Skip to content

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust

Regenerate the model catalog (#1481)

Sebastian Müller941d7b3eb53c
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 9e95310f29..fb3d3447fb 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -796,6 +796,60 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "global.openai.gpt-5.6-luna": {
+ id: "global.openai.gpt-5.6-luna",
+ name: "GPT-5.6 Luna (Global)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.22,
+ output: 1.32,
+ cacheRead: 0.022,
+ cacheWrite: 0.275,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "global.openai.gpt-5.6-sol": {
+ id: "global.openai.gpt-5.6-sol",
+ name: "GPT-5.6 Sol (Global)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5.5,
+ output: 33,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "global.openai.gpt-5.6-terra": {
+ id: "global.openai.gpt-5.6-terra",
+ name: "GPT-5.6 Terra (Global)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.2,
+ output: 13.2,
+ cacheRead: 0.22,
+ cacheWrite: 2.75,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
"google.gemma-3-27b-it": {
id: "google.gemma-3-27b-it",
name: "Google Gemma 3 27B Instruct",
@@ -2992,23 +3046,6 @@ export const MODELS = {
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: 2.25,
- cacheWrite: 0,
- },
- contextWindow: 131072,
- maxTokens: 40960,
- } satisfies Model<"openai-completions">,
},
"cloudflare-ai-gateway": {
"claude-fable-5": {
@@ -3029,8 +3066,8 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
- "claude-haiku-4-5": {
- id: "claude-haiku-4-5",
+ "claude-haiku-4.5": {
+ id: "claude-haiku-4.5",
name: "Claude Haiku 4.5 (latest)",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3046,8 +3083,8 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
- "claude-opus-4-5": {
- id: "claude-opus-4-5",
+ "claude-opus-4.5": {
+ id: "claude-opus-4.5",
name: "Claude Opus 4.5 (latest)",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3063,8 +3100,8 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
- "claude-opus-4-6": {
- id: "claude-opus-4-6",
+ "claude-opus-4.6": {
+ id: "claude-opus-4.6",
name: "Claude Opus 4.6",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3081,8 +3118,8 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
- "claude-opus-4-7": {
- id: "claude-opus-4-7",
+ "claude-opus-4.7": {
+ id: "claude-opus-4.7",
name: "Claude Opus 4.7",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3099,8 +3136,8 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
- "claude-opus-4-8": {
- id: "claude-opus-4-8",
+ "claude-opus-4.8": {
+ id: "claude-opus-4.8",
name: "Claude Opus 4.8",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3135,8 +3172,8 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
- "claude-sonnet-4-5": {
- id: "claude-sonnet-4-5",
+ "claude-sonnet-4.5": {
+ id: "claude-sonnet-4.5",
name: "Claude Sonnet 4.5 (latest)",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3152,8 +3189,8 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
- "claude-sonnet-4-6": {
- id: "claude-sonnet-4-6",
+ "claude-sonnet-4.6": {
+ id: "claude-sonnet-4.6",
name: "Claude Sonnet 4.6",
api: "anthropic-messages",
provider: "cloudflare-ai-gateway",
@@ -3282,9 +3319,9 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 2.5,
- output: 10,
- cacheRead: 1.25,
+ input: 1.25,
+ output: 5,
+ cacheRead: 0.625,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -3299,9 +3336,9 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.15,
- output: 0.6,
- cacheRead: 0.075,
+ input: 0.075,
+ output: 0.3,
+ cacheRead: 0.0375,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -4039,7 +4076,7 @@ export const MODELS = {
cacheRead: 0.014,
cacheWrite: 0,
},
- contextWindow: 1048576,
+ contextWindow: 1310720,
maxTokens: 1048576,
} satisfies Model<"openai-completions">,
"@cf/deepseek-ai/deepseek-v4-pro-0813": {
@@ -6408,6 +6445,24 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
+ "Qwen/Qwen3.8-2.4T-A95B": {
+ id: "Qwen/Qwen3.8-2.4T-A95B",
+ name: "Qwen3.8 2.4T A95B",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 2.5,
+ output: 6.25,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"XiaomiMiMo/MiMo-V2-Flash": {
id: "XiaomiMiMo/MiMo-V2-Flash",
name: "MiMo-V2-Flash",
@@ -10220,9 +10275,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.14,
- output: 0.28,
- cacheRead: 0.0028,
+ input: 0.22,
+ output: 0.66,
+ cacheRead: 0.007,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -10239,9 +10294,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.435,
- output: 0.87,
- cacheRead: 0.003625,
+ input: 0.66,
+ output: 1.98,
+ cacheRead: 0.022,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -11333,12 +11388,12 @@ export const MODELS = {
input: ["text"],
cost: {
input: 0.27,
- output: 0.95,
- cacheRead: 0.13,
+ output: 1,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 32768,
+ maxTokens: 163840,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2": {
id: "deepseek/deepseek-v3.2",
@@ -11389,9 +11444,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.061459999999999994,
- output: 0.12291999999999999,
- cacheRead: 0.012292,
+ input: 0.0798,
+ output: 0.1596,
+ cacheRead: 0.01596,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11413,12 +11468,12 @@ export const MODELS = {
cacheRead: 0.028,
cacheWrite: 0,
},
- contextWindow: 1048576,
+ contextWindow: 1310720,
maxTokens: 393216,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
- name: "DeepSeek: DeepSeek V4 Pro",
+ name: "DeepSeek: DeepSeek V4 Pro 0423",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -11427,13 +11482,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 1.1680000000000001,
- output: 2.3360000000000003,
- cacheRead: 0.09855000000000001,
+ input: 0.66,
+ output: 1.9800000000000002,
+ cacheRead: 0.022,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 393216,
+ maxTokens: 384000,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro-0813": {
id: "deepseek/deepseek-v4-pro-0813",
@@ -11446,9 +11501,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.435,
- output: 0.87,
- cacheRead: 0.003625,
+ input: 0.66,
+ output: 1.9800000000000002,
+ cacheRead: 0.022,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11794,13 +11849,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.12,
- output: 0.39999999999999997,
- cacheRead: 0.049999999999999996,
+ input: 0.07,
+ output: 0.33999999999999997,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"google/gemma-4-26b-a4b-it:free": {
id: "google/gemma-4-26b-a4b-it:free",
@@ -12664,9 +12719,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.5415,
- output: 2.2800000000000002,
- cacheRead: 0.09119999999999999,
+ input: 0.5605,
+ output: 2.36,
+ cacheRead: 0.0944,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -12760,11 +12815,11 @@ export const MODELS = {
cost: {
input: 0.049999999999999996,
output: 0.19999999999999998,
- cacheRead: 0.024999999999999998,
+ cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 228000,
+ maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-30b-a3b:free": {
id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -12887,13 +12942,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.09999999999999999,
- output: 0.25,
- cacheRead: 0.049999999999999996,
+ input: 0.08,
+ output: 0.19999999999999998,
+ cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 1000000,
- maxTokens: 262144,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3.5-lightning:free": {
id: "nvidia/nemotron-3.5-lightning:free",
@@ -13559,10 +13614,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 0.09999999999999999,
- output: 0.6,
- cacheRead: 0.01,
- cacheWrite: 0.125,
+ input: 0.19999999999999998,
+ output: 1.2,
+ cacheRead: 0.02,
+ cacheWrite: 0.25,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -13577,10 +13632,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 0.09999999999999999,
- output: 0.6,
- cacheRead: 0.01,
- cacheWrite: 0.125,
+ input: 0.19999999999999998,
+ output: 1.2,
+ cacheRead: 0.02,
+ cacheWrite: 0.25,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -13595,10 +13650,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -13631,10 +13686,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 1,
- output: 6,
- cacheRead: 0.09999999999999999,
- cacheWrite: 1.25,
+ input: 2,
+ output: 12,
+ cacheRead: 0.19999999999999998,
+ cacheWrite: 2.5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -13649,10 +13704,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 1,
- output: 6,
- cacheRead: 0.09999999999999999,
- cacheWrite: 1.25,
+ input: 2,
+ output: 12,
+ cacheRead: 0.19999999999999998,
+ cacheWrite: 2.5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -14459,9 +14514,9 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.26,
- output: 1.04,
- cacheRead: 0,
+ input: 0.21,
+ output: 1.9,
+ cacheRead: 0.09999999999999999,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -14738,13 +14793,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.6,
- output: 3.5999999999999996,
- cacheRead: 0.12,
+ input: 0.28900000000000003,
+ output: 2.4,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -14757,7 +14812,7 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.15,
+ input: 0.14,
output: 1,
cacheRead: 0.049999999999999996,
cacheWrite: 0,
@@ -14909,7 +14964,7 @@ export const MODELS = {
cost: {
input: 0.44999999999999996,
output: 3.1999999999999997,
- cacheRead: 0,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -15382,9 +15437,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.55,
- output: 2.2,
- cacheRead: 0.11,
+ input: 0.5,
+ output: 2,
+ cacheRead: 0.09999999999999999,
cacheWrite: 0,
},
contextWindow: 204800,
@@ -15514,13 +15569,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":null},
input: ["text"],
cost: {
- input: 0.308,
- output: 0.9680000000000001,
- cacheRead: 0.0572,
+ input: 0.49,
+ output: 1.54,
+ cacheRead: 0.091,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 128000,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"z-ai/glm-5v-turbo": {
id: "z-ai/glm-5v-turbo",
@@ -15625,13 +15680,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.063,
- output: 0.126,
- cacheRead: 0.0126,
+ input: 0.078596,
+ output: 0.157192,
+ cacheRead: 0.015719200000000003,
cacheWrite: 0,
},
- contextWindow: 1048576,
- maxTokens: 262144,
+ contextWindow: 1310720,
+ maxTokens: 384000,
} satisfies Model<"openai-completions">,
"~google/gemini-flash-latest": {
id: "~google/gemini-flash-latest",
@@ -15679,13 +15734,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 2.8,
- output: 14,
+ input: 2.6,
+ output: 13,
cacheRead: 0.29,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 1048576,
+ maxTokens: 974842,
} satisfies Model<"openai-completions">,
"~openai/gpt-latest": {
id: "~openai/gpt-latest",
@@ -15697,10 +15752,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -16051,7 +16106,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 32768,
+ maxTokens: 163840,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2": {
id: "deepseek/deepseek-v3.2",
@@ -16128,7 +16183,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1048576,
+ contextWindow: 1310720,
maxTokens: 393216,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
@@ -16148,7 +16203,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 393216,
+ maxTokens: 384000,
featured: true,
} satisfies Model<"openai-completions">,
"google/gemini-2.5-flash": {
@@ -16618,7 +16673,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 228000,
+ maxTokens: 262144,
featured: true,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b": {
@@ -17433,7 +17488,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -17723,7 +17778,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 128000,
+ maxTokens: 131072,
featured: true,
} satisfies Model<"openai-completions">,
},
@@ -18164,12 +18219,29 @@ export const MODELS = {
cost: {
input: 2,
output: 6,
- cacheRead: 0.25,
+ cacheRead: 0.19999999999999998,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
+ "alibaba/qwen3.8-27b": {
+ id: "alibaba/qwen3.8-27b",
+ name: "Qwen3.8 27B",
+ 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: 262144,
+ maxTokens: 262133,
+ } satisfies Model<"anthropic-messages">,
"alibaba/qwen3.8-max": {
id: "alibaba/qwen3.8-max",
name: "Qwen 3.8 Max",
@@ -18715,9 +18787,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.19999999999999998,
- output: 0.39999999999999997,
- cacheRead: 0.04,
+ input: 0.13,
+ output: 0.26,
+ cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -18732,9 +18804,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.19999999999999998,
- output: 0.39999999999999997,
- cacheRead: 0.04,
+ input: 0.13,
+ output: 0.26,
+ cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -18919,9 +18991,9 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 1.5,
- output: 7.5,
- cacheRead: 0.15,
+ input: 0.75,
+ output: 3.75,
+ cacheRead: 0.075,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -19830,6 +19902,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 65000,
} satisfies Model<"anthropic-messages">,
+ "nvidia/nemotron-3.5-lightning": {
+ id: "nvidia/nemotron-3.5-lightning",
+ name: "Nemotron 3.5 Lightning 30B",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
"nvidia/nemotron-nano-12b-v2-vl": {
id: "nvidia/nemotron-nano-12b-v2-vl",
name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -20344,10 +20433,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 2.5,
+ output: 15,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
},
contextWindow: 1050000,
maxTokens: 128000,
diff --git a/packages/ai/test/cross-provider-handoff.test.ts b/packages/ai/test/cross-provider-handoff.test.ts
index 9407119b37..69bb2fdc59 100644
--- a/packages/ai/test/cross-provider-handoff.test.ts
+++ b/packages/ai/test/cross-provider-handoff.test.ts
@@ -73,9 +73,9 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
{ provider: "prime-inference", model: "openai/gpt-5.5", label: "prime-inference-gpt-5.5" },
// GitHub Copilot
{ provider: "github-copilot", model: "claude-sonnet-4.5", label: "copilot-claude-sonnet-4.5" },
- { provider: "github-copilot", model: "gpt-5.1-codex", label: "copilot-gpt-5.1-codex" },
- { provider: "github-copilot", model: "gemini-3-flash-preview", label: "copilot-gemini-3-flash-preview" },
- { provider: "github-copilot", model: "grok-code-fast-1", label: "copilot-grok-code-fast-1" },
+ { provider: "github-copilot", model: "gpt-5.2-codex", label: "copilot-gpt-5.2-codex" },
+ { provider: "github-copilot", model: "gemini-3.5-flash", label: "copilot-gemini-3.5-flash" },
+ { provider: "github-copilot", model: "grok-4.5", label: "copilot-grok-4.5" },
// Amazon Bedrock
{
provider: "amazon-bedrock",
@@ -85,7 +85,7 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
// xAI
{ provider: "xai", model: "grok-code-fast-1", label: "xai-grok-code-fast-1" },
// Cerebras
- { provider: "cerebras", model: "zai-glm-4.7", label: "cerebras-zai-glm-4.7" },
+ { provider: "cerebras", model: "gpt-oss-120b", label: "cerebras-gpt-oss-120b" },
// Cloudflare Workers AI
{ provider: "cloudflare-workers-ai", model: "@cf/moonshotai/kimi-k2.6", label: "cloudflare-kimi-k2.6" },
// Cloudflare AI Gateway
@@ -96,8 +96,8 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
},
{
provider: "cloudflare-ai-gateway",
- model: "claude-sonnet-4-5",
- label: "cloudflare-gateway-claude-sonnet-4-5",
+ model: "claude-sonnet-4.5",
+ label: "cloudflare-gateway-claude-sonnet-4.5",
upstreamApiKeyEnv: "ANTHROPIC_API_KEY",
},
{
@@ -121,12 +121,12 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
{ provider: "opencode", model: "big-pickle", label: "zen-big-pickle" },
{ provider: "opencode", model: "claude-sonnet-4-5", label: "zen-claude-sonnet-4-5" },
{ provider: "opencode", model: "gemini-3-flash", label: "zen-gemini-3-flash" },
- { provider: "opencode", model: "glm-4.7-free", label: "zen-glm-4.7-free" },
+ { provider: "opencode", model: "glm-5.2", label: "zen-glm-5.2" },
{ provider: "opencode", model: "gpt-5.2-codex", label: "zen-gpt-5.2-codex" },
- { provider: "opencode", model: "minimax-m2.1-free", label: "zen-minimax-m2.1-free" },
+ { provider: "opencode", model: "minimax-m2.7", label: "zen-minimax-m2.7" },
// OpenCode Go
- { provider: "opencode-go", model: "kimi-k2.5", label: "go-kimi-k2.5" },
- { provider: "opencode-go", model: "minimax-m2.5", label: "go-minimax-m2.5" },
+ { provider: "opencode-go", model: "kimi-k2.6", label: "go-kimi-k2.6" },
+ { provider: "opencode-go", model: "minimax-m2.7", label: "go-minimax-m2.7" },
// Xiaomi MiMo
{ provider: "xiaomi", model: "mimo-v2.5-pro", label: "xiaomi-mimo-v2.5-pro" },
{ provider: "xiaomi-token-plan-cn", model: "mimo-v2.5-pro", label: "xiaomi-token-plan-cn-mimo-v2.5-pro" },
@@ -134,6 +134,19 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
{ provider: "xiaomi-token-plan-sgp", model: "mimo-v2.5-pro", label: "xiaomi-token-plan-sgp-mimo-v2.5-pro" },
];
+function resolveProviderModel(pair: ProviderModelPair): Model<Api> | undefined {
+ return (getModel as (provider: string, model: string) => Model<Api> | undefined)(pair.provider, pair.model);
+}
+
+describe("Cross-Provider Handoff configuration", () => {
+ it("references models in the generated catalog", () => {
+ const missingModels = PROVIDER_MODEL_PAIRS.filter((pair) => !resolveProviderModel(pair)).map(
+ (pair) => `${pair.provider}/${pair.model}`,
+ );
+ expect(missingModels).toEqual([]);
+ });
+});
+
// Cached context structure
interface CachedContext {
label: string;
@@ -203,7 +216,7 @@ async function generateContext(
pair: ProviderModelPair,
apiKey: string,
): Promise<{ messages: Message[]; api: Api } | null> {
- const baseModel = (getModel as (p: string, m: string) => Model<Api> | undefined)(pair.provider, pair.model);
+ const baseModel = resolveProviderModel(pair);
if (!baseModel) {
console.log(` Model not found: ${pair.provider}/${pair.model}`);
return null;
@@ -416,10 +429,7 @@ describe.skipIf(!hasAnyApiKey())("Cross-Provider Handoff", () => {
},
];
- const baseModel = (getModel as (p: string, m: string) => Model<Api> | undefined)(
- targetPair.provider,
- targetPair.model,
- );
+ const baseModel = resolveProviderModel(targetPair);
if (!baseModel) {
console.log(`[Target: ${targetPair.label}] Model not found`);
continue;
diff --git a/packages/coding-agent/src/core/model-resolver.ts b/packages/coding-agent/src/core/model-resolver.ts
index 51724206b6..d8c0ea5f25 100644
--- a/packages/coding-agent/src/core/model-resolver.ts
+++ b/packages/coding-agent/src/core/model-resolver.ts
@@ -32,7 +32,7 @@ export const defaultModelPerProvider: Record<KnownProvider, string> = {
"vercel-ai-gateway": "zai/glm-5.1",
xai: "grok-4.20-0309-reasoning",
groq: "openai/gpt-oss-120b",
- cerebras: "zai-glm-4.7",
+ cerebras: "gpt-oss-120b",
zai: "glm-5.1",
mistral: "devstral-medium-latest",
minimax: "MiniMax-M2.7",
diff --git a/packages/coding-agent/test/model-resolver.test.ts b/packages/coding-agent/test/model-resolver.test.ts
index d12f068a47..f62be8a262 100644
--- a/packages/coding-agent/test/model-resolver.test.ts
+++ b/packages/coding-agent/test/model-resolver.test.ts
@@ -432,7 +432,7 @@ describe("default model selection", () => {
expect(defaultModelPerProvider.zai).toBe("glm-5.1");
expect(defaultModelPerProvider.minimax).toBe("MiniMax-M2.7");
expect(defaultModelPerProvider["minimax-cn"]).toBe("MiniMax-M2.7");
- expect(defaultModelPerProvider.cerebras).toBe("zai-glm-4.7");
+ expect(defaultModelPerProvider.cerebras).toBe("gpt-oss-120b");
});
test("ai-gateway default tracks current model", () => {