shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: commit pending workspace updates
Some checks failed
CI / build-check-test (push) Has been cancelled
Details

Browse Source
This commit is contained in:
树萌芽
2026-06-14 20:36:01 +08:00
parent 62e2866228
commit ad62015fe3
152 changed files with 338 additions and 23015 deletions
Download Patch File Download Diff File Expand all files Collapse all files

608
packages/ai/src/models.generated.ts
View File

@@ -2846,30 +2846,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.25,
output: 0.69,
input: 0.35,
output: 0.75,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"llama3.1-8b": {
id: "llama3.1-8b",
name: "Llama 3.1 8B",
api: "openai-completions",
provider: "cerebras",
baseUrl: "https://api.cerebras.ai/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.1,
output: 0.1,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32000,
maxTokens: 8000,
maxTokens: 40960,
} satisfies Model<"openai-completions">,
"zai-glm-4.7": {
id: "zai-glm-4.7",
@@ -2877,7 +2860,7 @@ export const MODELS = {
api: "openai-completions",
provider: "cerebras",
baseUrl: "https://api.cerebras.ai/v1",
reasoning: false,
reasoning: true,
input: ["text"],
cost: {
input: 2.25,
@@ -2886,7 +2869,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 40000,
maxTokens: 40960,
} satisfies Model<"openai-completions">,
},
"cloudflare-ai-gateway": {
@@ -3642,6 +3625,24 @@ export const MODELS = {
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",
@@ -3864,24 +3865,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/kimi-k2p5": {
id: "accounts/fireworks/models/kimi-k2p5",
name: "Kimi K2.5",
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: 0.6,
output: 3,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/kimi-k2p6": {
id: "accounts/fireworks/models/kimi-k2p6",
name: "Kimi K2.6",
@@ -3900,23 +3883,23 @@ export const MODELS = {
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/minimax-m2p5": {
id: "accounts/fireworks/models/minimax-m2p5",
name: "MiniMax-M2.5",
"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"],
input: ["text", "image"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.03,
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 196608,
maxTokens: 196608,
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/minimax-m2p7": {
id: "accounts/fireworks/models/minimax-m2p7",
@@ -3936,9 +3919,27 @@ export const MODELS = {
contextWindow: 196608,
maxTokens: 196608,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/qwen3p6-plus": {
id: "accounts/fireworks/models/qwen3p6-plus",
name: "Qwen 3.6 Plus",
"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",
@@ -3946,9 +3947,9 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.5,
output: 3,
cacheRead: 0.1,
input: 0.4,
output: 1.6,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -4008,8 +4009,45 @@ export const MODELS = {
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: 2,
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)",
@@ -5457,6 +5495,24 @@ export const MODELS = {
} 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",
@@ -6205,6 +6261,24 @@ export const MODELS = {
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},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
},
"moonshotai-cn": {
"kimi-k2-0711-preview": {
@@ -7202,23 +7276,6 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 32000,
} satisfies Model<"openai-completions">,
"claude-fable-5": {
id: "claude-fable-5",
name: "Claude Fable 5",
api: "anthropic-messages",
provider: "opencode",
baseUrl: "https://opencode.ai/zen",
reasoning: true,
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",
@@ -8051,23 +8108,6 @@ export const MODELS = {
contextWindow: 202752,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"kimi-k2.5": {
id: "kimi-k2.5",
name: "Kimi K2.5",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.6,
output: 3,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"kimi-k2.6": {
id: "kimi-k2.6",
name: "Kimi K2.6",
@@ -8085,6 +8125,23 @@ export const MODELS = {
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",
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",
@@ -8119,23 +8176,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"minimax-m2.5": {
id: "minimax-m2.5",
name: "MiniMax M2.5",
api: "anthropic-messages",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go",
reasoning: true,
input: ["text"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 204800,
maxTokens: 65536,
} satisfies Model<"anthropic-messages">,
"minimax-m2.7": {
id: "minimax-m2.7",
name: "MiniMax M2.7",
@@ -8155,16 +8195,16 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"minimax-m3": {
id: "minimax-m3",
name: "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: 0.3,
output: 1.2,
cacheRead: 0.06,
input: 0.1,
output: 0.4,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 512000,
@@ -8919,13 +8959,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
cost: {
input: 0.0983,
output: 0.1966,
cacheRead: 0.019700000000000002,
input: 0.09,
output: 0.18,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 131072,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
@@ -9245,12 +9285,12 @@ export const MODELS = {
input: ["text", "image"],
cost: {
input: 0.12,
output: 0.36,
output: 0.35,
cacheRead: 0.09,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 8192,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it:free": {
id: "google/gemma-4-31b-it:free",
@@ -9551,9 +9591,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.27,
output: 1.08,
cacheRead: 0.054,
input: 0.25,
output: 1,
cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 204800,
@@ -9950,22 +9990,22 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 262142,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6:free": {
id: "moonshotai/kimi-k2.6:free",
name: "MoonshotAI: Kimi K2.6 (free)",
"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,
output: 0,
cacheRead: 0,
input: 0.75,
output: 3.5,
cacheRead: 0.16,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 4096,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nex-agi/nex-n2-pro:free": {
id: "nex-agi/nex-n2-pro:free",
@@ -10137,23 +10177,6 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-nano-9b-v2": {
id: "nvidia/nemotron-nano-9b-v2",
name: "NVIDIA: Nemotron Nano 9B V2",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text"],
cost: {
input: 0.04,
output: 0.16,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-nano-9b-v2:free": {
id: "nvidia/nemotron-nano-9b-v2:free",
name: "NVIDIA: Nemotron Nano 9B V2 (free)",
@@ -11875,13 +11898,13 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.28900000000000003,
output: 2.4,
input: 0.28850000000000003,
output: 3.17,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
maxTokens: 262140,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -11892,13 +11915,13 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.14,
input: 0.15,
output: 1,
cacheRead: 0,
cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262140,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-flash": {
id: "qwen/qwen3.6-flash",
@@ -11977,10 +12000,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
output: 1.5999999999999999,
cacheRead: 0.08,
cacheWrite: 0.5,
input: 0.32,
output: 1.28,
cacheRead: 0.064,
cacheWrite: 0.39999999999999997,
},
contextWindow: 1000000,
maxTokens: 65536,
@@ -12565,25 +12588,6 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
},
"together": {
"MiniMaxAI/MiniMax-M2.5": {
id: "MiniMaxAI/MiniMax-M2.5",
name: "MiniMax-M2.5",
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},
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: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"MiniMaxAI/MiniMax-M2.7": {
id: "MiniMaxAI/MiniMax-M2.7",
name: "MiniMax-M2.7",
@@ -12603,28 +12607,28 @@ export const MODELS = {
contextWindow: 202752,
maxTokens: 131072,
} 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",
"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"],
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.6,
cacheRead: 0,
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
contextWindow: 524288,
maxTokens: 250000,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
name: "Qwen3 Coder 480B A35B Instruct",
"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",
@@ -12632,27 +12636,26 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 2,
output: 2,
input: 0.3,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
contextWindow: 32768,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-Next-FP8": {
id: "Qwen/Qwen3-Coder-Next-FP8",
name: "Qwen3 Coder Next FP8",
"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,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0.5,
output: 1.2,
input: 0.2,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
@@ -12678,6 +12681,25 @@ export const MODELS = {
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",
@@ -12703,9 +12725,8 @@ export const MODELS = {
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},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 2.5,
@@ -12716,44 +12737,6 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 500000,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V3": {
id: "deepseek-ai/DeepSeek-V3",
name: "DeepSeek-V3",
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: 1.25,
output: 1.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V3-1": {
id: "deepseek-ai/DeepSeek-V3-1",
name: "DeepSeek V3.1",
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: 0.6,
output: 1.7,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V4-Pro": {
id: "deepseek-ai/DeepSeek-V4-Pro",
name: "DeepSeek V4 Pro",
@@ -12765,8 +12748,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null},
input: ["text"],
cost: {
input: 2.1,
output: 4.4,
input: 1.74,
output: 3.48,
cacheRead: 0.2,
cacheWrite: 0,
},
@@ -12802,8 +12785,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.5,
input: 0.39,
output: 0.97,
cacheRead: 0,
cacheWrite: 0,
},
@@ -12828,25 +12811,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.5": {
id: "moonshotai/Kimi-K2.5",
name: "Kimi K2.5",
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", "image"],
cost: {
input: 0.5,
output: 2.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.6": {
id: "moonshotai/Kimi-K2.6",
name: "Kimi K2.6",
@@ -12904,6 +12868,44 @@ export const MODELS = {
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",
@@ -13333,23 +13335,6 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-fable-5": {
id: "anthropic/claude-fable-5",
name: "Claude Fable 5",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 10,
output: 50,
cacheRead: 1,
cacheWrite: 12.5,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-haiku-4.5": {
id: "anthropic/claude-haiku-4.5",
name: "Claude Haiku 4.5",
@@ -14474,40 +14459,6 @@ export const MODELS = {
contextWindow: 262114,
maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-thinking-turbo": {
id: "moonshotai/kimi-k2-thinking-turbo",
name: "Kimi K2 Thinking Turbo",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1.15,
output: 8,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 262114,
maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-turbo": {
id: "moonshotai/kimi-k2-turbo",
name: "Kimi K2 Turbo",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 1.15,
output: 8,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2.5": {
id: "moonshotai/kimi-k2.5",
name: "Kimi K2.5",
@@ -14542,6 +14493,23 @@ export const MODELS = {
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">,
"nvidia/nemotron-3-super-120b-a12b": {
id: "nvidia/nemotron-3-super-120b-a12b",
name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -16430,6 +16398,24 @@ export const MODELS = {
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","zaiToolStream":true},
reasoning: true,
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",