id: "claude-haiku-4-5",
|
|
name: "Claude Haiku 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-haiku-4-5-20251001": {
|
|
id: "claude-haiku-4-5-20251001",
|
|
name: "Claude Haiku 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-0": {
|
|
id: "claude-opus-4-0",
|
|
name: "Claude Opus 4 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-1": {
|
|
id: "claude-opus-4-1",
|
|
name: "Claude Opus 4.1 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-1-20250805": {
|
|
id: "claude-opus-4-1-20250805",
|
|
name: "Claude Opus 4.1",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-20250514": {
|
|
id: "claude-opus-4-20250514",
|
|
name: "Claude Opus 4",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-5": {
|
|
id: "claude-opus-4-5",
|
|
name: "Claude Opus 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-5-20251101": {
|
|
id: "claude-opus-4-5-20251101",
|
|
name: "Claude Opus 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-6": {
|
|
id: "claude-opus-4-6",
|
|
name: "Claude Opus 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-7": {
|
|
id: "claude-opus-4-7",
|
|
name: "Claude Opus 4.7",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-8": {
|
|
id: "claude-opus-4-8",
|
|
name: "Claude Opus 4.8",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-0": {
|
|
id: "claude-sonnet-4-0",
|
|
name: "Claude Sonnet 4 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-20250514": {
|
|
id: "claude-sonnet-4-20250514",
|
|
name: "Claude Sonnet 4",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-5": {
|
|
id: "claude-sonnet-4-5",
|
|
name: "Claude Sonnet 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-5-20250929": {
|
|
id: "claude-sonnet-4-5-20250929",
|
|
name: "Claude Sonnet 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-6": {
|
|
id: "claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
baseUrl: "https://api.anthropic.com",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"azure-openai-responses": {
|
|
"gpt-4": {
|
|
id: "gpt-4",
|
|
name: "GPT-4",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 30,
|
|
output: 60,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 8192,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4-turbo": {
|
|
id: "gpt-4-turbo",
|
|
name: "GPT-4 Turbo",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 30,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4.1": {
|
|
id: "gpt-4.1",
|
|
name: "GPT-4.1",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4.1-mini": {
|
|
id: "gpt-4.1-mini",
|
|
name: "GPT-4.1 mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4.1-nano": {
|
|
id: "gpt-4.1-nano",
|
|
name: "GPT-4.1 nano",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4o": {
|
|
id: "gpt-4o",
|
|
name: "GPT-4o",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4o-2024-05-13": {
|
|
id: "gpt-4o-2024-05-13",
|
|
name: "GPT-4o (2024-05-13)",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4o-2024-08-06": {
|
|
id: "gpt-4o-2024-08-06",
|
|
name: "GPT-4o (2024-08-06)",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4o-2024-11-20": {
|
|
id: "gpt-4o-2024-11-20",
|
|
name: "GPT-4o (2024-11-20)",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-4o-mini": {
|
|
id: "gpt-4o-mini",
|
|
name: "GPT-4o mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5": {
|
|
id: "gpt-5",
|
|
name: "GPT-5",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5-chat-latest": {
|
|
id: "gpt-5-chat-latest",
|
|
name: "GPT-5 Chat Latest",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5-codex": {
|
|
id: "gpt-5-codex",
|
|
name: "GPT-5-Codex",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5-mini": {
|
|
id: "gpt-5-mini",
|
|
name: "GPT-5 Mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5-nano": {
|
|
id: "gpt-5-nano",
|
|
name: "GPT-5 Nano",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.4,
|
|
cacheRead: 0.005,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5-pro": {
|
|
id: "gpt-5-pro",
|
|
name: "GPT-5 Pro",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 120,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.1": {
|
|
id: "gpt-5.1",
|
|
name: "GPT-5.1",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.1-chat-latest": {
|
|
id: "gpt-5.1-chat-latest",
|
|
name: "GPT-5.1 Chat",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.1-codex": {
|
|
id: "gpt-5.1-codex",
|
|
name: "GPT-5.1 Codex",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.1-codex-max": {
|
|
id: "gpt-5.1-codex-max",
|
|
name: "GPT-5.1 Codex Max",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.1-codex-mini": {
|
|
id: "gpt-5.1-codex-mini",
|
|
name: "GPT-5.1 Codex mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.2": {
|
|
id: "gpt-5.2",
|
|
name: "GPT-5.2",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.2-chat-latest": {
|
|
id: "gpt-5.2-chat-latest",
|
|
name: "GPT-5.2 Chat",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.2-codex": {
|
|
id: "gpt-5.2-codex",
|
|
name: "GPT-5.2 Codex",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.2-pro": {
|
|
id: "gpt-5.2-pro",
|
|
name: "GPT-5.2 Pro",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 21,
|
|
output: 168,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.3-chat-latest": {
|
|
id: "gpt-5.3-chat-latest",
|
|
name: "GPT-5.3 Chat (latest)",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: false,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.3-codex": {
|
|
id: "gpt-5.3-codex",
|
|
name: "GPT-5.3 Codex",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.3-codex-spark": {
|
|
id: "gpt-5.3-codex-spark",
|
|
name: "GPT-5.3 Codex Spark",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.4": {
|
|
id: "gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.4-mini": {
|
|
id: "gpt-5.4-mini",
|
|
name: "GPT-5.4 mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.4-nano": {
|
|
id: "gpt-5.4-nano",
|
|
name: "GPT-5.4 nano",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.25,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.4-pro": {
|
|
id: "gpt-5.4-pro",
|
|
name: "GPT-5.4 Pro",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.5": {
|
|
id: "gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"gpt-5.5-pro": {
|
|
id: "gpt-5.5-pro",
|
|
name: "GPT-5.5 Pro",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"low":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o1": {
|
|
id: "o1",
|
|
name: "o1",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 60,
|
|
cacheRead: 7.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o1-pro": {
|
|
id: "o1-pro",
|
|
name: "o1-pro",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 150,
|
|
output: 600,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o3": {
|
|
id: "o3",
|
|
name: "o3",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o3-deep-research": {
|
|
id: "o3-deep-research",
|
|
name: "o3-deep-research",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 40,
|
|
cacheRead: 2.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o3-mini": {
|
|
id: "o3-mini",
|
|
name: "o3-mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o3-pro": {
|
|
id: "o3-pro",
|
|
name: "o3-pro",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 20,
|
|
output: 80,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o4-mini": {
|
|
id: "o4-mini",
|
|
name: "o4-mini",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.275,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
"o4-mini-deep-research": {
|
|
id: "o4-mini-deep-research",
|
|
name: "o4-mini-deep-research",
|
|
api: "azure-openai-responses",
|
|
provider: "azure-openai-responses",
|
|
baseUrl: "",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"azure-openai-responses">,
|
|
},
|
|
"cerebras": {
|
|
"gpt-oss-120b": {
|
|
id: "gpt-oss-120b",
|
|
name: "GPT OSS 120B",
|
|
api: "openai-completions",
|
|
provider: "cerebras",
|
|
baseUrl: "https://api.cerebras.ai/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.35,
|
|
output: 0.75,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 40960,
|
|
} satisfies Model<"openai-completions">,
|
|
"zai-glm-4.7": {
|
|
id: "zai-glm-4.7",
|
|
name: "Z.AI GLM-4.7",
|
|
api: "openai-completions",
|
|
provider: "cerebras",
|
|
baseUrl: "https://api.cerebras.ai/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.25,
|
|
output: 2.75,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 40960,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"cloudflare-ai-gateway": {
|
|
"claude-3-5-haiku": {
|
|
id: "claude-3-5-haiku",
|
|
name: "Claude Haiku 3.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 1,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-haiku": {
|
|
id: "claude-3-haiku",
|
|
name: "Claude Haiku 3",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.25,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.3,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-opus": {
|
|
id: "claude-3-opus",
|
|
name: "Claude Opus 3",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3-sonnet": {
|
|
id: "claude-3-sonnet",
|
|
name: "Claude Sonnet 3",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 0.3,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3.5-haiku": {
|
|
id: "claude-3.5-haiku",
|
|
name: "Claude Haiku 3.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 1,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-3.5-sonnet": {
|
|
id: "claude-3.5-sonnet",
|
|
name: "Claude Sonnet 3.5 v2",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-fable-5": {
|
|
id: "claude-fable-5",
|
|
name: "Claude Fable 5",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-haiku-4-5": {
|
|
id: "claude-haiku-4-5",
|
|
name: "Claude Haiku 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4": {
|
|
id: "claude-opus-4",
|
|
name: "Claude Opus 4 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-1": {
|
|
id: "claude-opus-4-1",
|
|
name: "Claude Opus 4.1 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-5": {
|
|
id: "claude-opus-4-5",
|
|
name: "Claude Opus 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-6": {
|
|
id: "claude-opus-4-6",
|
|
name: "Claude Opus 4.6 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-7": {
|
|
id: "claude-opus-4-7",
|
|
name: "Claude Opus 4.7",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-8": {
|
|
id: "claude-opus-4-8",
|
|
name: "Claude Opus 4.8",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4": {
|
|
id: "claude-sonnet-4",
|
|
name: "Claude Sonnet 4 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-5": {
|
|
id: "claude-sonnet-4-5",
|
|
name: "Claude Sonnet 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-6": {
|
|
id: "claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"gpt-4": {
|
|
id: "gpt-4",
|
|
name: "GPT-4",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 30,
|
|
output: 60,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 8192,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4-turbo": {
|
|
id: "gpt-4-turbo",
|
|
name: "GPT-4 Turbo",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 30,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o": {
|
|
id: "gpt-4o",
|
|
name: "GPT-4o",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o-mini": {
|
|
id: "gpt-4o-mini",
|
|
name: "GPT-4o mini",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1": {
|
|
id: "gpt-5.1",
|
|
name: "GPT-5.1",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex": {
|
|
id: "gpt-5.1-codex",
|
|
name: "GPT-5.1 Codex",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2": {
|
|
id: "gpt-5.2",
|
|
name: "GPT-5.2",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2-codex": {
|
|
id: "gpt-5.2-codex",
|
|
name: "GPT-5.2 Codex",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.3-codex": {
|
|
id: "gpt-5.3-codex",
|
|
name: "GPT-5.3 Codex",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4": {
|
|
id: "gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.5": {
|
|
id: "gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o1": {
|
|
id: "o1",
|
|
name: "o1",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 60,
|
|
cacheRead: 7.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3": {
|
|
id: "o3",
|
|
name: "o3",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3-mini": {
|
|
id: "o3-mini",
|
|
name: "o3-mini",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3-pro": {
|
|
id: "o3-pro",
|
|
name: "o3-pro",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 20,
|
|
output: 80,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o4-mini": {
|
|
id: "o4-mini",
|
|
name: "o4-mini",
|
|
api: "openai-responses",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.28,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"workers-ai/@cf/moonshotai/kimi-k2.5": {
|
|
id: "workers-ai/@cf/moonshotai/kimi-k2.5",
|
|
name: "Kimi K2.5",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"workers-ai/@cf/moonshotai/kimi-k2.6": {
|
|
id: "workers-ai/@cf/moonshotai/kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"workers-ai/@cf/nvidia/nemotron-3-120b-a12b": {
|
|
id: "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
|
|
name: "Nemotron 3 Super 120B",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"workers-ai/@cf/zai-org/glm-4.7-flash": {
|
|
id: "workers-ai/@cf/zai-org/glm-4.7-flash",
|
|
name: "GLM-4.7-Flash",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-ai-gateway",
|
|
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"cloudflare-workers-ai": {
|
|
"@cf/google/gemma-4-26b-a4b-it": {
|
|
id: "@cf/google/gemma-4-26b-a4b-it",
|
|
name: "Gemma 4 26B A4B IT",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/ibm-granite/granite-4.0-h-micro": {
|
|
id: "@cf/ibm-granite/granite-4.0-h-micro",
|
|
name: "Granite 4.0 H Micro",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.017,
|
|
output: 0.112,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131000,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
|
|
id: "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
|
|
name: "Llama 3.3 70B Instruct fp8 Fast",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.293,
|
|
output: 2.253,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 24000,
|
|
maxTokens: 24000,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/meta/llama-4-scout-17b-16e-instruct": {
|
|
id: "@cf/meta/llama-4-scout-17b-16e-instruct",
|
|
name: "Llama 4 Scout 17B 16E Instruct",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.27,
|
|
output: 0.85,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/mistralai/mistral-small-3.1-24b-instruct": {
|
|
id: "@cf/mistralai/mistral-small-3.1-24b-instruct",
|
|
name: "Mistral Small 3.1 24B Instruct",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.351,
|
|
output: 0.555,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/moonshotai/kimi-k2.6": {
|
|
id: "@cf/moonshotai/kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/moonshotai/kimi-k2.7-code": {
|
|
id: "@cf/moonshotai/kimi-k2.7-code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/nvidia/nemotron-3-120b-a12b": {
|
|
id: "@cf/nvidia/nemotron-3-120b-a12b",
|
|
name: "Nemotron 3 Super 120B",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/openai/gpt-oss-120b": {
|
|
id: "@cf/openai/gpt-oss-120b",
|
|
name: "GPT OSS 120B",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.35,
|
|
output: 0.75,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/openai/gpt-oss-20b": {
|
|
id: "@cf/openai/gpt-oss-20b",
|
|
name: "GPT OSS 20B",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/qwen/qwen3-30b-a3b-fp8": {
|
|
id: "@cf/qwen/qwen3-30b-a3b-fp8",
|
|
name: "Qwen3 30B A3b fp8",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.0509,
|
|
output: 0.335,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/zai-org/glm-4.7-flash": {
|
|
id: "@cf/zai-org/glm-4.7-flash",
|
|
name: "GLM-4.7-Flash",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.0605,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"@cf/zai-org/glm-5.2": {
|
|
id: "@cf/zai-org/glm-5.2",
|
|
name: "Glm 5.2",
|
|
api: "openai-completions",
|
|
provider: "cloudflare-workers-ai",
|
|
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
|
|
compat: {"sendSessionAffinityHeaders":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"deepseek": {
|
|
"deepseek-v4-flash": {
|
|
id: "deepseek-v4-flash",
|
|
name: "DeepSeek V4 Flash",
|
|
api: "openai-completions",
|
|
provider: "deepseek",
|
|
baseUrl: "https://api.deepseek.com",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.0028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-v4-pro": {
|
|
id: "deepseek-v4-pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "openai-completions",
|
|
provider: "deepseek",
|
|
baseUrl: "https://api.deepseek.com",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.435,
|
|
output: 0.87,
|
|
cacheRead: 0.003625,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"fireworks": {
|
|
"accounts/fireworks/models/deepseek-v4-flash": {
|
|
id: "accounts/fireworks/models/deepseek-v4-flash",
|
|
name: "DeepSeek V4 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/deepseek-v4-pro": {
|
|
id: "accounts/fireworks/models/deepseek-v4-pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.74,
|
|
output: 3.48,
|
|
cacheRead: 0.145,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/glm-5p1": {
|
|
id: "accounts/fireworks/models/glm-5p1",
|
|
name: "GLM 5.1",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/glm-5p2": {
|
|
id: "accounts/fireworks/models/glm-5p2",
|
|
name: "GLM 5.2",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/gpt-oss-120b": {
|
|
id: "accounts/fireworks/models/gpt-oss-120b",
|
|
name: "GPT OSS 120B",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/gpt-oss-20b": {
|
|
id: "accounts/fireworks/models/gpt-oss-20b",
|
|
name: "GPT OSS 20B",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.07,
|
|
output: 0.3,
|
|
cacheRead: 0.035,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/kimi-k2p6": {
|
|
id: "accounts/fireworks/models/kimi-k2p6",
|
|
name: "Kimi K2.6",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/kimi-k2p7-code": {
|
|
id: "accounts/fireworks/models/kimi-k2p7-code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/minimax-m2p7": {
|
|
id: "accounts/fireworks/models/minimax-m2p7",
|
|
name: "MiniMax-M2.7",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 196608,
|
|
maxTokens: 196608,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/minimax-m3": {
|
|
id: "accounts/fireworks/models/minimax-m3",
|
|
name: "MiniMax-M3",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 512000,
|
|
maxTokens: 512000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/models/qwen3p7-plus": {
|
|
id: "accounts/fireworks/models/qwen3p7-plus",
|
|
name: "Qwen 3.7 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/routers/glm-5p1-fast": {
|
|
id: "accounts/fireworks/routers/glm-5p1-fast",
|
|
name: "GLM 5.1 Fast",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.8,
|
|
output: 8.8,
|
|
cacheRead: 0.52,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/routers/kimi-k2p6-fast": {
|
|
id: "accounts/fireworks/routers/kimi-k2p6-fast",
|
|
name: "Kimi K2.6 Fast",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/routers/kimi-k2p6-turbo": {
|
|
id: "accounts/fireworks/routers/kimi-k2p6-turbo",
|
|
name: "Kimi K2.6 Turbo",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"accounts/fireworks/routers/kimi-k2p7-code-fast": {
|
|
id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
|
|
name: "Kimi K2.7 Code Fast",
|
|
api: "anthropic-messages",
|
|
provider: "fireworks",
|
|
baseUrl: "https://api.fireworks.ai/inference",
|
|
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.9,
|
|
output: 8,
|
|
cacheRead: 0.38,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"github-copilot": {
|
|
"claude-fable-5": {
|
|
id: "claude-fable-5",
|
|
name: "Claude Fable 5",
|
|
api: "openai-completions",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"claude-haiku-4.5": {
|
|
id: "claude-haiku-4.5",
|
|
name: "Claude Haiku 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsEagerToolInputStreaming":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4.5": {
|
|
id: "claude-opus-4.5",
|
|
name: "Claude Opus 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4.6": {
|
|
id: "claude-opus-4.6",
|
|
name: "Claude Opus 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4.7": {
|
|
id: "claude-opus-4.7",
|
|
name: "Claude Opus 4.7",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4.8": {
|
|
id: "claude-opus-4.8",
|
|
name: "Claude Opus 4.8",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4": {
|
|
id: "claude-sonnet-4",
|
|
name: "Claude Sonnet 4 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsEagerToolInputStreaming":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 216000,
|
|
maxTokens: 16000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4.5": {
|
|
id: "claude-sonnet-4.5",
|
|
name: "Claude Sonnet 4.5 (latest)",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsEagerToolInputStreaming":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4.6": {
|
|
id: "claude-sonnet-4.6",
|
|
name: "Claude Sonnet 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":"low","xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"gemini-2.5-pro": {
|
|
id: "gemini-2.5-pro",
|
|
name: "Gemini 2.5 Pro",
|
|
api: "openai-completions",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"gemini-3-flash-preview": {
|
|
id: "gemini-3-flash-preview",
|
|
name: "Gemini 3 Flash Preview",
|
|
api: "openai-completions",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"gemini-3.1-pro-preview": {
|
|
id: "gemini-3.1-pro-preview",
|
|
name: "Gemini 3.1 Pro Preview",
|
|
api: "openai-completions",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"gemini-3.5-flash": {
|
|
id: "gemini-3.5-flash",
|
|
name: "Gemini 3.5 Flash",
|
|
api: "openai-completions",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"gpt-4.1": {
|
|
id: "gpt-4.1",
|
|
name: "GPT-4.1",
|
|
api: "openai-completions",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"gpt-5-mini": {
|
|
id: "gpt-5-mini",
|
|
name: "GPT-5 Mini",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 264000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2": {
|
|
id: "gpt-5.2",
|
|
name: "GPT-5.2",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2-codex": {
|
|
id: "gpt-5.2-codex",
|
|
name: "GPT-5.2 Codex",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.3-codex": {
|
|
id: "gpt-5.3-codex",
|
|
name: "GPT-5.3 Codex",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4": {
|
|
id: "gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-mini": {
|
|
id: "gpt-5.4-mini",
|
|
name: "GPT-5.4 mini",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-nano": {
|
|
id: "gpt-5.4-nano",
|
|
name: "GPT-5.4 nano",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.25,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.5": {
|
|
id: "gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "openai-responses",
|
|
provider: "github-copilot",
|
|
baseUrl: "https://api.individual.githubcopilot.com",
|
|
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
},
|
|
"google": {
|
|
"gemini-2.0-flash": {
|
|
id: "gemini-2.0-flash",
|
|
name: "Gemini 2.0 Flash",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-2.0-flash-lite": {
|
|
id: "gemini-2.0-flash-lite",
|
|
name: "Gemini 2.0 Flash-Lite",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-2.5-flash": {
|
|
id: "gemini-2.5-flash",
|
|
name: "Gemini 2.5 Flash",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2.5,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-2.5-flash-lite": {
|
|
id: "gemini-2.5-flash-lite",
|
|
name: "Gemini 2.5 Flash-Lite",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-2.5-pro": {
|
|
id: "gemini-2.5-pro",
|
|
name: "Gemini 2.5 Pro",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3-flash-preview": {
|
|
id: "gemini-3-flash-preview",
|
|
name: "Gemini 3 Flash Preview",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3-pro-preview": {
|
|
id: "gemini-3-pro-preview",
|
|
name: "Gemini 3 Pro Preview",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.1-flash-lite": {
|
|
id: "gemini-3.1-flash-lite",
|
|
name: "Gemini 3.1 Flash Lite",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.1-flash-lite-preview": {
|
|
id: "gemini-3.1-flash-lite-preview",
|
|
name: "Gemini 3.1 Flash Lite Preview",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.1-pro-preview": {
|
|
id: "gemini-3.1-pro-preview",
|
|
name: "Gemini 3.1 Pro Preview",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.1-pro-preview-customtools": {
|
|
id: "gemini-3.1-pro-preview-customtools",
|
|
name: "Gemini 3.1 Pro Preview Custom Tools",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.5-flash": {
|
|
id: "gemini-3.5-flash",
|
|
name: "Gemini 3.5 Flash",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-flash-latest": {
|
|
id: "gemini-flash-latest",
|
|
name: "Gemini Flash Latest",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-flash-lite-latest": {
|
|
id: "gemini-flash-lite-latest",
|
|
name: "Gemini Flash-Lite Latest",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemma-4-26b-a4b-it": {
|
|
id: "gemma-4-26b-a4b-it",
|
|
name: "Gemma 4 26B A4B IT",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemma-4-31b-it": {
|
|
id: "gemma-4-31b-it",
|
|
name: "Gemma 4 31B IT",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemma-4-E2B-it": {
|
|
id: "gemma-4-E2B-it",
|
|
name: "Gemma 4 E2B IT",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemma-4-E4B-it": {
|
|
id: "gemma-4-E4B-it",
|
|
name: "Gemma 4 E4B IT",
|
|
api: "google-generative-ai",
|
|
provider: "google",
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"google-generative-ai">,
|
|
},
|
|
"google-vertex": {
|
|
"gemini-2.5-flash": {
|
|
id: "gemini-2.5-flash",
|
|
name: "Gemini 2.5 Flash",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2.5,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-2.5-flash-lite": {
|
|
id: "gemini-2.5-flash-lite",
|
|
name: "Gemini 2.5 Flash-Lite",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-2.5-pro": {
|
|
id: "gemini-2.5-pro",
|
|
name: "Gemini 2.5 Pro",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-3-flash-preview": {
|
|
id: "gemini-3-flash-preview",
|
|
name: "Gemini 3 Flash Preview",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-3.1-flash-lite": {
|
|
id: "gemini-3.1-flash-lite",
|
|
name: "Gemini 3.1 Flash Lite",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-3.1-pro-preview": {
|
|
id: "gemini-3.1-pro-preview",
|
|
name: "Gemini 3.1 Pro Preview",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-3.1-pro-preview-customtools": {
|
|
id: "gemini-3.1-pro-preview-customtools",
|
|
name: "Gemini 3.1 Pro Preview Custom Tools",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-3.5-flash": {
|
|
id: "gemini-3.5-flash",
|
|
name: "Gemini 3.5 Flash",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-flash-latest": {
|
|
id: "gemini-flash-latest",
|
|
name: "Gemini Flash Latest",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
"gemini-flash-lite-latest": {
|
|
id: "gemini-flash-lite-latest",
|
|
name: "Gemini Flash-Lite Latest",
|
|
api: "google-vertex",
|
|
provider: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-vertex">,
|
|
},
|
|
"groq": {
|
|
"llama-3.1-8b-instant": {
|
|
id: "llama-3.1-8b-instant",
|
|
name: "Llama 3.1 8B",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.08,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"llama-3.3-70b-versatile": {
|
|
id: "llama-3.3-70b-versatile",
|
|
name: "Llama 3.3 70B",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.59,
|
|
output: 0.79,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/llama-4-scout-17b-16e-instruct": {
|
|
id: "meta-llama/llama-4-scout-17b-16e-instruct",
|
|
name: "Llama 4 Scout 17B 16E",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.11,
|
|
output: 0.34,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-120b": {
|
|
id: "openai/gpt-oss-120b",
|
|
name: "GPT OSS 120B",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-20b": {
|
|
id: "openai/gpt-oss-20b",
|
|
name: "GPT OSS 20B",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.3,
|
|
cacheRead: 0.0375,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-safeguard-20b": {
|
|
id: "openai/gpt-oss-safeguard-20b",
|
|
name: "Safety GPT OSS 20B",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.3,
|
|
cacheRead: 0.037,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-32b": {
|
|
id: "qwen/qwen3-32b",
|
|
name: "Qwen3-32B",
|
|
api: "openai-completions",
|
|
provider: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"default"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.29,
|
|
output: 0.59,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 40960,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"huggingface": {
|
|
"MiniMaxAI/MiniMax-M2.1": {
|
|
id: "MiniMaxAI/MiniMax-M2.1",
|
|
name: "MiniMax-M2.1",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"MiniMaxAI/MiniMax-M2.5": {
|
|
id: "MiniMaxAI/MiniMax-M2.5",
|
|
name: "MiniMax-M2.5",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"MiniMaxAI/MiniMax-M2.7": {
|
|
id: "MiniMaxAI/MiniMax-M2.7",
|
|
name: "MiniMax-M2.7",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3-235B-A22B-Thinking-2507": {
|
|
id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
|
|
name: "Qwen3-235B-A22B-Thinking-2507",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
|
|
id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
|
name: "Qwen3-Coder-480B-A35B-Instruct",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 66536,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3-Coder-Next": {
|
|
id: "Qwen/Qwen3-Coder-Next",
|
|
name: "Qwen3-Coder-Next",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
|
|
id: "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
|
name: "Qwen3-Next-80B-A3B-Instruct",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 66536,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3-Next-80B-A3B-Thinking": {
|
|
id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
|
|
name: "Qwen3-Next-80B-A3B-Thinking",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3.5-397B-A17B": {
|
|
id: "Qwen/Qwen3.5-397B-A17B",
|
|
name: "Qwen3.5-397B-A17B",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"XiaomiMiMo/MiMo-V2-Flash": {
|
|
id: "XiaomiMiMo/MiMo-V2-Flash",
|
|
name: "MiMo-V2-Flash",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-ai/DeepSeek-R1-0528": {
|
|
id: "deepseek-ai/DeepSeek-R1-0528",
|
|
name: "DeepSeek-R1-0528",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 3,
|
|
output: 5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 163840,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-ai/DeepSeek-V3.2": {
|
|
id: "deepseek-ai/DeepSeek-V3.2",
|
|
name: "DeepSeek-V3.2",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.28,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-ai/DeepSeek-V4-Pro": {
|
|
id: "deepseek-ai/DeepSeek-V4-Pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.435,
|
|
output: 0.87,
|
|
cacheRead: 0.003625,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 393216,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2-Instruct": {
|
|
id: "moonshotai/Kimi-K2-Instruct",
|
|
name: "Kimi-K2-Instruct",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2-Instruct-0905": {
|
|
id: "moonshotai/Kimi-K2-Instruct-0905",
|
|
name: "Kimi-K2-Instruct-0905",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2-Thinking": {
|
|
id: "moonshotai/Kimi-K2-Thinking",
|
|
name: "Kimi-K2-Thinking",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2.5": {
|
|
id: "moonshotai/Kimi-K2.5",
|
|
name: "Kimi-K2.5",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2.6": {
|
|
id: "moonshotai/Kimi-K2.6",
|
|
name: "Kimi-K2.6",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"zai-org/GLM-4.7": {
|
|
id: "zai-org/GLM-4.7",
|
|
name: "GLM-4.7",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.2,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"zai-org/GLM-4.7-Flash": {
|
|
id: "zai-org/GLM-4.7-Flash",
|
|
name: "GLM-4.7-Flash",
|
|
api: "openai-completions",
|
|
provider: "huggingface",
|
|
baseUrl: "https://router.huggingface.co/v1",
|
|
compat: {"supportsDeveloperRole":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"zai-org/GLM-5": {
|
|
id: "zai-org/GLM-5",
|
|
name: "GLM-5",
|
|
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">,
|
|
"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": {
|
|
"k2p7": {
|
|
id: "k2p7",
|
|
name: "Kimi K2.7 Code",
|
|
api: "anthropic-messages",
|
|
provider: "kimi-coding",
|
|
baseUrl: "https://api.kimi.com/coding",
|
|
headers: {"User-Agent":"KimiCLI/1.5"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"kimi-for-coding": {
|
|
id: "kimi-for-coding",
|
|
name: "Kimi For Coding",
|
|
api: "anthropic-messages",
|
|
provider: "kimi-coding",
|
|
baseUrl: "https://api.kimi.com/coding",
|
|
headers: {"User-Agent":"KimiCLI/1.5"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"kimi-k2-thinking": {
|
|
id: "kimi-k2-thinking",
|
|
name: "Kimi K2 Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "kimi-coding",
|
|
baseUrl: "https://api.kimi.com/coding",
|
|
headers: {"User-Agent":"KimiCLI/1.5"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"minimax": {
|
|
"MiniMax-M2.7": {
|
|
id: "MiniMax-M2.7",
|
|
name: "MiniMax-M2.7",
|
|
api: "anthropic-messages",
|
|
provider: "minimax",
|
|
baseUrl: "https://api.minimax.io/anthropic",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"MiniMax-M2.7-highspeed": {
|
|
id: "MiniMax-M2.7-highspeed",
|
|
name: "MiniMax-M2.7-highspeed",
|
|
api: "anthropic-messages",
|
|
provider: "minimax",
|
|
baseUrl: "https://api.minimax.io/anthropic",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"MiniMax-M3": {
|
|
id: "MiniMax-M3",
|
|
name: "MiniMax-M3",
|
|
api: "anthropic-messages",
|
|
provider: "minimax",
|
|
baseUrl: "https://api.minimax.io/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.12,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 512000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"minimax-cn": {
|
|
"MiniMax-M2.7": {
|
|
id: "MiniMax-M2.7",
|
|
name: "MiniMax-M2.7",
|
|
api: "anthropic-messages",
|
|
provider: "minimax-cn",
|
|
baseUrl: "https://api.minimaxi.com/anthropic",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"MiniMax-M2.7-highspeed": {
|
|
id: "MiniMax-M2.7-highspeed",
|
|
name: "MiniMax-M2.7-highspeed",
|
|
api: "anthropic-messages",
|
|
provider: "minimax-cn",
|
|
baseUrl: "https://api.minimaxi.com/anthropic",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"MiniMax-M3": {
|
|
id: "MiniMax-M3",
|
|
name: "MiniMax-M3",
|
|
api: "anthropic-messages",
|
|
provider: "minimax-cn",
|
|
baseUrl: "https://api.minimaxi.com/anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.12,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 512000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"mistral": {
|
|
"codestral-latest": {
|
|
id: "codestral-latest",
|
|
name: "Codestral (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 0.9,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"devstral-2512": {
|
|
id: "devstral-2512",
|
|
name: "Devstral 2",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"devstral-latest": {
|
|
id: "devstral-latest",
|
|
name: "Devstral 2",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"devstral-medium-2507": {
|
|
id: "devstral-medium-2507",
|
|
name: "Devstral Medium",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"devstral-medium-latest": {
|
|
id: "devstral-medium-latest",
|
|
name: "Devstral 2 (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"devstral-small-2505": {
|
|
id: "devstral-small-2505",
|
|
name: "Devstral Small 2505",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"devstral-small-2507": {
|
|
id: "devstral-small-2507",
|
|
name: "Devstral Small",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"labs-devstral-small-2512": {
|
|
id: "labs-devstral-small-2512",
|
|
name: "Devstral Small 2",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"magistral-medium-latest": {
|
|
id: "magistral-medium-latest",
|
|
name: "Magistral Medium (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"magistral-small": {
|
|
id: "magistral-small",
|
|
name: "Magistral Small",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"ministral-3b-latest": {
|
|
id: "ministral-3b-latest",
|
|
name: "Ministral 3B (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.04,
|
|
output: 0.04,
|
|
cacheRead: 0.004,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"ministral-8b-latest": {
|
|
id: "ministral-8b-latest",
|
|
name: "Ministral 8B (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.1,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-large-2411": {
|
|
id: "mistral-large-2411",
|
|
name: "Mistral Large 2.1",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-large-2512": {
|
|
id: "mistral-large-2512",
|
|
name: "Mistral Large 3",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-large-latest": {
|
|
id: "mistral-large-latest",
|
|
name: "Mistral Large (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-medium-2505": {
|
|
id: "mistral-medium-2505",
|
|
name: "Mistral Medium 3",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-medium-2508": {
|
|
id: "mistral-medium-2508",
|
|
name: "Mistral Medium 3.1",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-medium-2604": {
|
|
id: "mistral-medium-2604",
|
|
name: "Mistral Medium 3.5",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 7.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-medium-3.5": {
|
|
id: "mistral-medium-3.5",
|
|
name: "Mistral Medium 3.5",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 7.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-medium-latest": {
|
|
id: "mistral-medium-latest",
|
|
name: "Mistral Medium (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-nemo": {
|
|
id: "mistral-nemo",
|
|
name: "Mistral Nemo",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-small-2506": {
|
|
id: "mistral-small-2506",
|
|
name: "Mistral Small 3.2",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-small-2603": {
|
|
id: "mistral-small-2603",
|
|
name: "Mistral Small 4",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"mistral-small-latest": {
|
|
id: "mistral-small-latest",
|
|
name: "Mistral Small (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"open-mistral-7b": {
|
|
id: "open-mistral-7b",
|
|
name: "Mistral 7B",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 0.25,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 8000,
|
|
maxTokens: 8000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"open-mistral-nemo": {
|
|
id: "open-mistral-nemo",
|
|
name: "Open Mistral Nemo",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"open-mixtral-8x22b": {
|
|
id: "open-mixtral-8x22b",
|
|
name: "Mixtral 8x22B",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 64000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"open-mixtral-8x7b": {
|
|
id: "open-mixtral-8x7b",
|
|
name: "Mixtral 8x7B",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.7,
|
|
output: 0.7,
|
|
cacheRead: 0.07,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"pixtral-12b": {
|
|
id: "pixtral-12b",
|
|
name: "Pixtral 12B",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
"pixtral-large-latest": {
|
|
id: "pixtral-large-latest",
|
|
name: "Pixtral Large (latest)",
|
|
api: "mistral-conversations",
|
|
provider: "mistral",
|
|
baseUrl: "https://api.mistral.ai",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"mistral-conversations">,
|
|
},
|
|
"moonshotai": {
|
|
"kimi-k2-0711-preview": {
|
|
id: "kimi-k2-0711-preview",
|
|
name: "Kimi K2 0711",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-0905-preview": {
|
|
id: "kimi-k2-0905-preview",
|
|
name: "Kimi K2 0905",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-thinking": {
|
|
id: "kimi-k2-thinking",
|
|
name: "Kimi K2 Thinking",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-thinking-turbo": {
|
|
id: "kimi-k2-thinking-turbo",
|
|
name: "Kimi K2 Thinking Turbo",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.15,
|
|
output: 8,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-turbo-preview": {
|
|
id: "kimi-k2-turbo-preview",
|
|
name: "Kimi K2 Turbo",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.4,
|
|
output: 10,
|
|
cacheRead: 0.6,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.5": {
|
|
id: "kimi-k2.5",
|
|
name: "Kimi K2.5",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.6": {
|
|
id: "kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.7-code": {
|
|
id: "kimi-k2.7-code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.7-code-highspeed": {
|
|
id: "kimi-k2.7-code-highspeed",
|
|
name: "Kimi K2.7 Code HighSpeed",
|
|
api: "openai-completions",
|
|
provider: "moonshotai",
|
|
baseUrl: "https://api.moonshot.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.9,
|
|
output: 8,
|
|
cacheRead: 0.38,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"moonshotai-cn": {
|
|
"kimi-k2-0711-preview": {
|
|
id: "kimi-k2-0711-preview",
|
|
name: "Kimi K2 0711",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-0905-preview": {
|
|
id: "kimi-k2-0905-preview",
|
|
name: "Kimi K2 0905",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-thinking": {
|
|
id: "kimi-k2-thinking",
|
|
name: "Kimi K2 Thinking",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-thinking-turbo": {
|
|
id: "kimi-k2-thinking-turbo",
|
|
name: "Kimi K2 Thinking Turbo",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.15,
|
|
output: 8,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2-turbo-preview": {
|
|
id: "kimi-k2-turbo-preview",
|
|
name: "Kimi K2 Turbo",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.4,
|
|
output: 10,
|
|
cacheRead: 0.6,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.5": {
|
|
id: "kimi-k2.5",
|
|
name: "Kimi K2.5",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.6": {
|
|
id: "kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.7-code": {
|
|
id: "kimi-k2.7-code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.7-code-highspeed": {
|
|
id: "kimi-k2.7-code-highspeed",
|
|
name: "Kimi K2.7 Code HighSpeed",
|
|
api: "openai-completions",
|
|
provider: "moonshotai-cn",
|
|
baseUrl: "https://api.moonshot.cn/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.9,
|
|
output: 8,
|
|
cacheRead: 0.38,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"nvidia": {
|
|
"meta/llama-3.1-70b-instruct": {
|
|
id: "meta/llama-3.1-70b-instruct",
|
|
name: "Llama 3.1 70b Instruct",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta/llama-3.1-8b-instruct": {
|
|
id: "meta/llama-3.1-8b-instruct",
|
|
name: "Llama 3.1 8B Instruct",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 16000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta/llama-3.2-11b-vision-instruct": {
|
|
id: "meta/llama-3.2-11b-vision-instruct",
|
|
name: "Llama 3.2 11b Vision Instruct",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta/llama-3.2-90b-vision-instruct": {
|
|
id: "meta/llama-3.2-90b-vision-instruct",
|
|
name: "Llama-3.2-90B-Vision-Instruct",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta/llama-3.3-70b-instruct": {
|
|
id: "meta/llama-3.3-70b-instruct",
|
|
name: "Llama 3.3 70b Instruct",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-large-3-675b-instruct-2512": {
|
|
id: "mistralai/mistral-large-3-675b-instruct-2512",
|
|
name: "Mistral Large 3 675B Instruct 2512",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-small-4-119b-2603": {
|
|
id: "mistralai/mistral-small-4-119b-2603",
|
|
name: "mistral-small-4-119b-2603",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2.6": {
|
|
id: "moonshotai/kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-nano-30b-a3b": {
|
|
id: "nvidia/nemotron-3-nano-30b-a3b",
|
|
name: "nemotron-3-nano-30b-a3b",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
|
|
id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
|
|
name: "Nemotron 3 Nano Omni",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-super-120b-a12b": {
|
|
id: "nvidia/nemotron-3-super-120b-a12b",
|
|
name: "Nemotron 3 Super",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.8,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-ultra-550b-a55b": {
|
|
id: "nvidia/nemotron-3-ultra-550b-a55b",
|
|
name: "Nemotron 3 Ultra 550B A55B",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nvidia-nemotron-nano-9b-v2": {
|
|
id: "nvidia/nvidia-nemotron-nano-9b-v2",
|
|
name: "nvidia-nemotron-nano-9b-v2",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-120b": {
|
|
id: "openai/gpt-oss-120b",
|
|
name: "GPT-OSS-120B",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-20b": {
|
|
id: "openai/gpt-oss-20b",
|
|
name: "GPT OSS 20B",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-122b-a10b": {
|
|
id: "qwen/qwen3.5-122b-a10b",
|
|
name: "Qwen3.5 122B-A10B",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"stepfun-ai/step-3.5-flash": {
|
|
id: "stepfun-ai/step-3.5-flash",
|
|
name: "Step 3.5 Flash",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"stepfun-ai/step-3.7-flash": {
|
|
id: "stepfun-ai/step-3.7-flash",
|
|
name: "Step 3.7 Flash",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-5.1": {
|
|
id: "z-ai/glm-5.1",
|
|
name: "GLM-5.1",
|
|
api: "openai-completions",
|
|
provider: "nvidia",
|
|
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
headers: {"NVCF-POLL-SECONDS":"3600"},
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"openai": {
|
|
"gpt-4": {
|
|
id: "gpt-4",
|
|
name: "GPT-4",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 30,
|
|
output: 60,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 8192,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4-turbo": {
|
|
id: "gpt-4-turbo",
|
|
name: "GPT-4 Turbo",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 30,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4.1": {
|
|
id: "gpt-4.1",
|
|
name: "GPT-4.1",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4.1-mini": {
|
|
id: "gpt-4.1-mini",
|
|
name: "GPT-4.1 mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4.1-nano": {
|
|
id: "gpt-4.1-nano",
|
|
name: "GPT-4.1 nano",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o": {
|
|
id: "gpt-4o",
|
|
name: "GPT-4o",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o-2024-05-13": {
|
|
id: "gpt-4o-2024-05-13",
|
|
name: "GPT-4o (2024-05-13)",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o-2024-08-06": {
|
|
id: "gpt-4o-2024-08-06",
|
|
name: "GPT-4o (2024-08-06)",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o-2024-11-20": {
|
|
id: "gpt-4o-2024-11-20",
|
|
name: "GPT-4o (2024-11-20)",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-4o-mini": {
|
|
id: "gpt-4o-mini",
|
|
name: "GPT-4o mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5": {
|
|
id: "gpt-5",
|
|
name: "GPT-5",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-chat-latest": {
|
|
id: "gpt-5-chat-latest",
|
|
name: "GPT-5 Chat Latest",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-codex": {
|
|
id: "gpt-5-codex",
|
|
name: "GPT-5-Codex",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-mini": {
|
|
id: "gpt-5-mini",
|
|
name: "GPT-5 Mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-nano": {
|
|
id: "gpt-5-nano",
|
|
name: "GPT-5 Nano",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.4,
|
|
cacheRead: 0.005,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-pro": {
|
|
id: "gpt-5-pro",
|
|
name: "GPT-5 Pro",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 120,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1": {
|
|
id: "gpt-5.1",
|
|
name: "GPT-5.1",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-chat-latest": {
|
|
id: "gpt-5.1-chat-latest",
|
|
name: "GPT-5.1 Chat",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex": {
|
|
id: "gpt-5.1-codex",
|
|
name: "GPT-5.1 Codex",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex-max": {
|
|
id: "gpt-5.1-codex-max",
|
|
name: "GPT-5.1 Codex Max",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex-mini": {
|
|
id: "gpt-5.1-codex-mini",
|
|
name: "GPT-5.1 Codex mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2": {
|
|
id: "gpt-5.2",
|
|
name: "GPT-5.2",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2-chat-latest": {
|
|
id: "gpt-5.2-chat-latest",
|
|
name: "GPT-5.2 Chat",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2-codex": {
|
|
id: "gpt-5.2-codex",
|
|
name: "GPT-5.2 Codex",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2-pro": {
|
|
id: "gpt-5.2-pro",
|
|
name: "GPT-5.2 Pro",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 21,
|
|
output: 168,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.3-chat-latest": {
|
|
id: "gpt-5.3-chat-latest",
|
|
name: "GPT-5.3 Chat (latest)",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: false,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.3-codex": {
|
|
id: "gpt-5.3-codex",
|
|
name: "GPT-5.3 Codex",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.3-codex-spark": {
|
|
id: "gpt-5.3-codex-spark",
|
|
name: "GPT-5.3 Codex Spark",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4": {
|
|
id: "gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-mini": {
|
|
id: "gpt-5.4-mini",
|
|
name: "GPT-5.4 mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-nano": {
|
|
id: "gpt-5.4-nano",
|
|
name: "GPT-5.4 nano",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none","xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.25,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-pro": {
|
|
id: "gpt-5.4-pro",
|
|
name: "GPT-5.4 Pro",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.5": {
|
|
id: "gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.5-pro": {
|
|
id: "gpt-5.5-pro",
|
|
name: "GPT-5.5 Pro",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"low":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o1": {
|
|
id: "o1",
|
|
name: "o1",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 60,
|
|
cacheRead: 7.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o1-pro": {
|
|
id: "o1-pro",
|
|
name: "o1-pro",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 150,
|
|
output: 600,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3": {
|
|
id: "o3",
|
|
name: "o3",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3-deep-research": {
|
|
id: "o3-deep-research",
|
|
name: "o3-deep-research",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 40,
|
|
cacheRead: 2.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3-mini": {
|
|
id: "o3-mini",
|
|
name: "o3-mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o3-pro": {
|
|
id: "o3-pro",
|
|
name: "o3-pro",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 20,
|
|
output: 80,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o4-mini": {
|
|
id: "o4-mini",
|
|
name: "o4-mini",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.275,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
"o4-mini-deep-research": {
|
|
id: "o4-mini-deep-research",
|
|
name: "o4-mini-deep-research",
|
|
api: "openai-responses",
|
|
provider: "openai",
|
|
baseUrl: "https://api.openai.com/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-responses">,
|
|
},
|
|
"openai-codex": {
|
|
"gpt-5.3-codex-spark": {
|
|
id: "gpt-5.3-codex-spark",
|
|
name: "GPT-5.3 Codex Spark",
|
|
api: "openai-codex-responses",
|
|
provider: "openai-codex",
|
|
baseUrl: "https://chatgpt.com/backend-api",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-codex-responses">,
|
|
"gpt-5.4": {
|
|
id: "gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "openai-codex-responses",
|
|
provider: "openai-codex",
|
|
baseUrl: "https://chatgpt.com/backend-api",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-codex-responses">,
|
|
"gpt-5.4-mini": {
|
|
id: "gpt-5.4-mini",
|
|
name: "GPT-5.4 mini",
|
|
api: "openai-codex-responses",
|
|
provider: "openai-codex",
|
|
baseUrl: "https://chatgpt.com/backend-api",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-codex-responses">,
|
|
"gpt-5.5": {
|
|
id: "gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "openai-codex-responses",
|
|
provider: "openai-codex",
|
|
baseUrl: "https://chatgpt.com/backend-api",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-codex-responses">,
|
|
},
|
|
"opencode": {
|
|
"big-pickle": {
|
|
id: "big-pickle",
|
|
name: "Big Pickle",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"claude-haiku-4-5": {
|
|
id: "claude-haiku-4-5",
|
|
name: "Claude Haiku 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-1": {
|
|
id: "claude-opus-4-1",
|
|
name: "Claude Opus 4.1",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-5": {
|
|
id: "claude-opus-4-5",
|
|
name: "Claude Opus 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-6": {
|
|
id: "claude-opus-4-6",
|
|
name: "Claude Opus 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-7": {
|
|
id: "claude-opus-4-7",
|
|
name: "Claude Opus 4.7",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-opus-4-8": {
|
|
id: "claude-opus-4-8",
|
|
name: "Claude Opus 4.8",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4": {
|
|
id: "claude-sonnet-4",
|
|
name: "Claude Sonnet 4",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-5": {
|
|
id: "claude-sonnet-4-5",
|
|
name: "Claude Sonnet 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"claude-sonnet-4-6": {
|
|
id: "claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek-v4-flash": {
|
|
id: "deepseek-v4-flash",
|
|
name: "DeepSeek V4 Flash",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-v4-flash-free": {
|
|
id: "deepseek-v4-flash-free",
|
|
name: "DeepSeek V4 Flash Free",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-v4-pro": {
|
|
id: "deepseek-v4-pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.74,
|
|
output: 3.84,
|
|
cacheRead: 0.145,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
"gemini-3-flash": {
|
|
id: "gemini-3-flash",
|
|
name: "Gemini 3 Flash",
|
|
api: "google-generative-ai",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.1-pro": {
|
|
id: "gemini-3.1-pro",
|
|
name: "Gemini 3.1 Pro Preview",
|
|
api: "google-generative-ai",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"gemini-3.5-flash": {
|
|
id: "gemini-3.5-flash",
|
|
name: "Gemini 3.5 Flash",
|
|
api: "google-generative-ai",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"google-generative-ai">,
|
|
"glm-5": {
|
|
id: "glm-5",
|
|
name: "GLM-5",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3.2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
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",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.07,
|
|
output: 8.5,
|
|
cacheRead: 0.107,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-codex": {
|
|
id: "gpt-5-codex",
|
|
name: "GPT-5 Codex",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.07,
|
|
output: 8.5,
|
|
cacheRead: 0.107,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5-nano": {
|
|
id: "gpt-5-nano",
|
|
name: "GPT-5 Nano",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.4,
|
|
cacheRead: 0.005,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1": {
|
|
id: "gpt-5.1",
|
|
name: "GPT-5.1",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.07,
|
|
output: 8.5,
|
|
cacheRead: 0.107,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex": {
|
|
id: "gpt-5.1-codex",
|
|
name: "GPT-5.1 Codex",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.07,
|
|
output: 8.5,
|
|
cacheRead: 0.107,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex-max": {
|
|
id: "gpt-5.1-codex-max",
|
|
name: "GPT-5.1 Codex Max",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.1-codex-mini": {
|
|
id: "gpt-5.1-codex-mini",
|
|
name: "GPT-5.1 Codex Mini",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2": {
|
|
id: "gpt-5.2",
|
|
name: "GPT-5.2",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.2-codex": {
|
|
id: "gpt-5.2-codex",
|
|
name: "GPT-5.2 Codex",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.3-codex": {
|
|
id: "gpt-5.3-codex",
|
|
name: "GPT-5.3 Codex",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4": {
|
|
id: "gpt-5.4",
|
|
name: "GPT-5.4",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 272000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-mini": {
|
|
id: "gpt-5.4-mini",
|
|
name: "GPT-5.4 Mini",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-nano": {
|
|
id: "gpt-5.4-nano",
|
|
name: "GPT-5.4 Nano",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.25,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.4-pro": {
|
|
id: "gpt-5.4-pro",
|
|
name: "GPT-5.4 Pro",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 30,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.5": {
|
|
id: "gpt-5.5",
|
|
name: "GPT-5.5",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"gpt-5.5-pro": {
|
|
id: "gpt-5.5-pro",
|
|
name: "GPT-5.5 Pro",
|
|
api: "openai-responses",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"low":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 30,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-responses">,
|
|
"grok-build-0.1": {
|
|
id: "grok-build-0.1",
|
|
name: "Grok Build 0.1",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"supportsReasoningEffort":false,"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.5": {
|
|
id: "kimi-k2.5",
|
|
name: "Kimi K2.5",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.6": {
|
|
id: "kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-free": {
|
|
id: "mimo-v2.5-free",
|
|
name: "MiMo V2.5 Free",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax-m2.5": {
|
|
id: "minimax-m2.5",
|
|
name: "MiniMax M2.5",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax-m2.7": {
|
|
id: "minimax-m2.7",
|
|
name: "MiniMax M2.7",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"nemotron-3-ultra-free": {
|
|
id: "nemotron-3-ultra-free",
|
|
name: "Nemotron 3 Ultra Free",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"north-mini-code-free": {
|
|
id: "north-mini-code-free",
|
|
name: "North Mini Code Free",
|
|
api: "openai-completions",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen3.5-plus": {
|
|
id: "qwen3.5-plus",
|
|
name: "Qwen3.5 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.2,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0.25,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"qwen3.6-plus": {
|
|
id: "qwen3.6-plus",
|
|
name: "Qwen3.6 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "opencode",
|
|
baseUrl: "https://opencode.ai/zen",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0.625,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"opencode-go": {
|
|
"deepseek-v4-flash": {
|
|
id: "deepseek-v4-flash",
|
|
name: "DeepSeek V4 Flash",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.0028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-v4-pro": {
|
|
id: "deepseek-v4-pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.74,
|
|
output: 3.48,
|
|
cacheRead: 0.0145,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} 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",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5.2": {
|
|
id: "glm-5.2",
|
|
name: "GLM-5.2",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.6": {
|
|
id: "kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"kimi-k2.7-code": {
|
|
id: "kimi-k2.7-code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5": {
|
|
id: "mimo-v2.5",
|
|
name: "MiMo V2.5",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.0028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro": {
|
|
id: "mimo-v2.5-pro",
|
|
name: "MiMo V2.5 Pro",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.74,
|
|
output: 3.48,
|
|
cacheRead: 0.0145,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax-m2.7": {
|
|
id: "minimax-m2.7",
|
|
name: "MiniMax M2.7",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax-m3": {
|
|
id: "minimax-m3",
|
|
name: "MiniMax M3 (3x usage)",
|
|
api: "anthropic-messages",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 512000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"qwen3.6-plus": {
|
|
id: "qwen3.6-plus",
|
|
name: "Qwen3.6 Plus",
|
|
api: "openai-completions",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go/v1",
|
|
compat: {"thinkingFormat":"qwen","maxTokensField":"max_tokens"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0.625,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen3.7-max": {
|
|
id: "qwen3.7-max",
|
|
name: "Qwen3.7 Max",
|
|
api: "anthropic-messages",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 7.5,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 3.125,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"qwen3.7-plus": {
|
|
id: "qwen3.7-plus",
|
|
name: "Qwen3.7 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "opencode-go",
|
|
baseUrl: "https://opencode.ai/zen/go",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"openrouter": {
|
|
"ai21/jamba-large-1.7": {
|
|
id: "ai21/jamba-large-1.7",
|
|
name: "AI21: Jamba Large 1.7",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"amazon/nova-2-lite-v1": {
|
|
id: "amazon/nova-2-lite-v1",
|
|
name: "Amazon: Nova 2 Lite",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65535,
|
|
} satisfies Model<"openai-completions">,
|
|
"amazon/nova-lite-v1": {
|
|
id: "amazon/nova-lite-v1",
|
|
name: "Amazon: Nova Lite 1.0",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.24,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 300000,
|
|
maxTokens: 5120,
|
|
} satisfies Model<"openai-completions">,
|
|
"amazon/nova-micro-v1": {
|
|
id: "amazon/nova-micro-v1",
|
|
name: "Amazon: Nova Micro 1.0",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.035,
|
|
output: 0.14,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 5120,
|
|
} satisfies Model<"openai-completions">,
|
|
"amazon/nova-premier-v1": {
|
|
id: "amazon/nova-premier-v1",
|
|
name: "Amazon: Nova Premier 1.0",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 12.5,
|
|
cacheRead: 0.625,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"amazon/nova-pro-v1": {
|
|
id: "amazon/nova-pro-v1",
|
|
name: "Amazon: Nova Pro 1.0",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 3.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 300000,
|
|
maxTokens: 5120,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-3-haiku": {
|
|
id: "anthropic/claude-3-haiku",
|
|
name: "Anthropic: Claude 3 Haiku",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.25,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.3,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-3.5-haiku": {
|
|
id: "anthropic/claude-3.5-haiku",
|
|
name: "Anthropic: Claude 3.5 Haiku",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 1,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-fable-5": {
|
|
id: "anthropic/claude-fable-5",
|
|
name: "Anthropic: Claude Fable 5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-haiku-4.5": {
|
|
id: "anthropic/claude-haiku-4.5",
|
|
name: "Anthropic: Claude Haiku 4.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4": {
|
|
id: "anthropic/claude-opus-4",
|
|
name: "Anthropic: Claude Opus 4",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.1": {
|
|
id: "anthropic/claude-opus-4.1",
|
|
name: "Anthropic: Claude Opus 4.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.5": {
|
|
id: "anthropic/claude-opus-4.5",
|
|
name: "Anthropic: Claude Opus 4.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.6": {
|
|
id: "anthropic/claude-opus-4.6",
|
|
name: "Anthropic: Claude Opus 4.6",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
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,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 150,
|
|
cacheRead: 3,
|
|
cacheWrite: 37.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.7": {
|
|
id: "anthropic/claude-opus-4.7",
|
|
name: "Anthropic: Claude Opus 4.7",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.7-fast": {
|
|
id: "anthropic/claude-opus-4.7-fast",
|
|
name: "Anthropic: Claude Opus 4.7 (Fast)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 150,
|
|
cacheRead: 3,
|
|
cacheWrite: 37.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.8": {
|
|
id: "anthropic/claude-opus-4.8",
|
|
name: "Anthropic: Claude Opus 4.8",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-opus-4.8-fast": {
|
|
id: "anthropic/claude-opus-4.8-fast",
|
|
name: "Anthropic: Claude Opus 4.8 (Fast)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-sonnet-4": {
|
|
id: "anthropic/claude-sonnet-4",
|
|
name: "Anthropic: Claude Sonnet 4",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-sonnet-4.5": {
|
|
id: "anthropic/claude-sonnet-4.5",
|
|
name: "Anthropic: Claude Sonnet 4.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"anthropic/claude-sonnet-4.6": {
|
|
id: "anthropic/claude-sonnet-4.6",
|
|
name: "Anthropic: Claude Sonnet 4.6",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"arcee-ai/trinity-large-thinking": {
|
|
id: "arcee-ai/trinity-large-thinking",
|
|
name: "Arcee AI: Trinity Large Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 0.85,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"arcee-ai/trinity-mini": {
|
|
id: "arcee-ai/trinity-mini",
|
|
name: "Arcee AI: Trinity Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.045,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"arcee-ai/virtuoso-large": {
|
|
id: "arcee-ai/virtuoso-large",
|
|
name: "Arcee AI: Virtuoso Large",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"auto": {
|
|
id: "auto",
|
|
name: "Auto",
|
|
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: 2000000,
|
|
maxTokens: 30000,
|
|
} satisfies Model<"openai-completions">,
|
|
"bytedance-seed/seed-1.6": {
|
|
id: "bytedance-seed/seed-1.6",
|
|
name: "ByteDance Seed: Seed 1.6",
|
|
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: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"bytedance-seed/seed-1.6-flash": {
|
|
id: "bytedance-seed/seed-1.6-flash",
|
|
name: "ByteDance Seed: Seed 1.6 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"cohere/command-r-08-2024": {
|
|
id: "cohere/command-r-08-2024",
|
|
name: "Cohere: Command R (08-2024)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"openai-completions">,
|
|
"cohere/command-r-plus-08-2024": {
|
|
id: "cohere/command-r-plus-08-2024",
|
|
name: "Cohere: Command R+ (08-2024)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"openai-completions">,
|
|
"cohere/north-mini-code:free": {
|
|
id: "cohere/north-mini-code:free",
|
|
name: "Cohere: North Mini Code (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: 256000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-chat": {
|
|
id: "deepseek/deepseek-chat",
|
|
name: "DeepSeek: DeepSeek V3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2002,
|
|
output: 0.8001,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-chat-v3-0324": {
|
|
id: "deepseek/deepseek-chat-v3-0324",
|
|
name: "DeepSeek: DeepSeek V3 0324",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.77,
|
|
cacheRead: 0.135,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-chat-v3.1": {
|
|
id: "deepseek/deepseek-chat-v3.1",
|
|
name: "DeepSeek: DeepSeek V3.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.21,
|
|
output: 0.79,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-r1": {
|
|
id: "deepseek/deepseek-r1",
|
|
name: "DeepSeek: R1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.7,
|
|
output: 2.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 16000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-r1-0528": {
|
|
id: "deepseek/deepseek-r1-0528",
|
|
name: "DeepSeek: R1 0528",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 2.15,
|
|
cacheRead: 0.35,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-v3.1-terminus": {
|
|
id: "deepseek/deepseek-v3.1-terminus",
|
|
name: "DeepSeek: DeepSeek V3.1 Terminus",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.27,
|
|
output: 0.95,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-v3.2": {
|
|
id: "deepseek/deepseek-v3.2",
|
|
name: "DeepSeek: DeepSeek V3.2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2288,
|
|
output: 0.3432,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-v3.2-exp": {
|
|
id: "deepseek/deepseek-v3.2-exp",
|
|
name: "DeepSeek: DeepSeek V3.2 Exp",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.27,
|
|
output: 0.41,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-v4-flash": {
|
|
id: "deepseek/deepseek-v4-flash",
|
|
name: "DeepSeek: DeepSeek V4 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.09,
|
|
output: 0.18,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek/deepseek-v4-pro": {
|
|
id: "deepseek/deepseek-v4-pro",
|
|
name: "DeepSeek: DeepSeek V4 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.435,
|
|
output: 0.87,
|
|
cacheRead: 0.003625,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
"essentialai/rnj-1-instruct": {
|
|
id: "essentialai/rnj-1-instruct",
|
|
name: "EssentialAI: Rnj 1 Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-2.5-flash": {
|
|
id: "google/gemini-2.5-flash",
|
|
name: "Google: Gemini 2.5 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2.5,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65535,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-2.5-flash-lite": {
|
|
id: "google/gemini-2.5-flash-lite",
|
|
name: "Google: Gemini 2.5 Flash Lite",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65535,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-2.5-flash-lite-preview-09-2025": {
|
|
id: "google/gemini-2.5-flash-lite-preview-09-2025",
|
|
name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65535,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-2.5-pro": {
|
|
id: "google/gemini-2.5-pro",
|
|
name: "Google: Gemini 2.5 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-2.5-pro-preview": {
|
|
id: "google/gemini-2.5-pro-preview",
|
|
name: "Google: Gemini 2.5 Pro Preview 06-05",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-2.5-pro-preview-05-06": {
|
|
id: "google/gemini-2.5-pro-preview-05-06",
|
|
name: "Google: Gemini 2.5 Pro Preview 05-06",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65535,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3-flash-preview": {
|
|
id: "google/gemini-3-flash-preview",
|
|
name: "Google: Gemini 3 Flash Preview",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65535,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3-pro-image": {
|
|
id: "google/gemini-3-pro-image",
|
|
name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 65536,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3.1-flash-lite": {
|
|
id: "google/gemini-3.1-flash-lite",
|
|
name: "Google: Gemini 3.1 Flash Lite",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3.1-flash-lite-preview": {
|
|
id: "google/gemini-3.1-flash-lite-preview",
|
|
name: "Google: Gemini 3.1 Flash Lite Preview",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3.1-pro-preview": {
|
|
id: "google/gemini-3.1-pro-preview",
|
|
name: "Google: Gemini 3.1 Pro Preview",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3.1-pro-preview-customtools": {
|
|
id: "google/gemini-3.1-pro-preview-customtools",
|
|
name: "Google: Gemini 3.1 Pro Preview Custom Tools",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1048756,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemini-3.5-flash": {
|
|
id: "google/gemini-3.5-flash",
|
|
name: "Google: Gemini 3.5 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemma-3-12b-it": {
|
|
id: "google/gemma-3-12b-it",
|
|
name: "Google: Gemma 3 12B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemma-3-27b-it": {
|
|
id: "google/gemma-3-27b-it",
|
|
name: "Google: Gemma 3 27B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.08,
|
|
output: 0.16,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemma-4-26b-a4b-it": {
|
|
id: "google/gemma-4-26b-a4b-it",
|
|
name: "Google: Gemma 4 26B A4B ",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.33,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} 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",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.12,
|
|
output: 0.35,
|
|
cacheRead: 0.09,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} 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: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"ibm-granite/granite-4.1-8b": {
|
|
id: "ibm-granite/granite-4.1-8b",
|
|
name: "IBM: Granite 4.1 8B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.1,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"inception/mercury-2": {
|
|
id: "inception/mercury-2",
|
|
name: "Inception: Mercury 2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 0.75,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 50000,
|
|
} satisfies Model<"openai-completions">,
|
|
"inclusionai/ling-2.6-1t": {
|
|
id: "inclusionai/ling-2.6-1t",
|
|
name: "inclusionAI: Ling-2.6-1T",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.625,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"inclusionai/ling-2.6-flash": {
|
|
id: "inclusionai/ling-2.6-flash",
|
|
name: "inclusionAI: Ling-2.6-flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.01,
|
|
output: 0.03,
|
|
cacheRead: 0.002,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"inclusionai/ring-2.6-1t": {
|
|
id: "inclusionai/ring-2.6-1t",
|
|
name: "inclusionAI: Ring-2.6-1T",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.625,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"kwaipilot/kat-coder-pro-v2": {
|
|
id: "kwaipilot/kat-coder-pro-v2",
|
|
name: "Kwaipilot: KAT-Coder-Pro V2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 80000,
|
|
} satisfies Model<"openai-completions">,
|
|
"liquid/lfm-2.5-1.2b-thinking:free": {
|
|
id: "liquid/lfm-2.5-1.2b-thinking:free",
|
|
name: "LiquidAI: LFM2.5-1.2B-Thinking (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: 32768,
|
|
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",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/llama-3.1-8b-instruct": {
|
|
id: "meta-llama/llama-3.1-8b-instruct",
|
|
name: "Meta: Llama 3.1 8B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.02,
|
|
output: 0.03,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/llama-3.3-70b-instruct": {
|
|
id: "meta-llama/llama-3.3-70b-instruct",
|
|
name: "Meta: Llama 3.3 70B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.32,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/llama-3.3-70b-instruct:free": {
|
|
id: "meta-llama/llama-3.3-70b-instruct:free",
|
|
name: "Meta: Llama 3.3 70B Instruct (free)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/llama-4-maverick": {
|
|
id: "meta-llama/llama-4-maverick",
|
|
name: "Meta: Llama 4 Maverick",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/llama-4-scout": {
|
|
id: "meta-llama/llama-4-scout",
|
|
name: "Meta: Llama 4 Scout",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 10000000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax/minimax-m1": {
|
|
id: "minimax/minimax-m1",
|
|
name: "MiniMax: MiniMax M1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 40000,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax/minimax-m2": {
|
|
id: "minimax/minimax-m2",
|
|
name: "MiniMax: MiniMax M2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.255,
|
|
output: 1,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 196608,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax/minimax-m2.1": {
|
|
id: "minimax/minimax-m2.1",
|
|
name: "MiniMax: MiniMax M2.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.29,
|
|
output: 0.95,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 196608,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax/minimax-m2.5": {
|
|
id: "minimax/minimax-m2.5",
|
|
name: "MiniMax: MiniMax M2.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.9,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 196608,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax/minimax-m2.7": {
|
|
id: "minimax/minimax-m2.7",
|
|
name: "MiniMax: MiniMax M2.7",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"minimax/minimax-m3": {
|
|
id: "minimax/minimax-m3",
|
|
name: "MiniMax: MiniMax M3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 512000,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/codestral-2508": {
|
|
id: "mistralai/codestral-2508",
|
|
name: "Mistral: Codestral 2508",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 0.9,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/devstral-2512": {
|
|
id: "mistralai/devstral-2512",
|
|
name: "Mistral: Devstral 2 2512",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/ministral-14b-2512": {
|
|
id: "mistralai/ministral-14b-2512",
|
|
name: "Mistral: Ministral 3 14B 2512",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.2,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/ministral-3b-2512": {
|
|
id: "mistralai/ministral-3b-2512",
|
|
name: "Mistral: Ministral 3 3B 2512",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.1,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/ministral-8b-2512": {
|
|
id: "mistralai/ministral-8b-2512",
|
|
name: "Mistral: Ministral 3 8B 2512",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-large": {
|
|
id: "mistralai/mistral-large",
|
|
name: "Mistral Large",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-large-2407": {
|
|
id: "mistralai/mistral-large-2407",
|
|
name: "Mistral Large 2407",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-large-2512": {
|
|
id: "mistralai/mistral-large-2512",
|
|
name: "Mistral: Mistral Large 3 2512",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-medium-3": {
|
|
id: "mistralai/mistral-medium-3",
|
|
name: "Mistral: Mistral Medium 3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-medium-3-5": {
|
|
id: "mistralai/mistral-medium-3-5",
|
|
name: "Mistral: Mistral Medium 3.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 7.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-medium-3.1": {
|
|
id: "mistralai/mistral-medium-3.1",
|
|
name: "Mistral: Mistral Medium 3.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-nemo": {
|
|
id: "mistralai/mistral-nemo",
|
|
name: "Mistral: Mistral Nemo",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.02,
|
|
output: 0.03,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-saba": {
|
|
id: "mistralai/mistral-saba",
|
|
name: "Mistral: Saba",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.6,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-small-2603": {
|
|
id: "mistralai/mistral-small-2603",
|
|
name: "Mistral: Mistral Small 4",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mistral-small-3.2-24b-instruct": {
|
|
id: "mistralai/mistral-small-3.2-24b-instruct",
|
|
name: "Mistral: Mistral Small 3.2 24B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/mixtral-8x22b-instruct": {
|
|
id: "mistralai/mixtral-8x22b-instruct",
|
|
name: "Mistral: Mixtral 8x22B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2,
|
|
output: 6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 65536,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"mistralai/voxtral-small-24b-2507": {
|
|
id: "mistralai/voxtral-small-24b-2507",
|
|
name: "Mistral: Voxtral Small 24B 2507",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2": {
|
|
id: "moonshotai/kimi-k2",
|
|
name: "MoonshotAI: Kimi K2 0711",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.57,
|
|
output: 2.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2-0905": {
|
|
id: "moonshotai/kimi-k2-0905",
|
|
name: "MoonshotAI: Kimi K2 0905",
|
|
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: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2-thinking": {
|
|
id: "moonshotai/kimi-k2-thinking",
|
|
name: "MoonshotAI: Kimi K2 Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2.5": {
|
|
id: "moonshotai/kimi-k2.5",
|
|
name: "MoonshotAI: Kimi K2.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.41,
|
|
output: 2.06,
|
|
cacheRead: 0.07,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2.6": {
|
|
id: "moonshotai/kimi-k2.6",
|
|
name: "MoonshotAI: Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
compat: {"supportsDeveloperRole":false,"requiresReasoningContentOnAssistantMessages":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.68,
|
|
output: 3.41,
|
|
cacheRead: 0.34,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262142,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/kimi-k2.7-code": {
|
|
id: "moonshotai/kimi-k2.7-code",
|
|
name: "MoonshotAI: Kimi K2.7 Code",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.74,
|
|
output: 3.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"nex-agi/nex-n2-pro:free": {
|
|
id: "nex-agi/nex-n2-pro:free",
|
|
name: "Nex AGI: Nex-N2-Pro (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: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
|
|
id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
|
|
name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-nano-30b-a3b": {
|
|
id: "nvidia/nemotron-3-nano-30b-a3b",
|
|
name: "NVIDIA: Nemotron 3 Nano 30B A3B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 228000,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-nano-30b-a3b:free": {
|
|
id: "nvidia/nemotron-3-nano-30b-a3b:free",
|
|
name: "NVIDIA: Nemotron 3 Nano 30B A3B (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: 256000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
|
|
id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
|
|
name: "NVIDIA: Nemotron 3 Nano Omni (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: 256000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-super-120b-a12b": {
|
|
id: "nvidia/nemotron-3-super-120b-a12b",
|
|
name: "NVIDIA: Nemotron 3 Super",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.09,
|
|
output: 0.45,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
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: 1000000,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-ultra-550b-a55b": {
|
|
id: "nvidia/nemotron-3-ultra-550b-a55b",
|
|
name: "NVIDIA: Nemotron 3 Ultra",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 2.2,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-ultra-550b-a55b:free": {
|
|
id: "nvidia/nemotron-3-ultra-550b-a55b:free",
|
|
name: "NVIDIA: Nemotron 3 Ultra (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: 1000000,
|
|
maxTokens: 65536,
|
|
} 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)",
|
|
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: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-nano-9b-v2:free": {
|
|
id: "nvidia/nemotron-nano-9b-v2:free",
|
|
name: "NVIDIA: Nemotron Nano 9B V2 (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: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-3.5-turbo": {
|
|
id: "openai/gpt-3.5-turbo",
|
|
name: "OpenAI: GPT-3.5 Turbo",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 16385,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-3.5-turbo-0613": {
|
|
id: "openai/gpt-3.5-turbo-0613",
|
|
name: "OpenAI: GPT-3.5 Turbo (older v0613)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 4095,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-3.5-turbo-16k": {
|
|
id: "openai/gpt-3.5-turbo-16k",
|
|
name: "OpenAI: GPT-3.5 Turbo 16k",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 3,
|
|
output: 4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 16385,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4": {
|
|
id: "openai/gpt-4",
|
|
name: "OpenAI: GPT-4",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 30,
|
|
output: 60,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 8191,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4-turbo": {
|
|
id: "openai/gpt-4-turbo",
|
|
name: "OpenAI: GPT-4 Turbo",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 30,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4-turbo-preview": {
|
|
id: "openai/gpt-4-turbo-preview",
|
|
name: "OpenAI: GPT-4 Turbo Preview",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 10,
|
|
output: 30,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4.1": {
|
|
id: "openai/gpt-4.1",
|
|
name: "OpenAI: GPT-4.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4.1-mini": {
|
|
id: "openai/gpt-4.1-mini",
|
|
name: "OpenAI: GPT-4.1 Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4.1-nano": {
|
|
id: "openai/gpt-4.1-nano",
|
|
name: "OpenAI: GPT-4.1 Nano",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4o": {
|
|
id: "openai/gpt-4o",
|
|
name: "OpenAI: GPT-4o",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4o-2024-05-13": {
|
|
id: "openai/gpt-4o-2024-05-13",
|
|
name: "OpenAI: GPT-4o (2024-05-13)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4o-2024-08-06": {
|
|
id: "openai/gpt-4o-2024-08-06",
|
|
name: "OpenAI: GPT-4o (2024-08-06)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4o-2024-11-20": {
|
|
id: "openai/gpt-4o-2024-11-20",
|
|
name: "OpenAI: GPT-4o (2024-11-20)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4o-mini": {
|
|
id: "openai/gpt-4o-mini",
|
|
name: "OpenAI: GPT-4o-mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-4o-mini-2024-07-18": {
|
|
id: "openai/gpt-4o-mini-2024-07-18",
|
|
name: "OpenAI: GPT-4o-mini (2024-07-18)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5": {
|
|
id: "openai/gpt-5",
|
|
name: "OpenAI: GPT-5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5-codex": {
|
|
id: "openai/gpt-5-codex",
|
|
name: "OpenAI: GPT-5 Codex",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5-mini": {
|
|
id: "openai/gpt-5-mini",
|
|
name: "OpenAI: GPT-5 Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5-nano": {
|
|
id: "openai/gpt-5-nano",
|
|
name: "OpenAI: GPT-5 Nano",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5-pro": {
|
|
id: "openai/gpt-5-pro",
|
|
name: "OpenAI: GPT-5 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 120,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.1": {
|
|
id: "openai/gpt-5.1",
|
|
name: "OpenAI: GPT-5.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.1-chat": {
|
|
id: "openai/gpt-5.1-chat",
|
|
name: "OpenAI: GPT-5.1 Chat",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.1-codex": {
|
|
id: "openai/gpt-5.1-codex",
|
|
name: "OpenAI: GPT-5.1-Codex",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.1-codex-max": {
|
|
id: "openai/gpt-5.1-codex-max",
|
|
name: "OpenAI: GPT-5.1-Codex-Max",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.1-codex-mini": {
|
|
id: "openai/gpt-5.1-codex-mini",
|
|
name: "OpenAI: GPT-5.1-Codex-Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.2": {
|
|
id: "openai/gpt-5.2",
|
|
name: "OpenAI: GPT-5.2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.2-chat": {
|
|
id: "openai/gpt-5.2-chat",
|
|
name: "OpenAI: GPT-5.2 Chat",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.2-codex": {
|
|
id: "openai/gpt-5.2-codex",
|
|
name: "OpenAI: GPT-5.2-Codex",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.2-pro": {
|
|
id: "openai/gpt-5.2-pro",
|
|
name: "OpenAI: GPT-5.2 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 21,
|
|
output: 168,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.3-chat": {
|
|
id: "openai/gpt-5.3-chat",
|
|
name: "OpenAI: GPT-5.3 Chat",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.3-codex": {
|
|
id: "openai/gpt-5.3-codex",
|
|
name: "OpenAI: GPT-5.3-Codex",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.4": {
|
|
id: "openai/gpt-5.4",
|
|
name: "OpenAI: GPT-5.4",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.4-mini": {
|
|
id: "openai/gpt-5.4-mini",
|
|
name: "OpenAI: GPT-5.4 Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.4-nano": {
|
|
id: "openai/gpt-5.4-nano",
|
|
name: "OpenAI: GPT-5.4 Nano",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.25,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.4-pro": {
|
|
id: "openai/gpt-5.4-pro",
|
|
name: "OpenAI: GPT-5.4 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.5": {
|
|
id: "openai/gpt-5.5",
|
|
name: "OpenAI: GPT-5.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-5.5-pro": {
|
|
id: "openai/gpt-5.5-pro",
|
|
name: "OpenAI: GPT-5.5 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","off":null,"minimal":null,"low":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-audio": {
|
|
id: "openai/gpt-audio",
|
|
name: "OpenAI: GPT Audio",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-audio-mini": {
|
|
id: "openai/gpt-audio-mini",
|
|
name: "OpenAI: GPT Audio Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-chat-latest": {
|
|
id: "openai/gpt-chat-latest",
|
|
name: "OpenAI: GPT Chat Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-120b": {
|
|
id: "openai/gpt-oss-120b",
|
|
name: "OpenAI: gpt-oss-120b",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.039,
|
|
output: 0.18,
|
|
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)",
|
|
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: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-20b": {
|
|
id: "openai/gpt-oss-20b",
|
|
name: "OpenAI: gpt-oss-20b",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.029,
|
|
output: 0.14,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-20b:free": {
|
|
id: "openai/gpt-oss-20b:free",
|
|
name: "OpenAI: gpt-oss-20b (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: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-safeguard-20b": {
|
|
id: "openai/gpt-oss-safeguard-20b",
|
|
name: "OpenAI: gpt-oss-safeguard-20b",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.3,
|
|
cacheRead: 0.037,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o1": {
|
|
id: "openai/o1",
|
|
name: "OpenAI: o1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 60,
|
|
cacheRead: 7.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o3": {
|
|
id: "openai/o3",
|
|
name: "OpenAI: o3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o3-deep-research": {
|
|
id: "openai/o3-deep-research",
|
|
name: "OpenAI: o3 Deep Research",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 40,
|
|
cacheRead: 2.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o3-mini": {
|
|
id: "openai/o3-mini",
|
|
name: "OpenAI: o3 Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o3-mini-high": {
|
|
id: "openai/o3-mini-high",
|
|
name: "OpenAI: o3 Mini High",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o3-pro": {
|
|
id: "openai/o3-pro",
|
|
name: "OpenAI: o3 Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 20,
|
|
output: 80,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o4-mini": {
|
|
id: "openai/o4-mini",
|
|
name: "OpenAI: o4 Mini",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.275,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o4-mini-deep-research": {
|
|
id: "openai/o4-mini-deep-research",
|
|
name: "OpenAI: o4 Mini Deep Research",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/o4-mini-high": {
|
|
id: "openai/o4-mini-high",
|
|
name: "OpenAI: o4 Mini High",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.275,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"openai-completions">,
|
|
"openrouter/auto": {
|
|
id: "openrouter/auto",
|
|
name: "Auto Router",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: -1000000,
|
|
output: -1000000,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 2000000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openrouter/free": {
|
|
id: "openrouter/free",
|
|
name: "Free Models Router",
|
|
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: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"openrouter/owl-alpha": {
|
|
id: "openrouter/owl-alpha",
|
|
name: "Owl Alpha",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048756,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"poolside/laguna-m.1": {
|
|
id: "poolside/laguna-m.1",
|
|
name: "Poolside: Laguna M.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.4,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"poolside/laguna-m.1:free": {
|
|
id: "poolside/laguna-m.1:free",
|
|
name: "Poolside: Laguna M.1 (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: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"poolside/laguna-xs.2": {
|
|
id: "poolside/laguna-xs.2",
|
|
name: "Poolside: Laguna XS.2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.2,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"poolside/laguna-xs.2:free": {
|
|
id: "poolside/laguna-xs.2:free",
|
|
name: "Poolside: Laguna XS.2 (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: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"prime-intellect/intellect-3": {
|
|
id: "prime-intellect/intellect-3",
|
|
name: "Prime Intellect: INTELLECT-3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen-2.5-72b-instruct": {
|
|
id: "qwen/qwen-2.5-72b-instruct",
|
|
name: "Qwen2.5 72B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.36,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen-2.5-7b-instruct": {
|
|
id: "qwen/qwen-2.5-7b-instruct",
|
|
name: "Qwen: Qwen2.5 7B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.04,
|
|
output: 0.1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen-plus": {
|
|
id: "qwen/qwen-plus",
|
|
name: "Qwen: Qwen-Plus",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.26,
|
|
output: 0.78,
|
|
cacheRead: 0.052,
|
|
cacheWrite: 0.325,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen-plus-2025-07-28": {
|
|
id: "qwen/qwen-plus-2025-07-28",
|
|
name: "Qwen: Qwen Plus 0728",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.26,
|
|
output: 0.78,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen-plus-2025-07-28:thinking": {
|
|
id: "qwen/qwen-plus-2025-07-28:thinking",
|
|
name: "Qwen: Qwen Plus 0728 (thinking)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.26,
|
|
output: 0.78,
|
|
cacheRead: 0,
|
|
cacheWrite: 0.325,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-14b": {
|
|
id: "qwen/qwen3-14b",
|
|
name: "Qwen: Qwen3 14B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.24,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131702,
|
|
maxTokens: 40960,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-235b-a22b": {
|
|
id: "qwen/qwen3-235b-a22b",
|
|
name: "Qwen: Qwen3 235B A22B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.455,
|
|
output: 1.82,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-235b-a22b-2507": {
|
|
id: "qwen/qwen3-235b-a22b-2507",
|
|
name: "Qwen: Qwen3 235B A22B Instruct 2507",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.09,
|
|
output: 0.1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-235b-a22b-thinking-2507": {
|
|
id: "qwen/qwen3-235b-a22b-thinking-2507",
|
|
name: "Qwen: Qwen3 235B A22B Thinking 2507",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.1,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-30b-a3b": {
|
|
id: "qwen/qwen3-30b-a3b",
|
|
name: "Qwen: Qwen3 30B A3B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.12,
|
|
output: 0.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-30b-a3b-instruct-2507": {
|
|
id: "qwen/qwen3-30b-a3b-instruct-2507",
|
|
name: "Qwen: Qwen3 30B A3B Instruct 2507",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.04815,
|
|
output: 0.19305,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-30b-a3b-thinking-2507": {
|
|
id: "qwen/qwen3-30b-a3b-thinking-2507",
|
|
name: "Qwen: Qwen3 30B A3B Thinking 2507",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.08,
|
|
output: 0.4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-32b": {
|
|
id: "qwen/qwen3-32b",
|
|
name: "Qwen: Qwen3 32B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.08,
|
|
output: 0.28,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-8b": {
|
|
id: "qwen/qwen3-8b",
|
|
name: "Qwen: Qwen3 8B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.4,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-coder": {
|
|
id: "qwen/qwen3-coder",
|
|
name: "Qwen: Qwen3 Coder 480B A35B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 1.8,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-coder-30b-a3b-instruct": {
|
|
id: "qwen/qwen3-coder-30b-a3b-instruct",
|
|
name: "Qwen: Qwen3 Coder 30B A3B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.07,
|
|
output: 0.27,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 160000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-coder-flash": {
|
|
id: "qwen/qwen3-coder-flash",
|
|
name: "Qwen: Qwen3 Coder Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.195,
|
|
output: 0.975,
|
|
cacheRead: 0.039,
|
|
cacheWrite: 0.24375,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-coder-next": {
|
|
id: "qwen/qwen3-coder-next",
|
|
name: "Qwen: Qwen3 Coder Next",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.11,
|
|
output: 0.8,
|
|
cacheRead: 0.07,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-coder-plus": {
|
|
id: "qwen/qwen3-coder-plus",
|
|
name: "Qwen: Qwen3 Coder Plus",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.65,
|
|
output: 3.25,
|
|
cacheRead: 0.13,
|
|
cacheWrite: 0.8125,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-coder:free": {
|
|
id: "qwen/qwen3-coder:free",
|
|
name: "Qwen: Qwen3 Coder 480B A35B (free)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-max": {
|
|
id: "qwen/qwen3-max",
|
|
name: "Qwen: Qwen3 Max",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.78,
|
|
output: 3.9,
|
|
cacheRead: 0.156,
|
|
cacheWrite: 0.975,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-max-thinking": {
|
|
id: "qwen/qwen3-max-thinking",
|
|
name: "Qwen: Qwen3 Max Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.78,
|
|
output: 3.9,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-next-80b-a3b-instruct": {
|
|
id: "qwen/qwen3-next-80b-a3b-instruct",
|
|
name: "Qwen: Qwen3 Next 80B A3B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.09,
|
|
output: 1.1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-next-80b-a3b-instruct:free": {
|
|
id: "qwen/qwen3-next-80b-a3b-instruct:free",
|
|
name: "Qwen: Qwen3 Next 80B A3B Instruct (free)",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-next-80b-a3b-thinking": {
|
|
id: "qwen/qwen3-next-80b-a3b-thinking",
|
|
name: "Qwen: Qwen3 Next 80B A3B Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.0975,
|
|
output: 0.78,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-235b-a22b-instruct": {
|
|
id: "qwen/qwen3-vl-235b-a22b-instruct",
|
|
name: "Qwen: Qwen3 VL 235B A22B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.88,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-235b-a22b-thinking": {
|
|
id: "qwen/qwen3-vl-235b-a22b-thinking",
|
|
name: "Qwen: Qwen3 VL 235B A22B Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.26,
|
|
output: 2.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-30b-a3b-instruct": {
|
|
id: "qwen/qwen3-vl-30b-a3b-instruct",
|
|
name: "Qwen: Qwen3 VL 30B A3B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.13,
|
|
output: 0.52,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-30b-a3b-thinking": {
|
|
id: "qwen/qwen3-vl-30b-a3b-thinking",
|
|
name: "Qwen: Qwen3 VL 30B A3B Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.13,
|
|
output: 1.56,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-32b-instruct": {
|
|
id: "qwen/qwen3-vl-32b-instruct",
|
|
name: "Qwen: Qwen3 VL 32B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.104,
|
|
output: 0.416,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-8b-instruct": {
|
|
id: "qwen/qwen3-vl-8b-instruct",
|
|
name: "Qwen: Qwen3 VL 8B Instruct",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.08,
|
|
output: 0.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3-vl-8b-thinking": {
|
|
id: "qwen/qwen3-vl-8b-thinking",
|
|
name: "Qwen: Qwen3 VL 8B Thinking",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.117,
|
|
output: 1.365,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-122b-a10b": {
|
|
id: "qwen/qwen3.5-122b-a10b",
|
|
name: "Qwen: Qwen3.5-122B-A10B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.26,
|
|
output: 2.08,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-27b": {
|
|
id: "qwen/qwen3.5-27b",
|
|
name: "Qwen: Qwen3.5-27B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.195,
|
|
output: 1.56,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-35b-a3b": {
|
|
id: "qwen/qwen3.5-35b-a3b",
|
|
name: "Qwen: Qwen3.5-35B-A3B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-397b-a17b": {
|
|
id: "qwen/qwen3.5-397b-a17b",
|
|
name: "Qwen: Qwen3.5 397B A17B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.385,
|
|
output: 2.45,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 4096,
|
|
} 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: 0.1,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-flash-02-23": {
|
|
id: "qwen/qwen3.5-flash-02-23",
|
|
name: "Qwen: Qwen3.5-Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.065,
|
|
output: 0.26,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-plus-02-15": {
|
|
id: "qwen/qwen3.5-plus-02-15",
|
|
name: "Qwen: Qwen3.5 Plus 2026-02-15",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.26,
|
|
output: 1.56,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.5-plus-20260420": {
|
|
id: "qwen/qwen3.5-plus-20260420",
|
|
name: "Qwen: Qwen3.5 Plus 2026-04-20",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.8,
|
|
cacheRead: 0,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.6-27b": {
|
|
id: "qwen/qwen3.6-27b",
|
|
name: "Qwen: Qwen3.6 27B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2885,
|
|
output: 3.17,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262140,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.6-35b-a3b": {
|
|
id: "qwen/qwen3.6-35b-a3b",
|
|
name: "Qwen: Qwen3.6 35B A3B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.6-flash": {
|
|
id: "qwen/qwen3.6-flash",
|
|
name: "Qwen: Qwen3.6 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1875,
|
|
output: 1.125,
|
|
cacheRead: 0,
|
|
cacheWrite: 0.234375,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.6-max-preview": {
|
|
id: "qwen/qwen3.6-max-preview",
|
|
name: "Qwen: Qwen3.6 Max Preview",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.04,
|
|
output: 6.24,
|
|
cacheRead: 0,
|
|
cacheWrite: 1.3,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"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: 0.325,
|
|
output: 1.95,
|
|
cacheRead: 0,
|
|
cacheWrite: 0.40625,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.7-max": {
|
|
id: "qwen/qwen3.7-max",
|
|
name: "Qwen: Qwen3.7 Max",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 3.75,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 1.5625,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"qwen/qwen3.7-plus": {
|
|
id: "qwen/qwen3.7-plus",
|
|
name: "Qwen: Qwen3.7 Plus",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.32,
|
|
output: 1.28,
|
|
cacheRead: 0.064,
|
|
cacheWrite: 0.4,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"rekaai/reka-edge": {
|
|
id: "rekaai/reka-edge",
|
|
name: "Reka Edge",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 16384,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"relace/relace-search": {
|
|
id: "relace/relace-search",
|
|
name: "Relace: Relace Search",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"sao10k/l3.1-euryale-70b": {
|
|
id: "sao10k/l3.1-euryale-70b",
|
|
name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.85,
|
|
output: 0.85,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"stepfun/step-3.5-flash": {
|
|
id: "stepfun/step-3.5-flash",
|
|
name: "StepFun: Step 3.5 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.09,
|
|
output: 0.3,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"stepfun/step-3.7-flash": {
|
|
id: "stepfun/step-3.7-flash",
|
|
name: "StepFun: Step 3.7 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.15,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"tencent/hy3-preview": {
|
|
id: "tencent/hy3-preview",
|
|
name: "Tencent: Hy3 preview",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.066,
|
|
output: 0.26,
|
|
cacheRead: 0.029,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"thedrummer/rocinante-12b": {
|
|
id: "thedrummer/rocinante-12b",
|
|
name: "TheDrummer: Rocinante 12B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.17,
|
|
output: 0.43,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"thedrummer/unslopnemo-12b": {
|
|
id: "thedrummer/unslopnemo-12b",
|
|
name: "TheDrummer: UnslopNemo 12B",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"upstage/solar-pro-3": {
|
|
id: "upstage/solar-pro-3",
|
|
name: "Upstage: Solar Pro 3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"x-ai/grok-4.20": {
|
|
id: "x-ai/grok-4.20",
|
|
name: "xAI: Grok 4.20",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 2000000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"x-ai/grok-4.3": {
|
|
id: "x-ai/grok-4.3",
|
|
name: "xAI: Grok 4.3",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"x-ai/grok-build-0.1": {
|
|
id: "x-ai/grok-build-0.1",
|
|
name: "xAI: Grok Build 0.1",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"xiaomi/mimo-v2.5": {
|
|
id: "xiaomi/mimo-v2.5",
|
|
name: "Xiaomi: MiMo-V2.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.0028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"xiaomi/mimo-v2.5-pro": {
|
|
id: "xiaomi/mimo-v2.5-pro",
|
|
name: "Xiaomi: MiMo-V2.5-Pro",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.435,
|
|
output: 0.87,
|
|
cacheRead: 0.0036,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.5": {
|
|
id: "z-ai/glm-4.5",
|
|
name: "Z.ai: GLM 4.5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.2,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 98304,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.5-air": {
|
|
id: "z-ai/glm-4.5-air",
|
|
name: "Z.ai: GLM 4.5 Air",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.13,
|
|
output: 0.85,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 98304,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.5v": {
|
|
id: "z-ai/glm-4.5v",
|
|
name: "Z.ai: GLM 4.5V",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 1.8,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 65536,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.6": {
|
|
id: "z-ai/glm-4.6",
|
|
name: "Z.ai: GLM 4.6",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.43,
|
|
output: 1.74,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.6v": {
|
|
id: "z-ai/glm-4.6v",
|
|
name: "Z.ai: GLM 4.6V",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 0.9,
|
|
cacheRead: 0.055,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.7": {
|
|
id: "z-ai/glm-4.7",
|
|
name: "Z.ai: GLM 4.7",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.75,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-4.7-flash": {
|
|
id: "z-ai/glm-4.7-flash",
|
|
name: "Z.ai: GLM 4.7 Flash",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-5": {
|
|
id: "z-ai/glm-5",
|
|
name: "Z.ai: GLM 5",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 1.9,
|
|
cacheRead: 0.119,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-5-turbo": {
|
|
id: "z-ai/glm-5-turbo",
|
|
name: "Z.ai: GLM 5 Turbo",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.2,
|
|
output: 4,
|
|
cacheRead: 0.24,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
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: 0.98,
|
|
output: 3.08,
|
|
cacheRead: 0.182,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"openai-completions">,
|
|
"z-ai/glm-5.2": {
|
|
id: "z-ai/glm-5.2",
|
|
name: "Z.ai: GLM 5.2",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.7,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 524288,
|
|
} satisfies Model<"openai-completions">,
|
|
"~anthropic/claude-fable-latest": {
|
|
id: "~anthropic/claude-fable-latest",
|
|
name: "Anthropic: Claude Fable Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 50,
|
|
cacheRead: 1,
|
|
cacheWrite: 12.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"~anthropic/claude-haiku-latest": {
|
|
id: "~anthropic/claude-haiku-latest",
|
|
name: "Anthropic Claude Haiku Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"openai-completions">,
|
|
"~anthropic/claude-opus-latest": {
|
|
id: "~anthropic/claude-opus-latest",
|
|
name: "Anthropic: Claude Opus Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"~anthropic/claude-sonnet-latest": {
|
|
id: "~anthropic/claude-sonnet-latest",
|
|
name: "Anthropic Claude Sonnet Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"~google/gemini-flash-latest": {
|
|
id: "~google/gemini-flash-latest",
|
|
name: "Google Gemini Flash Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0.083333,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"~google/gemini-pro-latest": {
|
|
id: "~google/gemini-pro-latest",
|
|
name: "Google Gemini Pro Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"~moonshotai/kimi-latest": {
|
|
id: "~moonshotai/kimi-latest",
|
|
name: "MoonshotAI Kimi Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.68,
|
|
output: 3.41,
|
|
cacheRead: 0.34,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262142,
|
|
} satisfies Model<"openai-completions">,
|
|
"~openai/gpt-latest": {
|
|
id: "~openai/gpt-latest",
|
|
name: "OpenAI GPT Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
"~openai/gpt-mini-latest": {
|
|
id: "~openai/gpt-mini-latest",
|
|
name: "OpenAI GPT Mini Latest",
|
|
api: "openai-completions",
|
|
provider: "openrouter",
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"together": {
|
|
"MiniMaxAI/MiniMax-M2.7": {
|
|
id: "MiniMaxAI/MiniMax-M2.7",
|
|
name: "MiniMax-M2.7",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"MiniMaxAI/MiniMax-M3": {
|
|
id: "MiniMaxAI/MiniMax-M3",
|
|
name: "MiniMax-M3",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 524288,
|
|
maxTokens: 250000,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
|
|
id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
|
|
name: "Qwen 2.5 7B Instruct Turbo",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
|
|
id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
|
|
name: "Qwen3 235B A22B Instruct 2507 FP8",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 262144,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3.5-397B-A17B": {
|
|
id: "Qwen/Qwen3.5-397B-A17B",
|
|
name: "Qwen3.5 397B A17B",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 130000,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3.5-9B": {
|
|
id: "Qwen/Qwen3.5-9B",
|
|
name: "Qwen3.5 9B",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.17,
|
|
output: 0.25,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3.6-Plus": {
|
|
id: "Qwen/Qwen3.6-Plus",
|
|
name: "Qwen3.6 Plus",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 500000,
|
|
} satisfies Model<"openai-completions">,
|
|
"Qwen/Qwen3.7-Max": {
|
|
id: "Qwen/Qwen3.7-Max",
|
|
name: "Qwen3.7 Max",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 3.75,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 500000,
|
|
} satisfies Model<"openai-completions">,
|
|
"deepseek-ai/DeepSeek-V4-Pro": {
|
|
id: "deepseek-ai/DeepSeek-V4-Pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.74,
|
|
output: 3.48,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 512000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"openai-completions">,
|
|
"essentialai/Rnj-1-Instruct": {
|
|
id: "essentialai/Rnj-1-Instruct",
|
|
name: "Rnj-1 Instruct",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"openai-completions">,
|
|
"google/gemma-4-31B-it": {
|
|
id: "google/gemma-4-31B-it",
|
|
name: "Gemma 4 31B Instruct",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.39,
|
|
output: 0.97,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
|
|
id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
|
name: "Llama 3.3 70B",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.88,
|
|
output: 0.88,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2.6": {
|
|
id: "moonshotai/Kimi-K2.6",
|
|
name: "Kimi K2.6",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.2,
|
|
output: 4.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"openai-completions">,
|
|
"moonshotai/Kimi-K2.7-Code": {
|
|
id: "moonshotai/Kimi-K2.7-Code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"nvidia/nemotron-3-ultra-550b-a55b": {
|
|
id: "nvidia/nemotron-3-ultra-550b-a55b",
|
|
name: "Nemotron 3 Ultra 550B A55B",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3.6,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 512300,
|
|
maxTokens: 512300,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-120b": {
|
|
id: "openai/gpt-oss-120b",
|
|
name: "GPT OSS 120B",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"openai/gpt-oss-20b": {
|
|
id: "openai/gpt-oss-20b",
|
|
name: "GPT OSS 20B",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"off":null,"minimal":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"zai-org/GLM-5": {
|
|
id: "zai-org/GLM-5",
|
|
name: "GLM-5",
|
|
api: "openai-completions",
|
|
provider: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
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: "together",
|
|
baseUrl: "https://api.together.ai/v1",
|
|
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202752,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"vercel-ai-gateway": {
|
|
"alibaba/qwen-3-14b": {
|
|
id: "alibaba/qwen-3-14b",
|
|
name: "Qwen3-14B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.12,
|
|
output: 0.24,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 40960,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen-3-235b": {
|
|
id: "alibaba/qwen-3-235b",
|
|
name: "Qwen3 235B A22B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 0.88,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen-3-30b": {
|
|
id: "alibaba/qwen-3-30b",
|
|
name: "Qwen3-30B-A3B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.12,
|
|
output: 0.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 40960,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen-3-32b": {
|
|
id: "alibaba/qwen-3-32b",
|
|
name: "Qwen 3 32B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.16,
|
|
output: 0.64,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen-3.6-max-preview": {
|
|
id: "alibaba/qwen-3.6-max-preview",
|
|
name: "Qwen 3.6 Max Preview",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.3,
|
|
output: 7.8,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 1.625,
|
|
},
|
|
contextWindow: 240000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-235b-a22b-thinking": {
|
|
id: "alibaba/qwen3-235b-a22b-thinking",
|
|
name: "Qwen3 VL 235B A22B Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-coder": {
|
|
id: "alibaba/qwen3-coder",
|
|
name: "Qwen3 Coder 480B A35B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 7.5,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-coder-30b-a3b": {
|
|
id: "alibaba/qwen3-coder-30b-a3b",
|
|
name: "Qwen 3 Coder 30B A3B Instruct",
|
|
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: 262144,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-coder-next": {
|
|
id: "alibaba/qwen3-coder-next",
|
|
name: "Qwen3 Coder Next",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-coder-plus": {
|
|
id: "alibaba/qwen3-coder-plus",
|
|
name: "Qwen3 Coder Plus",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
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-thinking": {
|
|
id: "alibaba/qwen3-max-thinking",
|
|
name: "Qwen 3 Max Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.2,
|
|
output: 6,
|
|
cacheRead: 0.24,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-next-80b-a3b-instruct": {
|
|
id: "alibaba/qwen3-next-80b-a3b-instruct",
|
|
name: "Qwen3 Next 80B A3B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-next-80b-a3b-thinking": {
|
|
id: "alibaba/qwen3-next-80b-a3b-thinking",
|
|
name: "Qwen3 Next 80B A3B Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 1.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3-vl-thinking": {
|
|
id: "alibaba/qwen3-vl-thinking",
|
|
name: "Qwen3 VL 235B A22B Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3.5-flash": {
|
|
id: "alibaba/qwen3.5-flash",
|
|
name: "Qwen 3.5 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.001,
|
|
cacheWrite: 0.125,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3.5-plus": {
|
|
id: "alibaba/qwen3.5-plus",
|
|
name: "Qwen 3.5 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2.4,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3.6-27b": {
|
|
id: "alibaba/qwen3.6-27b",
|
|
name: "Qwen 3.6 27B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3.6-plus": {
|
|
id: "alibaba/qwen3.6-plus",
|
|
name: "Qwen 3.6 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0.625,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3.7-max": {
|
|
id: "alibaba/qwen3.7-max",
|
|
name: "Qwen 3.7 Max",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 3.75,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 1.5625,
|
|
},
|
|
contextWindow: 991000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"alibaba/qwen3.7-plus": {
|
|
id: "alibaba/qwen3.7-plus",
|
|
name: "Qwen 3.7 Plus",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0.5,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-3-haiku": {
|
|
id: "anthropic/claude-3-haiku",
|
|
name: "Claude 3 Haiku",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.25,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.3,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-3.5-haiku": {
|
|
id: "anthropic/claude-3.5-haiku",
|
|
name: "Claude 3.5 Haiku",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.8,
|
|
output: 4,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 1,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-haiku-4.5": {
|
|
id: "anthropic/claude-haiku-4.5",
|
|
name: "Claude Haiku 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 5,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 1.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-opus-4": {
|
|
id: "anthropic/claude-opus-4",
|
|
name: "Claude Opus 4",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-opus-4.1": {
|
|
id: "anthropic/claude-opus-4.1",
|
|
name: "Claude Opus 4.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 75,
|
|
cacheRead: 1.5,
|
|
cacheWrite: 18.75,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-opus-4.5": {
|
|
id: "anthropic/claude-opus-4.5",
|
|
name: "Claude Opus 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-opus-4.6": {
|
|
id: "anthropic/claude-opus-4.6",
|
|
name: "Claude Opus 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"max"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-opus-4.7": {
|
|
id: "anthropic/claude-opus-4.7",
|
|
name: "Claude Opus 4.7",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-opus-4.8": {
|
|
id: "anthropic/claude-opus-4.8",
|
|
name: "Claude Opus 4.8",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 6.25,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-sonnet-4": {
|
|
id: "anthropic/claude-sonnet-4",
|
|
name: "Claude Sonnet 4",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-sonnet-4.5": {
|
|
id: "anthropic/claude-sonnet-4.5",
|
|
name: "Claude Sonnet 4.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"anthropic/claude-sonnet-4.6": {
|
|
id: "anthropic/claude-sonnet-4.6",
|
|
name: "Claude Sonnet 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
compat: {"forceAdaptiveThinking":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 3.75,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"arcee-ai/trinity-large-preview": {
|
|
id: "arcee-ai/trinity-large-preview",
|
|
name: "Trinity Large Preview",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131000,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"arcee-ai/trinity-large-thinking": {
|
|
id: "arcee-ai/trinity-large-thinking",
|
|
name: "Trinity Large Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 0.9,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262100,
|
|
maxTokens: 80000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"bytedance/seed-1.6": {
|
|
id: "bytedance/seed-1.6",
|
|
name: "Seed 1.6",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"cohere/command-a": {
|
|
id: "cohere/command-a",
|
|
name: "Command A",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
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",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.27,
|
|
output: 1.12,
|
|
cacheRead: 0.135,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 163840,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek/deepseek-v3.1": {
|
|
id: "deepseek/deepseek-v3.1",
|
|
name: "DeepSeek V3.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.56,
|
|
output: 1.68,
|
|
cacheRead: 0.28,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 163840,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek/deepseek-v3.1-terminus": {
|
|
id: "deepseek/deepseek-v3.1-terminus",
|
|
name: "DeepSeek V3.1 Terminus",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.27,
|
|
output: 1,
|
|
cacheRead: 0.135,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek/deepseek-v3.2": {
|
|
id: "deepseek/deepseek-v3.2",
|
|
name: "DeepSeek V3.2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.28,
|
|
output: 0.42,
|
|
cacheRead: 0.028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek/deepseek-v3.2-thinking": {
|
|
id: "deepseek/deepseek-v3.2-thinking",
|
|
name: "DeepSeek V3.2 Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.62,
|
|
output: 1.85,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek/deepseek-v4-flash": {
|
|
id: "deepseek/deepseek-v4-flash",
|
|
name: "DeepSeek V4 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.0028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"deepseek/deepseek-v4-pro": {
|
|
id: "deepseek/deepseek-v4-pro",
|
|
name: "DeepSeek V4 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.435,
|
|
output: 0.87,
|
|
cacheRead: 0.0036,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 384000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-2.5-flash": {
|
|
id: "google/gemini-2.5-flash",
|
|
name: "Gemini 2.5 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2.5,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-2.5-flash-lite": {
|
|
id: "google/gemini-2.5-flash-lite",
|
|
name: "Gemini 2.5 Flash Lite",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-2.5-pro": {
|
|
id: "google/gemini-2.5-pro",
|
|
name: "Gemini 2.5 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-3-flash": {
|
|
id: "google/gemini-3-flash",
|
|
name: "Gemini 3 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.5,
|
|
output: 3,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-3-pro-preview": {
|
|
id: "google/gemini-3-pro-preview",
|
|
name: "Gemini 3 Pro Preview",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-3.1-flash-lite": {
|
|
id: "google/gemini-3.1-flash-lite",
|
|
name: "Gemini 3.1 Flash Lite",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-3.1-flash-lite-preview": {
|
|
id: "google/gemini-3.1-flash-lite-preview",
|
|
name: "Gemini 3.1 Flash Lite Preview",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1.5,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-3.1-pro-preview": {
|
|
id: "google/gemini-3.1-pro-preview",
|
|
name: "Gemini 3.1 Pro Preview",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 12,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemini-3.5-flash": {
|
|
id: "google/gemini-3.5-flash",
|
|
name: "Gemini 3.5 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 9,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemma-4-26b-a4b-it": {
|
|
id: "google/gemma-4-26b-a4b-it",
|
|
name: "Gemma 4 26B A4B IT",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.6,
|
|
cacheRead: 0.015,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"google/gemma-4-31b-it": {
|
|
id: "google/gemma-4-31b-it",
|
|
name: "Gemma 4 31B IT",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.4,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"inception/mercury-2": {
|
|
id: "inception/mercury-2",
|
|
name: "Mercury 2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 0.75,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"inception/mercury-coder-small": {
|
|
id: "inception/mercury-coder-small",
|
|
name: "Mercury Coder Small Beta",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"kwaipilot/kat-coder-pro-v2": {
|
|
id: "kwaipilot/kat-coder-pro-v2",
|
|
name: "Kat Coder Pro V2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meituan/longcat-flash-chat": {
|
|
id: "meituan/longcat-flash-chat",
|
|
name: "LongCat Flash Chat",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-3.1-70b": {
|
|
id: "meta/llama-3.1-70b",
|
|
name: "Llama 3.1 70B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.72,
|
|
output: 0.72,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-3.1-8b": {
|
|
id: "meta/llama-3.1-8b",
|
|
name: "Llama 3.1 8B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.22,
|
|
output: 0.22,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-3.2-11b": {
|
|
id: "meta/llama-3.2-11b",
|
|
name: "Llama 3.2 11B Vision Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.16,
|
|
output: 0.16,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-3.2-90b": {
|
|
id: "meta/llama-3.2-90b",
|
|
name: "Llama 3.2 90B Vision Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.72,
|
|
output: 0.72,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-3.3-70b": {
|
|
id: "meta/llama-3.3-70b",
|
|
name: "Llama 3.3 70B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.72,
|
|
output: 0.72,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-4-maverick": {
|
|
id: "meta/llama-4-maverick",
|
|
name: "Llama 4 Maverick 17B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.24,
|
|
output: 0.97,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"meta/llama-4-scout": {
|
|
id: "meta/llama-4-scout",
|
|
name: "Llama 4 Scout 17B Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.17,
|
|
output: 0.66,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2": {
|
|
id: "minimax/minimax-m2",
|
|
name: "MiniMax M2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 205000,
|
|
maxTokens: 205000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2.1": {
|
|
id: "minimax/minimax-m2.1",
|
|
name: "MiniMax M2.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2.1-lightning": {
|
|
id: "minimax/minimax-m2.1-lightning",
|
|
name: "MiniMax M2.1 Lightning",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 2.4,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2.5": {
|
|
id: "minimax/minimax-m2.5",
|
|
name: "MiniMax M2.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2.5-highspeed": {
|
|
id: "minimax/minimax-m2.5-highspeed",
|
|
name: "MiniMax M2.5 High Speed",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2.7": {
|
|
id: "minimax/minimax-m2.7",
|
|
name: "MiniMax M2.7",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m2.7-highspeed": {
|
|
id: "minimax/minimax-m2.7-highspeed",
|
|
name: "MiniMax M2.7 High Speed",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0.375,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131100,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"minimax/minimax-m3": {
|
|
id: "minimax/minimax-m3",
|
|
name: "MiniMax M3",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 1.2,
|
|
cacheRead: 0.06,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 1000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/codestral": {
|
|
id: "mistral/codestral",
|
|
name: "Mistral Codestral",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 0.9,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/devstral-2": {
|
|
id: "mistral/devstral-2",
|
|
name: "Devstral 2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/devstral-small": {
|
|
id: "mistral/devstral-small",
|
|
name: "Devstral Small 1.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/devstral-small-2": {
|
|
id: "mistral/devstral-small-2",
|
|
name: "Devstral Small 2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/ministral-3b": {
|
|
id: "mistral/ministral-3b",
|
|
name: "Ministral 3B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.1,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/ministral-8b": {
|
|
id: "mistral/ministral-8b",
|
|
name: "Ministral 8B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/mistral-medium": {
|
|
id: "mistral/mistral-medium",
|
|
name: "Mistral Medium 3.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/mistral-medium-3.5": {
|
|
id: "mistral/mistral-medium-3.5",
|
|
name: "Mistral Medium Latest",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 7.5,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/mistral-nemo": {
|
|
id: "mistral/mistral-nemo",
|
|
name: "Mistral Nemo 12B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/mistral-small": {
|
|
id: "mistral/mistral-small",
|
|
name: "Mistral Small",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/pixtral-12b": {
|
|
id: "mistral/pixtral-12b",
|
|
name: "Pixtral 12B 2409",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.15,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"mistral/pixtral-large": {
|
|
id: "mistral/pixtral-large",
|
|
name: "Pixtral Large",
|
|
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,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"moonshotai/kimi-k2": {
|
|
id: "moonshotai/kimi-k2",
|
|
name: "Kimi K2 Instruct",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.57,
|
|
output: 2.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"moonshotai/kimi-k2-thinking": {
|
|
id: "moonshotai/kimi-k2-thinking",
|
|
name: "Kimi K2 Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.5,
|
|
cacheRead: 0.15,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262114,
|
|
maxTokens: 262114,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"moonshotai/kimi-k2.5": {
|
|
id: "moonshotai/kimi-k2.5",
|
|
name: "Kimi K2.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 3,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262114,
|
|
maxTokens: 262114,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"moonshotai/kimi-k2.6": {
|
|
id: "moonshotai/kimi-k2.6",
|
|
name: "Kimi K2.6",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.16,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262000,
|
|
maxTokens: 262000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"moonshotai/kimi-k2.7-code": {
|
|
id: "moonshotai/kimi-k2.7-code",
|
|
name: "Kimi K2.7 Code",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.95,
|
|
output: 4,
|
|
cacheRead: 0.19,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"moonshotai/kimi-k2.7-code-highspeed": {
|
|
id: "moonshotai/kimi-k2.7-code-highspeed",
|
|
name: "Kimi K2.7 Code High Speed",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.9,
|
|
output: 8,
|
|
cacheRead: 0.38,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"nvidia/nemotron-3-super-120b-a12b": {
|
|
id: "nvidia/nemotron-3-super-120b-a12b",
|
|
name: "NVIDIA Nemotron 3 Super 120B A12B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.15,
|
|
output: 0.65,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"nvidia/nemotron-3-ultra-550b-a55b": {
|
|
id: "nvidia/nemotron-3-ultra-550b-a55b",
|
|
name: "Nemotron 3 Ultra",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.4,
|
|
cacheRead: 0.12,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 65000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"nvidia/nemotron-nano-12b-v2-vl": {
|
|
id: "nvidia/nemotron-nano-12b-v2-vl",
|
|
name: "Nvidia Nemotron Nano 12B V2 VL",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.6,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"nvidia/nemotron-nano-9b-v2": {
|
|
id: "nvidia/nemotron-nano-9b-v2",
|
|
name: "Nvidia Nemotron Nano 9B V2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.23,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-4-turbo": {
|
|
id: "openai/gpt-4-turbo",
|
|
name: "GPT-4 Turbo",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 30,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 4096,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-4.1": {
|
|
id: "openai/gpt-4.1",
|
|
name: "GPT-4.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-4.1-mini": {
|
|
id: "openai/gpt-4.1-mini",
|
|
name: "GPT-4.1 mini",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 1.6,
|
|
cacheRead: 0.1,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-4.1-nano": {
|
|
id: "openai/gpt-4.1-nano",
|
|
name: "GPT-4.1 nano",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.4,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1047576,
|
|
maxTokens: 32768,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-4o": {
|
|
id: "openai/gpt-4o",
|
|
name: "GPT-4o",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 10,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-4o-mini": {
|
|
id: "openai/gpt-4o-mini",
|
|
name: "GPT-4o mini",
|
|
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: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5": {
|
|
id: "openai/gpt-5",
|
|
name: "GPT-5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5-chat": {
|
|
id: "openai/gpt-5-chat",
|
|
name: "GPT 5 Chat",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5-codex": {
|
|
id: "openai/gpt-5-codex",
|
|
name: "GPT-5-Codex",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5-mini": {
|
|
id: "openai/gpt-5-mini",
|
|
name: "GPT-5 mini",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5-nano": {
|
|
id: "openai/gpt-5-nano",
|
|
name: "GPT-5 nano",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.4,
|
|
cacheRead: 0.005,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5-pro": {
|
|
id: "openai/gpt-5-pro",
|
|
name: "GPT-5 pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 120,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 272000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.1-codex": {
|
|
id: "openai/gpt-5.1-codex",
|
|
name: "GPT-5.1-Codex",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.1-codex-max": {
|
|
id: "openai/gpt-5.1-codex-max",
|
|
name: "GPT 5.1 Codex Max",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.1-codex-mini": {
|
|
id: "openai/gpt-5.1-codex-mini",
|
|
name: "GPT 5.1 Codex Mini",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.25,
|
|
output: 2,
|
|
cacheRead: 0.025,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.1-instant": {
|
|
id: "openai/gpt-5.1-instant",
|
|
name: "GPT-5.1 Instant",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.1-thinking": {
|
|
id: "openai/gpt-5.1-thinking",
|
|
name: "GPT 5.1 Thinking",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 10,
|
|
cacheRead: 0.125,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.2": {
|
|
id: "openai/gpt-5.2",
|
|
name: "GPT 5.2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.2-chat": {
|
|
id: "openai/gpt-5.2-chat",
|
|
name: "GPT 5.2 Chat",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.2-codex": {
|
|
id: "openai/gpt-5.2-codex",
|
|
name: "GPT 5.2 Codex",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.2-pro": {
|
|
id: "openai/gpt-5.2-pro",
|
|
name: "GPT 5.2 ",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 21,
|
|
output: 168,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.3-chat": {
|
|
id: "openai/gpt-5.3-chat",
|
|
name: "GPT-5.3 Chat",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 16384,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.3-codex": {
|
|
id: "openai/gpt-5.3-codex",
|
|
name: "GPT 5.3 Codex",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.75,
|
|
output: 14,
|
|
cacheRead: 0.175,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.4": {
|
|
id: "openai/gpt-5.4",
|
|
name: "GPT 5.4",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2.5,
|
|
output: 15,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.4-mini": {
|
|
id: "openai/gpt-5.4-mini",
|
|
name: "GPT 5.4 Mini",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.75,
|
|
output: 4.5,
|
|
cacheRead: 0.075,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.4-nano": {
|
|
id: "openai/gpt-5.4-nano",
|
|
name: "GPT 5.4 Nano",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.25,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 400000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.4-pro": {
|
|
id: "openai/gpt-5.4-pro",
|
|
name: "GPT 5.4 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.5": {
|
|
id: "openai/gpt-5.5",
|
|
name: "GPT 5.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh"},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 5,
|
|
output: 30,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-5.5-pro": {
|
|
id: "openai/gpt-5.5-pro",
|
|
name: "GPT 5.5 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
thinkingLevelMap: {"xhigh":"xhigh","off":null,"minimal":null,"low":null},
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 30,
|
|
output: 180,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
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: 0.35,
|
|
output: 0.75,
|
|
cacheRead: 0.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-oss-20b": {
|
|
id: "openai/gpt-oss-20b",
|
|
name: "GPT OSS 20B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.05,
|
|
output: 0.2,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/gpt-oss-safeguard-20b": {
|
|
id: "openai/gpt-oss-safeguard-20b",
|
|
name: "GPT OSS Safeguard 20B",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.075,
|
|
output: 0.3,
|
|
cacheRead: 0.037,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/o1": {
|
|
id: "openai/o1",
|
|
name: "o1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 15,
|
|
output: 60,
|
|
cacheRead: 7.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/o3": {
|
|
id: "openai/o3",
|
|
name: "o3",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 2,
|
|
output: 8,
|
|
cacheRead: 0.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/o3-deep-research": {
|
|
id: "openai/o3-deep-research",
|
|
name: "o3-deep-research",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 10,
|
|
output: 40,
|
|
cacheRead: 2.5,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/o3-mini": {
|
|
id: "openai/o3-mini",
|
|
name: "o3-mini",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.55,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/o3-pro": {
|
|
id: "openai/o3-pro",
|
|
name: "o3 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 20,
|
|
output: 80,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"openai/o4-mini": {
|
|
id: "openai/o4-mini",
|
|
name: "o4-mini",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.1,
|
|
output: 4.4,
|
|
cacheRead: 0.275,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 100000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"perplexity/sonar": {
|
|
id: "perplexity/sonar",
|
|
name: "Sonar",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 127000,
|
|
maxTokens: 8000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"perplexity/sonar-pro": {
|
|
id: "perplexity/sonar-pro",
|
|
name: "Sonar Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 8000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"stepfun/step-3.5-flash": {
|
|
id: "stepfun/step-3.5-flash",
|
|
name: "StepFun 3.5 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.09,
|
|
output: 0.3,
|
|
cacheRead: 0,
|
|
cacheWrite: 0.02,
|
|
},
|
|
contextWindow: 262114,
|
|
maxTokens: 262114,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"stepfun/step-3.7-flash": {
|
|
id: "stepfun/step-3.7-flash",
|
|
name: "Step 3.7 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.15,
|
|
cacheRead: 0.04,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-4.1-fast-non-reasoning": {
|
|
id: "xai/grok-4.1-fast-non-reasoning",
|
|
name: "Grok 4.1 Fast Non-Reasoning",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.5,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 1000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-4.1-fast-reasoning": {
|
|
id: "xai/grok-4.1-fast-reasoning",
|
|
name: "Grok 4.1 Fast Reasoning",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 0.5,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 1000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-4.20-multi-agent": {
|
|
id: "xai/grok-4.20-multi-agent",
|
|
name: "Grok 4.20 Multi-Agent",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 2000000,
|
|
maxTokens: 2000000,
|
|
} 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", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 2000000,
|
|
maxTokens: 2000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-4.20-non-reasoning": {
|
|
id: "xai/grok-4.20-non-reasoning",
|
|
name: "Grok 4.20 Non-Reasoning",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
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: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 2000000,
|
|
maxTokens: 2000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-4.20-reasoning": {
|
|
id: "xai/grok-4.20-reasoning",
|
|
name: "Grok 4.20 Reasoning",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
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: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 2000000,
|
|
maxTokens: 2000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-4.3": {
|
|
id: "xai/grok-4.3",
|
|
name: "Grok 4.3",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 1000000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xai/grok-build-0.1": {
|
|
id: "xai/grok-build-0.1",
|
|
name: "Grok Build 0.1",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xiaomi/mimo-v2-flash": {
|
|
id: "xiaomi/mimo-v2-flash",
|
|
name: "MiMo V2 Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 32000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xiaomi/mimo-v2-pro": {
|
|
id: "xiaomi/mimo-v2-pro",
|
|
name: "MiMo V2 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xiaomi/mimo-v2.5": {
|
|
id: "xiaomi/mimo-v2.5",
|
|
name: "MiMo M2.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.14,
|
|
output: 0.28,
|
|
cacheRead: 0.0028,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 131100,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"xiaomi/mimo-v2.5-pro": {
|
|
id: "xiaomi/mimo-v2.5-pro",
|
|
name: "MiMo V2.5 Pro",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.435,
|
|
output: 0.87,
|
|
cacheRead: 0.0036,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1050000,
|
|
maxTokens: 131000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.5": {
|
|
id: "zai/glm-4.5",
|
|
name: "GLM-4.5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.2,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 96000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.5-air": {
|
|
id: "zai/glm-4.5-air",
|
|
name: "GLM 4.5 Air",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.1,
|
|
cacheRead: 0.03,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 96000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.5v": {
|
|
id: "zai/glm-4.5v",
|
|
name: "GLM 4.5V",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 1.8,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 66000,
|
|
maxTokens: 16000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.6": {
|
|
id: "zai/glm-4.6",
|
|
name: "GLM 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.6,
|
|
output: 2.2,
|
|
cacheRead: 0.11,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 96000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.6v": {
|
|
id: "zai/glm-4.6v",
|
|
name: "GLM-4.6V",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.3,
|
|
output: 0.9,
|
|
cacheRead: 0.05,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 24000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.6v-flash": {
|
|
id: "zai/glm-4.6v-flash",
|
|
name: "GLM-4.6V-Flash",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 128000,
|
|
maxTokens: 24000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-4.7": {
|
|
id: "zai/glm-4.7",
|
|
name: "GLM 4.7",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 2.25,
|
|
output: 2.75,
|
|
cacheRead: 2.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131000,
|
|
maxTokens: 40000,
|
|
} 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: 0.4,
|
|
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",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.06,
|
|
output: 0.4,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-5": {
|
|
id: "zai/glm-5",
|
|
name: "GLM 5",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3.2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202800,
|
|
maxTokens: 131100,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-5-turbo": {
|
|
id: "zai/glm-5-turbo",
|
|
name: "GLM 5 Turbo",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.2,
|
|
output: 4,
|
|
cacheRead: 0.24,
|
|
cacheWrite: 0,
|
|
},
|
|
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", "image"],
|
|
cost: {
|
|
input: 1.4,
|
|
output: 4.4,
|
|
cacheRead: 0.26,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 202800,
|
|
maxTokens: 64000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-5.2": {
|
|
id: "zai/glm-5.2",
|
|
name: "GLM 5.2",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.5,
|
|
output: 4.5,
|
|
cacheRead: 0.3,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
"zai/glm-5v-turbo": {
|
|
id: "zai/glm-5v-turbo",
|
|
name: "GLM 5V Turbo",
|
|
api: "anthropic-messages",
|
|
provider: "vercel-ai-gateway",
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.2,
|
|
output: 4,
|
|
cacheRead: 0.24,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 128000,
|
|
} satisfies Model<"anthropic-messages">,
|
|
},
|
|
"xai": {
|
|
"grok-3": {
|
|
id: "grok-3",
|
|
name: "Grok 3",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 3,
|
|
output: 15,
|
|
cacheRead: 0.75,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"grok-3-fast": {
|
|
id: "grok-3-fast",
|
|
name: "Grok 3 Fast",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 5,
|
|
output: 25,
|
|
cacheRead: 1.25,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
"grok-4.20-0309-non-reasoning": {
|
|
id: "grok-4.20-0309-non-reasoning",
|
|
name: "Grok 4.20 (Non-Reasoning)",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: false,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 30000,
|
|
} satisfies Model<"openai-completions">,
|
|
"grok-4.20-0309-reasoning": {
|
|
id: "grok-4.20-0309-reasoning",
|
|
name: "Grok 4.20 (Reasoning)",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 30000,
|
|
} satisfies Model<"openai-completions">,
|
|
"grok-4.3": {
|
|
id: "grok-4.3",
|
|
name: "Grok 4.3",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1.25,
|
|
output: 2.5,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 30000,
|
|
} satisfies Model<"openai-completions">,
|
|
"grok-build-0.1": {
|
|
id: "grok-build-0.1",
|
|
name: "Grok Build 0.1",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 1,
|
|
output: 2,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 256000,
|
|
maxTokens: 256000,
|
|
} satisfies Model<"openai-completions">,
|
|
"grok-code-fast-1": {
|
|
id: "grok-code-fast-1",
|
|
name: "Grok Code Fast 1",
|
|
api: "openai-completions",
|
|
provider: "xai",
|
|
baseUrl: "https://api.x.ai/v1",
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.2,
|
|
output: 1.5,
|
|
cacheRead: 0.02,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 32768,
|
|
maxTokens: 8192,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"xiaomi": {
|
|
"mimo-v2-flash": {
|
|
id: "mimo-v2-flash",
|
|
name: "MiMo-V2-Flash",
|
|
api: "openai-completions",
|
|
provider: "xiaomi",
|
|
baseUrl: "https://api.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0.1,
|
|
output: 0.3,
|
|
cacheRead: 0.01,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 65536,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2-omni": {
|
|
id: "mimo-v2-omni",
|
|
name: "MiMo-V2-Omni",
|
|
api: "openai-completions",
|
|
provider: "xiaomi",
|
|
baseUrl: "https://api.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2-pro": {
|
|
id: "mimo-v2-pro",
|
|
name: "MiMo-V2-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi",
|
|
baseUrl: "https://api.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5": {
|
|
id: "mimo-v2.5",
|
|
name: "MiMo-V2.5",
|
|
api: "openai-completions",
|
|
provider: "xiaomi",
|
|
baseUrl: "https://api.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro": {
|
|
id: "mimo-v2.5-pro",
|
|
name: "MiMo-V2.5-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi",
|
|
baseUrl: "https://api.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro-ultraspeed": {
|
|
id: "mimo-v2.5-pro-ultraspeed",
|
|
name: "MiMo-V2.5-Pro-UltraSpeed",
|
|
api: "openai-completions",
|
|
provider: "xiaomi",
|
|
baseUrl: "https://api.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.305,
|
|
output: 2.61,
|
|
cacheRead: 0.0108,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"xiaomi-token-plan-ams": {
|
|
"mimo-v2-omni": {
|
|
id: "mimo-v2-omni",
|
|
name: "MiMo-V2-Omni",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-ams",
|
|
baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2-pro": {
|
|
id: "mimo-v2-pro",
|
|
name: "MiMo-V2-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-ams",
|
|
baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5": {
|
|
id: "mimo-v2.5",
|
|
name: "MiMo-V2.5",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-ams",
|
|
baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro": {
|
|
id: "mimo-v2.5-pro",
|
|
name: "MiMo-V2.5-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-ams",
|
|
baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro-ultraspeed": {
|
|
id: "mimo-v2.5-pro-ultraspeed",
|
|
name: "MiMo-V2.5-Pro-UltraSpeed",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-ams",
|
|
baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.305,
|
|
output: 2.61,
|
|
cacheRead: 0.0108,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"xiaomi-token-plan-cn": {
|
|
"mimo-v2-omni": {
|
|
id: "mimo-v2-omni",
|
|
name: "MiMo-V2-Omni",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-cn",
|
|
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2-pro": {
|
|
id: "mimo-v2-pro",
|
|
name: "MiMo-V2-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-cn",
|
|
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5": {
|
|
id: "mimo-v2.5",
|
|
name: "MiMo-V2.5",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-cn",
|
|
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro": {
|
|
id: "mimo-v2.5-pro",
|
|
name: "MiMo-V2.5-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-cn",
|
|
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro-ultraspeed": {
|
|
id: "mimo-v2.5-pro-ultraspeed",
|
|
name: "MiMo-V2.5-Pro-UltraSpeed",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-cn",
|
|
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.305,
|
|
output: 2.61,
|
|
cacheRead: 0.0108,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"xiaomi-token-plan-sgp": {
|
|
"mimo-v2-omni": {
|
|
id: "mimo-v2-omni",
|
|
name: "MiMo-V2-Omni",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-sgp",
|
|
baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 262144,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2-pro": {
|
|
id: "mimo-v2-pro",
|
|
name: "MiMo-V2-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-sgp",
|
|
baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5": {
|
|
id: "mimo-v2.5",
|
|
name: "MiMo-V2.5",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-sgp",
|
|
baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0.4,
|
|
output: 2,
|
|
cacheRead: 0.08,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro": {
|
|
id: "mimo-v2.5-pro",
|
|
name: "MiMo-V2.5-Pro",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-sgp",
|
|
baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1,
|
|
output: 3,
|
|
cacheRead: 0.2,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"mimo-v2.5-pro-ultraspeed": {
|
|
id: "mimo-v2.5-pro-ultraspeed",
|
|
name: "MiMo-V2.5-Pro-UltraSpeed",
|
|
api: "openai-completions",
|
|
provider: "xiaomi-token-plan-sgp",
|
|
baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
|
|
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 1.305,
|
|
output: 2.61,
|
|
cacheRead: 0.0108,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1048576,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"zai": {
|
|
"glm-4.5-air": {
|
|
id: "glm-4.5-air",
|
|
name: "GLM-4.5-Air",
|
|
api: "openai-completions",
|
|
provider: "zai",
|
|
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 98304,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-4.7": {
|
|
id: "glm-4.7",
|
|
name: "GLM-4.7",
|
|
api: "openai-completions",
|
|
provider: "zai",
|
|
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5-turbo": {
|
|
id: "glm-5-turbo",
|
|
name: "GLM-5-Turbo",
|
|
api: "openai-completions",
|
|
provider: "zai",
|
|
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5.1": {
|
|
id: "glm-5.1",
|
|
name: "GLM-5.1",
|
|
api: "openai-completions",
|
|
provider: "zai",
|
|
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5.2": {
|
|
id: "glm-5.2",
|
|
name: "GLM-5.2",
|
|
api: "openai-completions",
|
|
provider: "zai",
|
|
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","supportsReasoningEffort":true,"zaiToolStream":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":"high","medium":"high","high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5v-turbo": {
|
|
id: "glm-5v-turbo",
|
|
name: "GLM-5V-Turbo",
|
|
api: "openai-completions",
|
|
provider: "zai",
|
|
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
"zai-coding-cn": {
|
|
"glm-4.5-air": {
|
|
id: "glm-4.5-air",
|
|
name: "GLM-4.5-Air",
|
|
api: "openai-completions",
|
|
provider: "zai-coding-cn",
|
|
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 131072,
|
|
maxTokens: 98304,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-4.7": {
|
|
id: "glm-4.7",
|
|
name: "GLM-4.7",
|
|
api: "openai-completions",
|
|
provider: "zai-coding-cn",
|
|
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 204800,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5-turbo": {
|
|
id: "glm-5-turbo",
|
|
name: "GLM-5-Turbo",
|
|
api: "openai-completions",
|
|
provider: "zai-coding-cn",
|
|
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5.1": {
|
|
id: "glm-5.1",
|
|
name: "GLM-5.1",
|
|
api: "openai-completions",
|
|
provider: "zai-coding-cn",
|
|
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5.2": {
|
|
id: "glm-5.2",
|
|
name: "GLM-5.2",
|
|
api: "openai-completions",
|
|
provider: "zai-coding-cn",
|
|
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","supportsReasoningEffort":true,"zaiToolStream":true},
|
|
reasoning: true,
|
|
thinkingLevelMap: {"minimal":null,"low":"high","medium":"high","high":"high","xhigh":"max"},
|
|
input: ["text"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 1000000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
"glm-5v-turbo": {
|
|
id: "glm-5v-turbo",
|
|
name: "GLM-5V-Turbo",
|
|
api: "openai-completions",
|
|
provider: "zai-coding-cn",
|
|
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
|
|
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: 200000,
|
|
maxTokens: 131072,
|
|
} satisfies Model<"openai-completions">,
|
|
},
|
|
} as const;
|