Skip to content

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

Rust

chore(ai): regenerate the model catalog from live provider catalogs (#1759)

Sebastian Müller9bc005574890
diff --git a/packages/ai/.changes/model-catalog-regen.md b/packages/ai/.changes/model-catalog-regen.md
new file mode 100644
index 0000000000..63f60a08f4
--- /dev/null
+++ b/packages/ai/.changes/model-catalog-regen.md
@@ -0,0 +1 @@
+- Refreshed the generated model catalog from live provider catalogs: models.dev rescoped `cloudflare-ai-gateway` to proxied third-party models (the `workers-ai/@cf/...` mirrors and legacy OpenAI ids are gone; Cloudflare-hosted models remain under `cloudflare-workers-ai`); added devstral-2512 and MiniMax M2.7/M3 free routes; picked up repricing for gpt-5.6/gpt-5.6-sol (5/30 -> 4/20), kimi-k2.6, glm-5.1/5.2, and deepseek-v4-pro.
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index b9d1b28cbe..83ea213dac 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -159,6 +159,9 @@ const PRIME_INFERENCE_MODEL_METADATA: Record<string, PrimeInferenceModelMetadata
"qwen/qwen3-30b-a3b-instruct-2507": { contextWindow: 262144 },
// OpenRouter has no max_completion_tokens for the rest of these.
"moonshotai/kimi-k2.5": { maxTokens: 65535 },
+ "minimax/minimax-m2.7": { maxTokens: 131072 },
+ // models.dev (moonshotai + openrouter) both list output = context for k2.6.
+ "moonshotai/kimi-k2.6": { maxTokens: 262144 },
"moonshotai/kimi-k3": { maxTokens: 1048576 },
"openai/gpt-4.1": { maxTokens: 32768 },
"openai/gpt-5-nano": { maxTokens: 128000 },
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 3403f5fec7..52a73ade27 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -2846,10 +2846,10 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 4,
+ output: 20,
+ cacheRead: 0.4,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -2882,10 +2882,10 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 4,
+ output: 20,
+ cacheRead: 0.4,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -3242,40 +3242,6 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} 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-4.1": {
id: "gpt-4.1",
name: "GPT-4.1",
@@ -3324,7 +3290,7 @@ export const MODELS = {
cacheRead: 0.025,
cacheWrite: 0,
},
- contextWindow: 1047576,
+ contextWindow: 1000000,
maxTokens: 32768,
} satisfies Model<"openai-responses">,
"gpt-4o": {
@@ -3376,7 +3342,7 @@ export const MODELS = {
cacheRead: 0.125,
cacheWrite: 0,
},
- contextWindow: 400000,
+ contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5-mini": {
@@ -3394,7 +3360,7 @@ export const MODELS = {
cacheRead: 0.025,
cacheWrite: 0,
},
- contextWindow: 400000,
+ contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5-nano": {
@@ -3412,27 +3378,9 @@ export const MODELS = {
cacheRead: 0.005,
cacheWrite: 0,
},
- contextWindow: 400000,
+ contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
- "gpt-5-pro": {
- id: "gpt-5-pro",
- name: "GPT-5 Pro",
- 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: 15,
- output: 120,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 400000,
- maxTokens: 272000,
- } satisfies Model<"openai-responses">,
"gpt-5.1": {
id: "gpt-5.1",
name: "GPT-5.1",
@@ -3448,117 +3396,9 @@ export const MODELS = {
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-chat-latest": {
- id: "gpt-5.2-chat-latest",
- name: "GPT-5.2 Chat",
- 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: 128000,
- maxTokens: 16384,
- } satisfies Model<"openai-responses">,
- "gpt-5.2-pro": {
- id: "gpt-5.2-pro",
- name: "GPT-5.2 Pro",
- 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: 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: "cloudflare-ai-gateway",
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
- 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: "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-spark": {
- id: "gpt-5.3-codex-spark",
- name: "GPT-5.3 Codex Spark",
- 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: 128000,
- maxTokens: 32000,
- } satisfies Model<"openai-responses">,
"gpt-5.4": {
id: "gpt-5.4",
name: "GPT-5.4",
@@ -3574,7 +3414,7 @@ export const MODELS = {
cacheRead: 0.25,
cacheWrite: 0,
},
- contextWindow: 1050000,
+ contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.4-mini": {
@@ -3592,7 +3432,7 @@ export const MODELS = {
cacheRead: 0.075,
cacheWrite: 0,
},
- contextWindow: 400000,
+ contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.4-nano": {
@@ -3610,7 +3450,7 @@ export const MODELS = {
cacheRead: 0.02,
cacheWrite: 0,
},
- contextWindow: 400000,
+ contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.4-pro": {
@@ -3628,7 +3468,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1050000,
+ contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.5": {
@@ -3643,10 +3483,10 @@ export const MODELS = {
cost: {
input: 5,
output: 30,
- cacheRead: 0.5,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1050000,
+ contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.5-pro": {
@@ -3664,25 +3504,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1050000,
- maxTokens: 128000,
- } satisfies Model<"openai-responses">,
- "gpt-5.6": {
- id: "gpt-5.6",
- name: "GPT-5.6",
- 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","minimal":null,"max":"max"},
- input: ["text", "image"],
- cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
- },
- contextWindow: 1050000,
+ contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.6-luna": {
@@ -3712,369 +3534,84 @@ export const MODELS = {
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
- cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
- },
- 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","minimal":null,"max":"max"},
- input: ["text", "image"],
- cost: {
- input: 2,
- output: 12,
- cacheRead: 0.2,
- cacheWrite: 2.5,
- },
- 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">,
- "o1-pro": {
- id: "o1-pro",
- name: "o1-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: 150,
- output: 600,
- cacheRead: 0,
- 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: 0.275,
- cacheWrite: 0,
- },
- contextWindow: 200000,
- maxTokens: 100000,
- } satisfies Model<"openai-responses">,
- "workers-ai/@cf/google/gemma-4-26b-a4b-it": {
- id: "workers-ai/@cf/google/gemma-4-26b-a4b-it",
- name: "Gemma 4 26B A4B IT",
- 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: 0.1,
- output: 0.3,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 256000,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/ibm-granite/granite-4.0-h-micro": {
- id: "workers-ai/@cf/ibm-granite/granite-4.0-h-micro",
- name: "Granite 4.0 H Micro",
- 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: false,
- input: ["text"],
- cost: {
- input: 0.017,
- output: 0.112,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 131000,
- maxTokens: 131000,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
- id: "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast",
- name: "Llama 3.3 70B Instruct fp8 Fast",
- 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: false,
- input: ["text"],
- cost: {
- input: 0.293,
- output: 2.253,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 24000,
- maxTokens: 24000,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct": {
- id: "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct",
- name: "Llama 4 Scout 17B 16E Instruct",
- 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: false,
- input: ["text", "image"],
- cost: {
- input: 0.27,
- output: 0.85,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 131000,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct": {
- id: "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct",
- name: "Mistral Small 3.1 24B Instruct",
- 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: false,
- input: ["text"],
- cost: {
- input: 0.351,
- output: 0.555,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 128000,
- } 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: 262144,
- maxTokens: 256000,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/moonshotai/kimi-k2.7-code": {
- id: "workers-ai/@cf/moonshotai/kimi-k2.7-code",
- name: "Kimi K2.7 Code",
- 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: 0.19,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } 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/openai/gpt-oss-120b": {
- id: "workers-ai/@cf/openai/gpt-oss-120b",
- name: "GPT OSS 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: 0.35,
- output: 0.75,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/openai/gpt-oss-20b": {
- id: "workers-ai/@cf/openai/gpt-oss-20b",
- name: "GPT OSS 20B",
- api: "openai-completions",
+ output: 10,
+ cacheRead: 0.25,
+ cacheWrite: 3.125,
+ },
+ 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}/compat",
- compat: {"sendSessionAffinityHeaders":true},
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
- input: ["text"],
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
cost: {
- input: 0.2,
- output: 0.3,
- cacheRead: 0,
- cacheWrite: 0,
+ input: 2,
+ output: 12,
+ cacheRead: 0.2,
+ cacheWrite: 2.5,
},
- contextWindow: 128000,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8": {
- id: "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8",
- name: "Qwen3 30B A3b fp8",
- api: "openai-completions",
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } 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}/compat",
- compat: {"sendSessionAffinityHeaders":true},
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
- input: 0.0509,
- output: 0.335,
- cacheRead: 0,
+ input: 2,
+ output: 8,
+ cacheRead: 0.5,
cacheWrite: 0,
},
- contextWindow: 32768,
- maxTokens: 32768,
- } 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",
+ 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}/compat",
- compat: {"sendSessionAffinityHeaders":true},
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text"],
cost: {
- input: 0.0605,
- output: 0.4,
- cacheRead: 0,
+ input: 1.1,
+ output: 4.4,
+ cacheRead: 0.55,
cacheWrite: 0,
},
- 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",
+ 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}/compat",
- compat: {"sendSessionAffinityHeaders":true},
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
- input: 1.4,
+ input: 1.1,
output: 4.4,
- cacheRead: 0.26,
+ cacheRead: 0.275,
cacheWrite: 0,
},
- contextWindow: 262144,
- maxTokens: 256000,
- } satisfies Model<"openai-completions">,
+ contextWindow: 200000,
+ maxTokens: 100000,
+ } satisfies Model<"openai-responses">,
},
"cloudflare-workers-ai": {
"@cf/deepseek-ai/deepseek-v4-flash-0731": {
@@ -8858,10 +8395,10 @@ export const MODELS = {
thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 4,
+ output: 20,
+ cacheRead: 0.4,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -8894,10 +8431,10 @@ export const MODELS = {
thinkingLevelMap: {"off":"none","xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 30,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 4,
+ output: 20,
+ cacheRead: 0.4,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -10563,6 +10100,23 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "longcat-2.0": {
+ id: "longcat-2.0",
+ name: "LongCat-2.0",
+ api: "openai-completions",
+ provider: "opencode-go",
+ baseUrl: "https://opencode.ai/zen/go/v1",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0.006,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"mimo-v2.5": {
id: "mimo-v2.5",
name: "MiMo V2.5",
@@ -11453,13 +11007,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.25,
- output: 0.95,
- cacheRead: 0.13,
+ input: 0.55,
+ output: 1.6500000000000001,
+ cacheRead: 0.55,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 32768,
+ maxTokens: 161000,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-r1": {
id: "deepseek/deepseek-r1",
@@ -11529,13 +11083,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.26899999999999996,
- output: 0.39999999999999997,
- cacheRead: 0.13449999999999998,
+ input: 0.26,
+ output: 0.38,
+ cacheRead: 0.13,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 65536,
+ maxTokens: 163840,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2-exp": {
id: "deepseek/deepseek-v3.2-exp",
@@ -11567,9 +11121,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.08106,
- output: 0.16212,
- cacheRead: 0.016212,
+ input: 0.0854,
+ output: 0.1708,
+ cacheRead: 0.01708,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11586,13 +11140,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.08,
- output: 0.18,
- cacheRead: 0.016,
+ input: 0.14,
+ output: 0.28,
+ cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 384000,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-flash-vision-exp": {
id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -11624,13 +11178,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 1.5999999999999999,
- output: 3.1999999999999997,
- cacheRead: 0.135,
+ input: 0.5790719999999999,
+ output: 1.1581439999999998,
+ cacheRead: 0.048256,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 393216,
+ maxTokens: 384000,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro-0813": {
id: "deepseek/deepseek-v4-pro-0813",
@@ -11643,9 +11197,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 1.1880000000000002,
- output: 3.564,
- cacheRead: 0.039599999999999996,
+ input: 1.122,
+ output: 3.366,
+ cacheRead: 0.037399999999999996,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -12091,40 +11645,6 @@ export const MODELS = {
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/ling-3.0-flash": {
id: "inclusionai/ling-3.0-flash",
name: "Ling-3.0-flash",
@@ -12144,24 +11664,6 @@ export const MODELS = {
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,
- thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":null},
- 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-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -12346,13 +11848,13 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
input: ["text", "image"],
cost: {
- input: 0.3,
- output: 1.1,
+ input: 0.35,
+ output: 1.5,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/muse-spark-1.1": {
id: "meta/muse-spark-1.1",
@@ -12390,6 +11892,24 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
+ "meta/muse-spark-1.2-contributor": {
+ id: "meta/muse-spark-1.2-contributor",
+ name: "Meta: Muse Spark 1.2 Contributor",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.09999999999999999,
+ output: 0.19999999999999998,
+ cacheRead: 0.002,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 4096,
+ } satisfies Model<"openai-completions">,
"minimax/minimax-m1": {
id: "minimax/minimax-m1",
name: "MiniMax: MiniMax M1",
@@ -12459,12 +11979,12 @@ export const MODELS = {
input: ["text"],
cost: {
input: 0.27,
- output: 0.95,
- cacheRead: 0.03,
+ output: 1.08,
+ cacheRead: 0.027,
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 32768,
+ maxTokens: 128000,
} satisfies Model<"openai-completions">,
"minimax/minimax-m2.7": {
id: "minimax/minimax-m2.7",
@@ -12483,7 +12003,26 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 131072,
+ maxTokens: 4096,
+ } satisfies Model<"openai-completions">,
+ "minimax/minimax-m2.7:free": {
+ id: "minimax/minimax-m2.7:free",
+ name: "MiniMax: MiniMax M2.7 (free)",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ compat: {"supportsReasoningEffort":false},
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 196608,
+ maxTokens: 4096,
} satisfies Model<"openai-completions">,
"minimax/minimax-m3": {
id: "minimax/minimax-m3",
@@ -12504,21 +12043,57 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 512000,
} satisfies Model<"openai-completions">,
- "mistralai/codestral-2508": {
- id: "mistralai/codestral-2508",
- name: "Mistral: Codestral 2508",
+ "minimax/minimax-m3:free": {
+ id: "minimax/minimax-m3:free",
+ name: "MiniMax: MiniMax M3 (free)",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ compat: {"supportsReasoningEffort":false},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 4096,
+ } 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: 0.8999999999999999,
+ 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: 0.3,
- output: 0.8999999999999999,
- cacheRead: 0.03,
+ input: 0.44,
+ output: 2.2,
+ cacheRead: 0.044,
cacheWrite: 0,
},
- contextWindow: 256000,
+ contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/ministral-14b-2512": {
@@ -12861,13 +12436,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.5795,
- output: 2.44,
- cacheRead: 0.0976,
+ input: 0.95,
+ output: 4,
+ cacheRead: 0.16,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 4096,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.7-code": {
id: "moonshotai/kimi-k2.7-code",
@@ -12882,7 +12457,7 @@ export const MODELS = {
cost: {
input: 0.67,
output: 3.4,
- cacheRead: 0.16999999999999998,
+ cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -12963,25 +12538,6 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 262144,
} 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",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- 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)",
@@ -13111,44 +12667,6 @@ export const MODELS = {
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",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- 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",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- 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",
@@ -13915,9 +13433,9 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.03,
+ input: 0.037,
output: 0.16999999999999998,
- cacheRead: 0.03,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
@@ -13941,24 +13459,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} 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,
- thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
- 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",
@@ -14394,7 +13894,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262144,
+ contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"qwen/qwen3-30b-a3b": {
@@ -14408,13 +13908,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.13,
- output: 0.52,
+ input: 0.12,
+ output: 0.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 8192,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"qwen/qwen3-30b-a3b-instruct-2507": {
id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -14620,13 +14120,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.09,
+ input: 0.09999999999999999,
output: 1.1,
- cacheRead: 0,
+ cacheRead: 0.07,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 262144,
} satisfies Model<"openai-completions">,
"qwen/qwen3-next-80b-a3b-thinking": {
id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14840,13 +14340,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.39,
- output: 2.34,
- cacheRead: 0,
+ input: 0.5,
+ output: 3.5999999999999996,
+ cacheRead: 0.3,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 65536,
+ maxTokens: 262144,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-9b": {
id: "qwen/qwen3.5-9b",
@@ -14935,13 +14435,13 @@ 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: 0.32,
+ output: 3.1999999999999997,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 81920,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -15104,10 +14604,10 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":null,"xhigh":"xhigh","max":null},
input: ["text", "image"],
cost: {
- input: 0.44999999999999996,
- output: 3.1999999999999997,
- cacheRead: 0.049999999999999996,
- cacheWrite: 0,
+ input: 0.425,
+ output: 2.5500000000000003,
+ cacheRead: 0.08499999999999999,
+ cacheWrite: 0.53125,
},
contextWindow: 1000000,
maxTokens: 131072,
@@ -15323,7 +14823,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1024000,
- maxTokens: 1024000,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
"thinkingmachines/inkling": {
id: "thinkingmachines/inkling",
@@ -15376,7 +14876,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262144,
+ contextWindow: 1048576,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"thinkingmachines/inkling:free": {
@@ -15394,7 +14894,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262144,
+ contextWindow: 1048576,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"upstage/solar-pro-3": {
@@ -15747,13 +15247,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.966,
- output: 3.036,
- cacheRead: 0.1794,
+ input: 1.26,
+ output: 3.9600000000000004,
+ cacheRead: 0.234,
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 128000,
+ maxTokens: 202752,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2": {
id: "z-ai/glm-5.2",
@@ -15765,13 +15265,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":null},
input: ["text"],
cost: {
- input: 0.966,
- output: 3.036,
- cacheRead: 0.1932,
+ input: 1.19,
+ output: 3.74,
+ cacheRead: 0.221,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 131072,
+ maxTokens: 262144,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2:free": {
id: "z-ai/glm-5.2:free",
@@ -15912,9 +15412,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.065,
- output: 0.18,
- cacheRead: 0.02,
+ input: 0.035,
+ output: 0.09999999999999999,
+ cacheRead: 0.008,
cacheWrite: 0,
},
contextWindow: 1310720,
@@ -15966,13 +15466,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 2.6,
- output: 13,
+ input: 2.8,
+ output: 14,
cacheRead: 0.29,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 974842,
+ maxTokens: 1048576,
} satisfies Model<"openai-completions">,
"~openai/gpt-latest": {
id: "~openai/gpt-latest",
@@ -16337,7 +15837,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 32768,
+ maxTokens: 161000,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.1-terminus": {
id: "deepseek/deepseek-v3.1-terminus",
@@ -16375,7 +15875,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 65536,
+ maxTokens: 163840,
featured: true,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2-exp": {
@@ -16434,7 +15934,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 384000,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
@@ -16453,7 +15953,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 393216,
+ maxTokens: 384000,
featured: true,
} satisfies Model<"openai-completions">,
"google/gemini-2.5-flash": {
@@ -16696,7 +16196,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 32768,
+ maxTokens: 128000,
} satisfies Model<"openai-completions">,
"minimax/minimax-m2.7": {
id: "minimax/minimax-m2.7",
@@ -17738,7 +17238,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 81920,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -18008,7 +17508,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 128000,
+ maxTokens: 202752,
featured: true,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2": {
@@ -18028,7 +17528,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 131072,
+ maxTokens: 262144,
featured: true,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.3": {
@@ -18877,23 +18377,6 @@ export const MODELS = {
contextWindow: 262100,
maxTokens: 80000,
} satisfies Model<"anthropic-messages">,
- "arcee-ai/trinity-mini": {
- id: "arcee-ai/trinity-mini",
- name: "Trinity Mini",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.045,
- output: 0.15,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 131072,
- maxTokens: 131072,
- } satisfies Model<"anthropic-messages">,
"bytedance/seed-1.6": {
id: "bytedance/seed-1.6",
name: "Seed 1.6",
@@ -19124,9 +18607,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 1.32,
- output: 3.9600000000000004,
- cacheRead: 0.13199999999999998,
+ input: 0.66,
+ output: 1.9800000000000002,
+ cacheRead: 0.06599999999999999,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -19727,6 +19210,23 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 131000,
} satisfies Model<"anthropic-messages">,
+ "minimax/minimax-m2.7-free": {
+ id: "minimax/minimax-m2.7-free",
+ name: "Minimax M2.7 (Free)",
+ 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: 196608,
+ maxTokens: 196608,
+ } satisfies Model<"anthropic-messages">,
"minimax/minimax-m2.7-highspeed": {
id: "minimax/minimax-m2.7-highspeed",
name: "MiniMax M2.7 High Speed",
@@ -19761,6 +19261,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 1000000,
} satisfies Model<"anthropic-messages">,
+ "minimax/minimax-m3-free": {
+ id: "minimax/minimax-m3-free",
+ name: "MiniMax M3 (Free)",
+ 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: 1048576,
+ maxTokens: 1048576,
+ } satisfies Model<"anthropic-messages">,
"mistral/codestral": {
id: "mistral/codestral",
name: "Mistral Codestral",
@@ -19812,40 +19329,6 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
- "mistral/magistral-medium": {
- id: "mistral/magistral-medium",
- name: "Magistral Medium 2509",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 2,
- output: 5,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 64000,
- } satisfies Model<"anthropic-messages">,
- "mistral/magistral-small": {
- id: "mistral/magistral-small",
- name: "Magistral Small 2509",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.5,
- output: 1.5,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 64000,
- } satisfies Model<"anthropic-messages">,
"mistral/ministral-14b": {
id: "mistral/ministral-14b",
name: "Ministral 14B",
@@ -21059,6 +20542,23 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
+ "openai/gpt-oss-safeguard-120b": {
+ id: "openai/gpt-oss-safeguard-120b",
+ name: "GPT OSS Safeguard 120B",
+ 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: 128000,
+ maxTokens: 16000,
+ } satisfies Model<"anthropic-messages">,
"openai/gpt-oss-safeguard-20b": {
id: "openai/gpt-oss-safeguard-20b",
name: "GPT OSS Safeguard 20B",
@@ -21068,13 +20568,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.075,
- output: 0.3,
- cacheRead: 0.037,
+ input: 0.07,
+ output: 0.19999999999999998,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 131072,
- maxTokens: 65536,
+ contextWindow: 128000,
+ maxTokens: 16000,
} satisfies Model<"anthropic-messages">,
"openai/o1": {
id: "openai/o1",
@@ -21110,23 +20610,6 @@ export const MODELS = {
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-fast": {
id: "openai/o3-fast",
name: "o3 (Fast)",
diff --git a/packages/ai/test/cross-provider-handoff.test.ts b/packages/ai/test/cross-provider-handoff.test.ts
index cf29af3807..b1abc6d5fa 100644
--- a/packages/ai/test/cross-provider-handoff.test.ts
+++ b/packages/ai/test/cross-provider-handoff.test.ts
@@ -52,11 +52,6 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
{ provider: "xai", model: "grok-code-fast-1", label: "xai-grok-code-fast-1" },
{ provider: "cerebras", model: "gpt-oss-120b", label: "cerebras-gpt-oss-120b" },
{ provider: "cloudflare-workers-ai", model: "@cf/moonshotai/kimi-k2.6", label: "cloudflare-kimi-k2.6" },
- {
- provider: "cloudflare-ai-gateway",
- model: "workers-ai/@cf/moonshotai/kimi-k2.6",
- label: "cloudflare-gateway-kimi-k2.6",
- },
{
provider: "cloudflare-ai-gateway",
model: "claude-sonnet-4.5",
diff --git a/packages/ai/test/empty.test.ts b/packages/ai/test/empty.test.ts
index c2850f82eb..d68c1bf6fb 100644
--- a/packages/ai/test/empty.test.ts
+++ b/packages/ai/test/empty.test.ts
@@ -9,7 +9,7 @@ type StreamOptionsWithExtras = StreamOptions & Record<string, unknown>;
import { hasAzureOpenAICredentials, resolveAzureDeploymentName } from "./azure-utils.js";
import { hasBedrockCredentials } from "./bedrock-utils.js";
-import { hasCloudflareAiGatewayCredentials, hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
+import { hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
import { resolveApiKey } from "./oauth.js";
const oauthTokens = await Promise.all([
@@ -318,26 +318,6 @@ describe("AI Providers Empty Message Tests", () => {
});
});
- describe.skipIf(!hasCloudflareAiGatewayCredentials())("Cloudflare AI Gateway Provider Empty Messages", () => {
- const llm = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6");
-
- it("should handle empty content array", { retry: 3, timeout: 30000 }, async () => {
- await testEmptyMessage(llm);
- });
-
- it("should handle empty string content", { retry: 3, timeout: 30000 }, async () => {
- await testEmptyStringMessage(llm);
- });
-
- it("should handle whitespace-only content", { retry: 3, timeout: 30000 }, async () => {
- await testWhitespaceOnlyMessage(llm);
- });
-
- it("should handle empty assistant message in conversation", { retry: 3, timeout: 30000 }, async () => {
- await testEmptyAssistantMessage(llm);
- });
- });
-
describe.skipIf(!process.env.HF_TOKEN)("Hugging Face Provider Empty Messages", () => {
const llm = getModel("huggingface", "moonshotai/Kimi-K2.5");
diff --git a/packages/ai/test/openai-completions-empty-tools.test.ts b/packages/ai/test/openai-completions-empty-tools.test.ts
index f04e2cfe83..61a65c1df4 100644
--- a/packages/ai/test/openai-completions-empty-tools.test.ts
+++ b/packages/ai/test/openai-completions-empty-tools.test.ts
@@ -1,5 +1,6 @@
import { beforeEach, describe, expect, it, vi } from "vitest";
import { getModel } from "../src/models.js";
+import { CLOUDFLARE_AI_GATEWAY_COMPAT_BASE_URL } from "../src/providers/cloudflare.js";
import { streamSimple } from "../src/stream.js";
import type { Model } from "../src/types.js";
@@ -50,6 +51,13 @@ vi.mock("openai", () => {
return { default: FakeOpenAI };
});
+const cloudflareGatewayCompatModel: Model<"openai-completions"> = {
+ ...getModel("cloudflare-workers-ai", "@cf/moonshotai/kimi-k2.6"),
+ provider: "cloudflare-ai-gateway",
+ baseUrl: CLOUDFLARE_AI_GATEWAY_COMPAT_BASE_URL,
+ id: "workers-ai/@cf/moonshotai/kimi-k2.6",
+};
+
describe("openai-completions empty tools handling", () => {
beforeEach(() => {
mockState.lastParams = undefined;
@@ -92,7 +100,7 @@ describe("openai-completions empty tools handling", () => {
it("uses conservative OpenAI-compatible fields for Cloudflare AI Gateway /compat models", async () => {
process.env.CLOUDFLARE_ACCOUNT_ID = "account-id";
process.env.CLOUDFLARE_GATEWAY_ID = "gateway-id";
- const model = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6")!;
+ const model = cloudflareGatewayCompatModel;
await streamSimple(
model,
@@ -177,7 +185,7 @@ describe("openai-completions empty tools handling", () => {
it("sends session affinity headers for Workers AI through Cloudflare AI Gateway", async () => {
process.env.CLOUDFLARE_ACCOUNT_ID = "account-id";
process.env.CLOUDFLARE_GATEWAY_ID = "gateway-id";
- const workersModel = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6")!;
+ const workersModel = cloudflareGatewayCompatModel;
await streamSimple(
workersModel,
diff --git a/packages/ai/test/stream.test.ts b/packages/ai/test/stream.test.ts
index 30bfe6a583..5de75a4f04 100644
--- a/packages/ai/test/stream.test.ts
+++ b/packages/ai/test/stream.test.ts
@@ -648,33 +648,6 @@ describe("Generate E2E Tests", () => {
},
);
- describe.skipIf(!hasCloudflareAiGatewayCredentials())(
- "Cloudflare AI Gateway → Workers AI (Kimi K2.6 via /compat)",
- () => {
- const llm = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6");
-
- it("should complete basic text generation", { retry: 3 }, async () => {
- await basicTextGeneration(llm);
- });
-
- it("should handle tool calling", { retry: 3 }, async () => {
- await handleToolCall(llm);
- });
-
- it("should handle streaming", { retry: 3 }, async () => {
- await handleStreaming(llm);
- });
-
- it("should handle thinking mode", { retry: 3 }, async () => {
- await handleThinking(llm, { reasoningEffort: "medium" });
- });
-
- it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
- await multiTurn(llm, { reasoningEffort: "medium" });
- });
- },
- );
-
describe.skipIf(!hasCloudflareAiGatewayCredentials() || !process.env.OPENAI_API_KEY)(
"Cloudflare AI Gateway → OpenAI BYOK (gpt-5.1 via /openai responses)",
() => {
diff --git a/packages/ai/test/tokens.test.ts b/packages/ai/test/tokens.test.ts
index d4a73abca9..cdf9dd2f9e 100644
--- a/packages/ai/test/tokens.test.ts
+++ b/packages/ai/test/tokens.test.ts
@@ -9,7 +9,7 @@ type StreamOptionsWithExtras = StreamOptions & Record<string, unknown>;
import { hasAzureOpenAICredentials, resolveAzureDeploymentName } from "./azure-utils.js";
import { hasBedrockCredentials } from "./bedrock-utils.js";
-import { hasCloudflareAiGatewayCredentials, hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
+import { hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
import { resolveApiKey } from "./oauth.js";
const oauthTokens = await Promise.all([
@@ -159,14 +159,6 @@ describe("Token Statistics on Abort", () => {
});
});
- describe.skipIf(!hasCloudflareAiGatewayCredentials())("Cloudflare AI Gateway Provider", () => {
- const llm = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6");
-
- it("should include token stats when aborted mid-stream", { retry: 3, timeout: 30000 }, async () => {
- await testTokensOnAbort(llm);
- });
- });
-
describe.skipIf(!process.env.HF_TOKEN)("Hugging Face Provider", () => {
const llm = getModel("huggingface", "moonshotai/Kimi-K2.5");
diff --git a/packages/ai/test/tool-call-without-result.test.ts b/packages/ai/test/tool-call-without-result.test.ts
index 10e4be9648..8a76350c5d 100644
--- a/packages/ai/test/tool-call-without-result.test.ts
+++ b/packages/ai/test/tool-call-without-result.test.ts
@@ -10,7 +10,7 @@ type StreamOptionsWithExtras = StreamOptions & Record<string, unknown>;
import { hasAzureOpenAICredentials, resolveAzureDeploymentName } from "./azure-utils.js";
import { hasBedrockCredentials } from "./bedrock-utils.js";
-import { hasCloudflareAiGatewayCredentials, hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
+import { hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
import { resolveApiKey } from "./oauth.js";
const oauthTokens = await Promise.all([
@@ -159,14 +159,6 @@ describe("Tool Call Without Result Tests", () => {
});
});
- describe.skipIf(!hasCloudflareAiGatewayCredentials())("Cloudflare AI Gateway Provider", () => {
- const model = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6");
-
- it("should filter out tool calls without corresponding tool results", { retry: 3, timeout: 30000 }, async () => {
- await testToolCallWithoutResult(model);
- });
- });
-
describe.skipIf(!process.env.HF_TOKEN)("Hugging Face Provider", () => {
const model = getModel("huggingface", "moonshotai/Kimi-K2.5");
diff --git a/packages/ai/test/total-tokens.test.ts b/packages/ai/test/total-tokens.test.ts
index 1b61538b92..c4da819dbd 100644
--- a/packages/ai/test/total-tokens.test.ts
+++ b/packages/ai/test/total-tokens.test.ts
@@ -9,7 +9,7 @@ type StreamOptionsWithExtras = StreamOptions & Record<string, unknown>;
import { hasAzureOpenAICredentials, resolveAzureDeploymentName } from "./azure-utils.js";
import { hasBedrockCredentials } from "./bedrock-utils.js";
-import { hasCloudflareAiGatewayCredentials, hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
+import { hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
import { resolveApiKey } from "./oauth.js";
const oauthTokens = await Promise.all([
@@ -273,26 +273,6 @@ describe("totalTokens field", () => {
});
});
- describe.skipIf(!hasCloudflareAiGatewayCredentials())("Cloudflare AI Gateway", () => {
- it("workers-ai/@cf/moonshotai/kimi-k2.6 - should return totalTokens equal to sum of components", {
- retry: 3,
- timeout: 60000,
- }, async () => {
- const llm = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6");
-
- console.log(`\nCloudflare AI Gateway / ${llm.id}:`);
- const { first, second } = await testTotalTokensWithCache(llm, {
- apiKey: process.env.CLOUDFLARE_API_KEY,
- });
-
- logUsage("First request", first);
- logUsage("Second request", second);
-
- assertTotalTokensEqualsComponents(first);
- assertTotalTokensEqualsComponents(second);
- });
- });
-
describe.skipIf(!process.env.HF_TOKEN)("Hugging Face", () => {
it("Kimi-K2.5 - should return totalTokens equal to sum of components", { retry: 3, timeout: 60000 }, async () => {
const llm = getModel("huggingface", "moonshotai/Kimi-K2.5");
diff --git a/packages/ai/test/unicode-surrogate.test.ts b/packages/ai/test/unicode-surrogate.test.ts
index f6ac63ed40..b0c05a73ee 100644
--- a/packages/ai/test/unicode-surrogate.test.ts
+++ b/packages/ai/test/unicode-surrogate.test.ts
@@ -10,7 +10,7 @@ type StreamOptionsWithExtras = StreamOptions & Record<string, unknown>;
import { hasAzureOpenAICredentials, resolveAzureDeploymentName } from "./azure-utils.js";
import { hasBedrockCredentials } from "./bedrock-utils.js";
-import { hasCloudflareAiGatewayCredentials, hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
+import { hasCloudflareWorkersAICredentials } from "./cloudflare-utils.js";
import { resolveApiKey } from "./oauth.js";
const emptySchema = Type.Object({});
@@ -489,22 +489,6 @@ describe("AI Providers Unicode Surrogate Pair Tests", () => {
});
});
- describe.skipIf(!hasCloudflareAiGatewayCredentials())("Cloudflare AI Gateway Provider Unicode Handling", () => {
- const llm = getModel("cloudflare-ai-gateway", "workers-ai/@cf/moonshotai/kimi-k2.6");
-
- it("should handle emoji in tool results", { retry: 3, timeout: 30000 }, async () => {
- await testEmojiInToolResults(llm);
- });
-
- it("should handle real-world LinkedIn comment data with emoji", { retry: 3, timeout: 30000 }, async () => {
- await testRealWorldLinkedInData(llm);
- });
-
- it("should handle unpaired high surrogate (0xD83D) in tool results", { retry: 3, timeout: 30000 }, async () => {
- await testUnpairedHighSurrogate(llm);
- });
- });
-
describe.skipIf(!process.env.HF_TOKEN)("Hugging Face Provider Unicode Handling", () => {
const llm = getModel("huggingface", "moonshotai/Kimi-K2.5");
diff --git a/packages/coding-agent/.changes/model-catalog-regen.md b/packages/coding-agent/.changes/model-catalog-regen.md
new file mode 100644
index 0000000000..9ba123b48d
--- /dev/null
+++ b/packages/coding-agent/.changes/model-catalog-regen.md
@@ -0,0 +1 @@
+- Changed the Cloudflare AI Gateway default model to claude-sonnet-4.5 after the catalog dropped the gateway's workers-ai mirror ids.
diff --git a/packages/coding-agent/docs/providers.md b/packages/coding-agent/docs/providers.md
index e013a85405..5c7ff364bb 100644
--- a/packages/coding-agent/docs/providers.md
+++ b/packages/coding-agent/docs/providers.md
@@ -194,7 +194,7 @@ export CLOUDFLARE_GATEWAY_ID=... # create at dash.cloudflare.com → AI
prime-agent --provider cloudflare-ai-gateway --model "claude-sonnet-4-5"
```
-Routes to OpenAI, Anthropic, and Workers AI through Cloudflare AI Gateway. Workers AI uses the Unified API (`/compat`) and prefixed model IDs (`workers-ai/@cf/...`). OpenAI uses the OpenAI passthrough route (`/openai`) with native OpenAI model IDs such as `gpt-5.1`. Anthropic uses the Anthropic passthrough route (`/anthropic`) with native Anthropic model IDs such as `claude-sonnet-4-5`.
+Routes to OpenAI and Anthropic through Cloudflare AI Gateway. OpenAI uses the OpenAI passthrough route (`/openai`) with native OpenAI model IDs such as `gpt-5.1`. Anthropic uses the Anthropic passthrough route (`/anthropic`) with native Anthropic model IDs such as `claude-sonnet-4-5`. Cloudflare-hosted `@cf/...` models are available through the separate `cloudflare-workers-ai` provider.
AI Gateway authentication uses `CLOUDFLARE_API_KEY` as `cf-aig-authorization`. Upstream authentication can be one of:
diff --git a/packages/coding-agent/src/core/model-resolver.ts b/packages/coding-agent/src/core/model-resolver.ts
index cb47c46a99..00187f0708 100644
--- a/packages/coding-agent/src/core/model-resolver.ts
+++ b/packages/coding-agent/src/core/model-resolver.ts
@@ -45,7 +45,7 @@ export const defaultModelPerProvider: Record<KnownProvider, string> = {
"opencode-go": "kimi-k2.6",
"kimi-coding": "kimi-for-coding",
"cloudflare-workers-ai": "@cf/moonshotai/kimi-k2.6",
- "cloudflare-ai-gateway": "workers-ai/@cf/moonshotai/kimi-k2.6",
+ "cloudflare-ai-gateway": "claude-sonnet-4.5",
xiaomi: "mimo-v2.5-pro",
"xiaomi-token-plan-cn": "mimo-v2.5-pro",
"xiaomi-token-plan-ams": "mimo-v2.5-pro",