ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Release v0.80.7

Browse Source
This commit is contained in:
Armin Ronacher
2026-07-14 18:36:46 +02:00
parent 53a087fe82
commit 818d67457c
31 changed files with 382 additions and 285 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/providers/amazon-bedrock.models.ts
+54
View File
@@ -1290,6 +1290,60 @@ export const AMAZON_BEDROCK_MODELS = {
contextWindow: 272000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"openai.gpt-5.6-luna": {
id: "openai.gpt-5.6-luna",
name: "GPT-5.6 Luna",
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: 1,
output: 6,
cacheRead: 0.1,
cacheWrite: 1.25,
},
contextWindow: 272000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"openai.gpt-5.6-sol": {
id: "openai.gpt-5.6-sol",
name: "GPT-5.6 Sol",
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: 30,
cacheRead: 0.5,
cacheWrite: 6.25,
},
contextWindow: 272000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"openai.gpt-5.6-terra": {
id: "openai.gpt-5.6-terra",
name: "GPT-5.6 Terra",
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: 2.5,
output: 15,
cacheRead: 0.25,
cacheWrite: 3.125,
},
contextWindow: 272000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"openai.gpt-oss-120b": {
id: "openai.gpt-oss-120b",
name: "gpt-oss-120b",
packages/ai/src/providers/azure-openai-responses.models.ts
+17
View File
@@ -660,6 +660,23 @@ export const AZURE_OPENAI_RESPONSES_MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"azure-openai-responses">,
"gpt-realtime-2.1": {
id: "gpt-realtime-2.1",
name: "GPT-Realtime-2.1",
api: "azure-openai-responses",
provider: "azure-openai-responses",
baseUrl: "",
reasoning: true,
input: ["text", "image"],
cost: {
input: 4,
output: 24,
cacheRead: 0.4,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 32000,
} satisfies Model<"azure-openai-responses">,
"o1": {
id: "o1",
name: "o1",
packages/ai/src/providers/cerebras.models.ts
+1 -1
View File
@@ -52,7 +52,7 @@ export const CEREBRAS_MODELS = {
cost: {
input: 2.25,
output: 2.75,
cacheRead: 0,
cacheRead: 2.25,
cacheWrite: 0,
},
contextWindow: 131072,
packages/ai/src/providers/cloudflare-ai-gateway.models.ts
+72
View File
@@ -528,6 +528,60 @@ export const CLOUDFLARE_AI_GATEWAY_MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-luna": {
id: "gpt-5.6-luna",
name: "GPT-5.6 Luna",
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","max":"max"},
input: ["text", "image"],
cost: {
input: 1,
output: 6,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-sol": {
id: "gpt-5.6-sol",
name: "GPT-5.6 Sol",
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","max":"max"},
input: ["text", "image"],
cost: {
input: 5,
output: 30,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-terra": {
id: "gpt-5.6-terra",
name: "GPT-5.6 Terra",
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","max":"max"},
input: ["text", "image"],
cost: {
input: 2.5,
output: 15,
cacheRead: 0.25,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"o1": {
id: "o1",
name: "o1",
@@ -685,4 +739,22 @@ export const CLOUDFLARE_AI_GATEWAY_MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"workers-ai/@cf/zai-org/glm-5.2": {
id: "workers-ai/@cf/zai-org/glm-5.2",
name: "Glm 5.2",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"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">,
} as const;
packages/ai/src/providers/github-copilot.models.ts
+58 -1
View File
@@ -253,7 +253,7 @@ export const GITHUB_COPILOT_MODELS = {
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 200000,
contextWindow: 1000000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"gemini-3.5-flash": {
@@ -446,6 +446,63 @@ export const GITHUB_COPILOT_MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-luna": {
id: "gpt-5.6-luna",
name: "GPT-5.6 Luna",
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","max":"max"},
input: ["text", "image"],
cost: {
input: 1,
output: 6,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-sol": {
id: "gpt-5.6-sol",
name: "GPT-5.6 Sol",
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","max":"max"},
input: ["text", "image"],
cost: {
input: 5,
output: 30,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-terra": {
id: "gpt-5.6-terra",
name: "GPT-5.6 Terra",
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","max":"max"},
input: ["text", "image"],
cost: {
input: 2.5,
output: 15,
cacheRead: 0.25,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"kimi-k2.7-code": {
id: "kimi-k2.7-code",
name: "Kimi K2.7 Code",
packages/ai/src/providers/openai.models.ts
+17
View File
@@ -674,6 +674,23 @@ export const OPENAI_MODELS = {
contextWindow: 272000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-realtime-2.1": {
id: "gpt-realtime-2.1",
name: "GPT-Realtime-2.1",
api: "openai-responses",
provider: "openai",
baseUrl: "https://api.openai.com/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 4,
output: 24,
cacheRead: 0.4,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 32000,
} satisfies Model<"openai-responses">,
"o1": {
id: "o1",
name: "o1",
packages/ai/src/providers/openrouter.models.ts
+57 -75
View File
@@ -462,24 +462,6 @@ export const OPENROUTER_MODELS = {
contextWindow: 262144,
maxTokens: 80000,
} 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",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
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",
@@ -688,8 +670,8 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.21,
output: 0.79,
input: 0.25,
output: 0.95,
cacheRead: 0.13,
cacheWrite: 0,
},
@@ -1122,13 +1104,13 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.12,
input: 0.06,
output: 0.35,
cacheRead: 0.09,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it:free": {
id: "google/gemma-4-31b-it:free",
@@ -1146,7 +1128,7 @@ export const OPENROUTER_MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 8192,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"ibm-granite/granite-4.1-8b": {
id: "ibm-granite/granite-4.1-8b",
@@ -1239,6 +1221,24 @@ export const OPENROUTER_MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kwaipilot: KAT-Coder-Air V2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: false,
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-pro-v2": {
id: "kwaipilot/kat-coder-pro-v2",
name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -1257,23 +1257,23 @@ export const OPENROUTER_MODELS = {
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)",
"kwaipilot/kat-coder-pro-v2.5": {
id: "kwaipilot/kat-coder-pro-v2.5",
name: "Kwaipilot: KAT-Coder-Pro V2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: true,
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
input: 0.74,
output: 2.96,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 4096,
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-70b-instruct": {
id: "meta-llama/llama-3.1-70b-instruct",
@@ -1357,8 +1357,8 @@ export const OPENROUTER_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
input: 0.2,
output: 0.8,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1866,7 +1866,7 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.07,
cacheWrite: 0,
},
contextWindow: 256000,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6": {
@@ -1897,9 +1897,9 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.72,
input: 0.719,
output: 3.49,
cacheRead: 0.159,
cacheRead: 0.149,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -2457,11 +2457,11 @@ export const OPENROUTER_MODELS = {
cost: {
input: 0.05,
output: 0.4,
cacheRead: 0.01,
cacheRead: 0.005,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 4096,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"openai/gpt-5-pro": {
id: "openai/gpt-5-pro",
@@ -2493,7 +2493,7 @@ export const OPENROUTER_MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -2977,26 +2977,8 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.036,
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",
compat: {"thinkingFormat":"openrouter"},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
input: 0.03,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
@@ -3482,7 +3464,7 @@ export const OPENROUTER_MODELS = {
input: ["text"],
cost: {
input: 0.09,
output: 0.1,
output: 0.55,
cacheRead: 0,
cacheWrite: 0,
},
@@ -4075,13 +4057,13 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.285,
input: 0.289,
output: 2.4,
cacheRead: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262140,
maxTokens: 262140,
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -4476,7 +4458,7 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 32000,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"xiaomi/mimo-v2.5-pro": {
@@ -4562,12 +4544,12 @@ export const OPENROUTER_MODELS = {
input: ["text"],
cost: {
input: 0.43,
output: 1.74,
output: 1.75,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
contextWindow: 198000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.6v": {
id: "z-ai/glm-4.6v",
@@ -4638,8 +4620,8 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.119,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 4096,
contextWindow: 198000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"z-ai/glm-5-turbo": {
id: "z-ai/glm-5-turbo",
@@ -4688,9 +4670,9 @@ export const OPENROUTER_MODELS = {
thinkingLevelMap: {"xhigh":"xhigh"},
input: ["text"],
cost: {
input: 0.84,
output: 2.64,
cacheRead: 0.156,
input: 0.924,
output: 2.904,
cacheRead: 0.1716,
cacheWrite: 0,
},
contextWindow: 1024000,
packages/ai/src/providers/vercel-ai-gateway.models.ts
+34 -136
View File
@@ -497,23 +497,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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-fable-5": {
id: "anthropic/claude-fable-5",
name: "Claude Fable 5",
@@ -565,7 +548,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cacheWrite: 18.75,
},
contextWindow: 200000,
maxTokens: 32000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-opus-4.1": {
id: "anthropic/claude-opus-4.1",
@@ -673,7 +656,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cacheWrite: 3.75,
},
contextWindow: 1000000,
maxTokens: 64000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-sonnet-4.5": {
id: "anthropic/claude-sonnet-4.5",
@@ -730,23 +713,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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",
@@ -875,12 +841,12 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.6,
output: 1.7,
cacheRead: 0,
input: 0.21,
output: 0.79,
cacheRead: 0.13,
cacheWrite: 0,
},
contextWindow: 128000,
contextWindow: 163840,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"deepseek/deepseek-v3.1-terminus": {
@@ -1206,6 +1172,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 1000000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
"kwaipilot/kat-coder-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kat Coder Air V2.5",
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: 0.03,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"anthropic-messages">,
"kwaipilot/kat-coder-pro-v1": {
id: "kwaipilot/kat-coder-pro-v1",
name: "KAT-Coder-Pro V1",
@@ -1240,39 +1223,22 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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">,
"meituan/longcat-flash-thinking-2601": {
id: "meituan/longcat-flash-thinking-2601",
name: "LongCat Flash Thinking 2601",
"kwaipilot/kat-coder-pro-v2.5": {
id: "kwaipilot/kat-coder-pro-v2.5",
name: "Kat Coder Pro V2.5",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
input: 0.74,
output: 2.96,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 32768,
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"anthropic-messages">,
"meta/llama-3.1-70b": {
id: "meta/llama-3.1-70b",
@@ -1580,23 +1546,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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",
@@ -1801,23 +1750,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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",
@@ -2972,40 +2904,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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",
@@ -3270,9 +3168,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 3,
output: 10.25,
cacheRead: 0.5,
input: 2.1,
output: 6.6,
cacheRead: 0.21,
cacheWrite: 0,
},
contextWindow: 1000000,