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

Merge main into model-registry

Browse Source
This commit is contained in:
Mario Zechner
2026-06-22 14:00:18 +02:00
parent 019b022068 717a8f958a
commit abbd911693
220 changed files with 10488 additions and 4354 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/providers/vercel-ai-gateway.models.ts
+145 -130
View File
@@ -98,7 +98,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 4,
cacheRead: 0,
cacheWrite: 0,
@@ -168,7 +168,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -268,7 +268,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 4,
cacheRead: 0,
cacheWrite: 0,
@@ -285,8 +285,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
input: 0.1,
output: 0.4,
cacheRead: 0.001,
cacheWrite: 0.125,
},
@@ -302,7 +302,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 2.4,
cacheRead: 0.04,
cacheWrite: 0.5,
@@ -320,7 +320,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.6,
output: 3.5999999999999996,
output: 3.6,
cacheRead: 0,
cacheWrite: 0,
},
@@ -338,7 +338,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.5,
output: 3,
cacheRead: 0.09999999999999999,
cacheRead: 0.1,
cacheWrite: 0.625,
},
contextWindow: 1000000,
@@ -370,8 +370,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
output: 1.5999999999999999,
input: 0.4,
output: 1.6,
cacheRead: 0.08,
cacheWrite: 0.5,
},
@@ -404,7 +404,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.7999999999999999,
input: 0.8,
output: 4,
cacheRead: 0.08,
cacheWrite: 1,
@@ -412,25 +412,6 @@ export const VERCEL_AI_GATEWAY_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",
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">,
"anthropic/claude-haiku-4.5": {
id: "anthropic/claude-haiku-4.5",
name: "Claude Haiku 4.5",
@@ -442,7 +423,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 5,
cacheRead: 0.09999999999999999,
cacheRead: 0.1,
cacheWrite: 1.25,
},
contextWindow: 200000,
@@ -635,7 +616,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.25,
output: 0.8999999999999999,
output: 0.9,
cacheRead: 0,
cacheWrite: 0,
},
@@ -653,7 +634,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -838,8 +819,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
input: 0.1,
output: 0.4,
cacheRead: 0.01,
cacheWrite: 0,
},
@@ -874,7 +855,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.5,
output: 3,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -891,7 +872,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 2,
output: 12,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -942,7 +923,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 2,
output: 12,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -992,7 +973,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.14,
output: 0.39999999999999997,
output: 0.4,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1010,7 +991,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 0.75,
cacheRead: 0.024999999999999998,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -1162,7 +1143,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.24,
output: 0.9700000000000001,
output: 0.97,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1178,7 +1159,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.16999999999999998,
input: 0.17,
output: 0.66,
cacheRead: 0,
cacheWrite: 0,
@@ -1332,7 +1313,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.3,
output: 0.8999999999999999,
output: 0.9,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1348,7 +1329,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 2,
cacheRead: 0,
cacheWrite: 0,
@@ -1365,7 +1346,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1382,7 +1363,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1399,8 +1380,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.09999999999999999,
output: 0.09999999999999999,
input: 0.1,
output: 0.1,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1433,7 +1414,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 2,
cacheRead: 0,
cacheWrite: 0,
@@ -1467,13 +1448,13 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.02,
output: 0.04,
input: 0.15,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"mistral/mistral-small": {
id: "mistral/mistral-small",
@@ -1484,7 +1465,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1535,7 +1516,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.5700000000000001,
input: 0.57,
output: 2.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1560,40 +1541,6 @@ export const VERCEL_AI_GATEWAY_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",
@@ -1605,7 +1552,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.6,
output: 3,
cacheRead: 0.09999999999999999,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 262114,
@@ -1628,6 +1575,40 @@ export const VERCEL_AI_GATEWAY_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">,
"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",
@@ -1671,7 +1652,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
@@ -1689,7 +1670,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.06,
output: 0.22999999999999998,
output: 0.23,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1739,9 +1720,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
output: 1.5999999999999999,
cacheRead: 0.09999999999999999,
input: 0.4,
output: 1.6,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 1047576,
@@ -1756,9 +1737,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
cacheRead: 0.024999999999999998,
input: 0.1,
output: 0.4,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 1047576,
@@ -1860,7 +1841,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.024999999999999998,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -1875,8 +1856,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.049999999999999996,
output: 0.39999999999999997,
input: 0.05,
output: 0.4,
cacheRead: 0.005,
cacheWrite: 0,
},
@@ -1945,7 +1926,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.024999999999999998,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -2139,7 +2120,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
thinkingLevelMap: {"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 1.25,
cacheRead: 0.02,
cacheWrite: 0,
@@ -2227,8 +2208,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.049999999999999996,
output: 0.19999999999999998,
input: 0.05,
output: 0.2,
cacheRead: 0,
cacheWrite: 0,
},
@@ -2388,6 +2369,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 200000,
maxTokens: 8000,
} satisfies Model<"anthropic-messages">,
"sakana/fugu-ultra": {
id: "sakana/fugu-ultra",
name: "Fugu Ultra",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 5,
output: 30,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 1000000,
} satisfies Model<"anthropic-messages">,
"stepfun/step-3.5-flash": {
id: "stepfun/step-3.5-flash",
name: "StepFun 3.5 Flash",
@@ -2399,8 +2397,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.09,
output: 0.3,
cacheRead: 0,
cacheWrite: 0.02,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 262114,
maxTokens: 262114,
@@ -2414,7 +2412,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 1.15,
cacheRead: 0.04,
cacheWrite: 0,
@@ -2431,9 +2429,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 0.5,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2448,9 +2446,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 0.5,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2467,7 +2465,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2484,7 +2482,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2501,7 +2499,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2518,7 +2516,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2535,7 +2533,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2552,7 +2550,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2569,7 +2567,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2586,7 +2584,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 2,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -2601,7 +2599,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0.01,
cacheWrite: 0,
@@ -2620,7 +2618,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 3,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2686,7 +2684,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 1.1,
cacheRead: 0.03,
cacheWrite: 0,
@@ -2704,7 +2702,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.6,
output: 1.7999999999999998,
output: 1.8,
cacheRead: 0.11,
cacheWrite: 0,
},
@@ -2738,8 +2736,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.3,
output: 0.8999999999999999,
cacheRead: 0.049999999999999996,
output: 0.9,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -2789,7 +2787,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.07,
output: 0.39999999999999997,
output: 0.4,
cacheRead: 0,
cacheWrite: 0,
},
@@ -2806,7 +2804,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.06,
output: 0.39999999999999997,
output: 0.4,
cacheRead: 0.01,
cacheWrite: 0,
},
@@ -2823,8 +2821,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 1,
output: 3.1999999999999997,
cacheRead: 0.19999999999999998,
output: 3.2,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 202800,
@@ -2864,6 +2862,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
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",