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 (#1878)

Sebastian Müller0fa717d4f012
diff --git a/packages/ai/.changes/refresh-model-catalog.md b/packages/ai/.changes/refresh-model-catalog.md
new file mode 100644
index 0000000000..fd36b89b6b
--- /dev/null
+++ b/packages/ai/.changes/refresh-model-catalog.md
@@ -0,0 +1 @@
+- Refreshed the model catalog from live provider catalogs (pricing updates, new and removed models); fixed OpenCode Go Qwen routes mislabeled as Anthropic and excluded private dev/ Prime Inference routes.
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 83ea213dac..1ba0fc83c4 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -232,7 +232,8 @@ function isPrimeInferenceRawVariant(modelId: string): boolean {
}
function isPrimeInferencePrivateModel(modelId: string): boolean {
- return modelId.toLowerCase().startsWith("internal/");
+ const id = modelId.toLowerCase();
+ return id.startsWith("internal/") || id.startsWith("dev/");
}
const OPENAI_RESPONSES_NONE_REASONING_MODELS = new Set([
@@ -1324,11 +1325,11 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
// OpenCode Go endpoint behaviour. models.dev reports these models
// as @ai-sdk/anthropic, but the OpenCode Go endpoints either don't
// accept Anthropic SDK auth (MiniMax M2.7) or are served through
- // the OpenAI-compatible /v1/chat/completions path (Qwen 3.5/3.6).
+ // the OpenAI-compatible /v1/chat/completions path (Qwen routes).
// Switch them to openai-completions so requests use Bearer auth
// and the standard /v1/chat/completions endpoint.
if (variant.provider === "opencode-go") {
- if (modelId === "minimax-m2.7") {
+ if (modelId === "minimax-m2.7" || (npm === "@ai-sdk/anthropic" && modelId.startsWith("qwen"))) {
api = "openai-completions";
baseUrl = `${variant.basePath}/v1`;
}
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 52a73ade27..a3945be9a1 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -806,10 +806,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 0.22,
- output: 1.32,
- cacheRead: 0.022,
- cacheWrite: 0.275,
+ input: 0.2,
+ output: 1.2,
+ cacheRead: 0.02,
+ cacheWrite: 0.25,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -824,10 +824,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5.5,
- output: 33,
- cacheRead: 0.55,
- cacheWrite: 6.875,
+ input: 4,
+ output: 20,
+ cacheRead: 0.4,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -842,10 +842,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 2.2,
- output: 13.2,
- cacheRead: 0.22,
- cacheWrite: 2.75,
+ input: 2,
+ output: 12,
+ cacheRead: 0.2,
+ cacheWrite: 2.5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -1463,10 +1463,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 5.5,
- output: 33,
- cacheRead: 0.55,
- cacheWrite: 6.875,
+ input: 4.4,
+ output: 22,
+ cacheRead: 0.44,
+ cacheWrite: 5.5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -3904,6 +3904,24 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
+ "@cf/zai-org/glm-5.3-flash": {
+ id: "@cf/zai-org/glm-5.3-flash",
+ name: "Glm 5.3 Flash",
+ api: "openai-completions",
+ provider: "cloudflare-workers-ai",
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+ compat: {"sendSessionAffinityHeaders":true},
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.5,
+ cacheRead: 0.03,
+ cacheWrite: 0,
+ },
+ contextWindow: 1310720,
+ maxTokens: 1310720,
+ } satisfies Model<"openai-completions">,
},
"deepseek": {
"deepseek-v4-flash": {
@@ -3980,23 +3998,6 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"anthropic-messages">,
- "accounts/fireworks/models/deepseek-v4-pro": {
- id: "accounts/fireworks/models/deepseek-v4-pro",
- name: "DeepSeek V4 Pro",
- api: "anthropic-messages",
- provider: "fireworks",
- baseUrl: "https://api.fireworks.ai/inference",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 1.74,
- output: 3.48,
- cacheRead: 0.145,
- cacheWrite: 0,
- },
- contextWindow: 1000000,
- maxTokens: 384000,
- } satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/deepseek-v4-pro-0813": {
id: "accounts/fireworks/models/deepseek-v4-pro-0813",
name: "DeepSeek V4 Pro 0813",
@@ -4048,23 +4049,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
- "accounts/fireworks/models/gpt-oss-20b": {
- id: "accounts/fireworks/models/gpt-oss-20b",
- name: "GPT OSS 20B",
- api: "anthropic-messages",
- provider: "fireworks",
- baseUrl: "https://api.fireworks.ai/inference",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0.07,
- output: 0.3,
- cacheRead: 0.035,
- cacheWrite: 0,
- },
- contextWindow: 131072,
- maxTokens: 32768,
- } satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/inkling": {
id: "accounts/fireworks/models/inkling",
name: "Inkling",
@@ -4134,23 +4118,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
- "accounts/fireworks/models/minimax-m2p7": {
- id: "accounts/fireworks/models/minimax-m2p7",
- name: "MiniMax-M2.7",
- api: "anthropic-messages",
- provider: "fireworks",
- baseUrl: "https://api.fireworks.ai/inference",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0.3,
- output: 1.2,
- cacheRead: 0.06,
- cacheWrite: 0,
- },
- contextWindow: 196608,
- maxTokens: 196608,
- } satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/minimax-m3": {
id: "accounts/fireworks/models/minimax-m3",
name: "MiniMax-M3",
@@ -4270,57 +4237,6 @@ export const MODELS = {
contextWindow: 1048575,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
- "accounts/fireworks/routers/kimi-k2p6-fast": {
- id: "accounts/fireworks/routers/kimi-k2p6-fast",
- name: "Kimi K2.6 Fast",
- api: "anthropic-messages",
- provider: "fireworks",
- baseUrl: "https://api.fireworks.ai/inference",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 2,
- output: 8,
- cacheRead: 0.3,
- cacheWrite: 0,
- },
- contextWindow: 262000,
- maxTokens: 262000,
- } satisfies Model<"anthropic-messages">,
- "accounts/fireworks/routers/kimi-k2p6-turbo": {
- id: "accounts/fireworks/routers/kimi-k2p6-turbo",
- name: "Kimi K2.6 Turbo",
- api: "anthropic-messages",
- provider: "fireworks",
- baseUrl: "https://api.fireworks.ai/inference",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 2,
- output: 8,
- cacheRead: 0.3,
- cacheWrite: 0,
- },
- contextWindow: 262000,
- maxTokens: 262000,
- } satisfies Model<"anthropic-messages">,
- "accounts/fireworks/routers/kimi-k2p7-code-fast": {
- id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
- name: "Kimi K2.7 Code Fast",
- api: "anthropic-messages",
- provider: "fireworks",
- baseUrl: "https://api.fireworks.ai/inference",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 1.9,
- output: 8,
- cacheRead: 0.38,
- cacheWrite: 0,
- },
- contextWindow: 262000,
- maxTokens: 262000,
- } satisfies Model<"anthropic-messages">,
"accounts/fireworks/routers/kimi-k3-fast": {
id: "accounts/fireworks/routers/kimi-k3-fast",
name: "Kimi K3 Fast",
@@ -4598,9 +4514,9 @@ 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,
@@ -4810,7 +4726,7 @@ export const MODELS = {
input: 0.2,
output: 1.2,
cacheRead: 0.02,
- cacheWrite: 0,
+ cacheWrite: 0.25,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -4826,10 +4742,10 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 2.5,
- output: 15,
- cacheRead: 0.25,
- cacheWrite: 3.125,
+ input: 2,
+ output: 10,
+ cacheRead: 0.2,
+ cacheWrite: 2.5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -4848,7 +4764,7 @@ export const MODELS = {
input: 2,
output: 12,
cacheRead: 0.2,
- cacheWrite: 0,
+ cacheWrite: 2.5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -5619,7 +5535,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 128000,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"MiniMaxAI/MiniMax-M2.1": {
id: "MiniMaxAI/MiniMax-M2.1",
@@ -5691,7 +5607,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 524288,
- maxTokens: 128000,
+ maxTokens: 512000,
} satisfies Model<"openai-completions">,
"Qwen/Qwen2.5-Coder-32B-Instruct": {
id: "Qwen/Qwen2.5-Coder-32B-Instruct",
@@ -6071,6 +5987,24 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "Qwen/Qwen3.8-27B": {
+ id: "Qwen/Qwen3.8-27B",
+ name: "Qwen3.8 27B",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.4,
+ output: 3,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
"XiaomiMiMo/MiMo-V2-Flash": {
id: "XiaomiMiMo/MiMo-V2-Flash",
name: "MiMo-V2-Flash",
@@ -6810,6 +6744,24 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "zai-org/GLM-5.3-Flash": {
+ id: "zai-org/GLM-5.3-Flash",
+ name: "GLM-5.3-Flash",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.15,
+ output: 0.5,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
},
"kimi-coding": {
"k3": {
@@ -7487,6 +7439,23 @@ export const MODELS = {
contextWindow: 32000,
maxTokens: 32000,
} satisfies Model<"mistral-conversations">,
+ "zai-glm-5-2": {
+ id: "zai-glm-5-2",
+ name: "GLM-5.2",
+ api: "mistral-conversations",
+ provider: "mistral",
+ baseUrl: "https://api.mistral.ai",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 1.4,
+ output: 4.4,
+ cacheRead: 0.14,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"mistral-conversations">,
},
"moonshotai": {
"kimi-k2-0711-preview": {
@@ -9573,7 +9542,7 @@ export const MODELS = {
cost: {
input: 2,
output: 6,
- cacheRead: 0.5,
+ cacheRead: 0.3,
cacheWrite: 0,
},
contextWindow: 500000,
@@ -9869,23 +9838,6 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"anthropic-messages">,
- "x-preview-f-free": {
- id: "x-preview-f-free",
- name: "Ox Alpha Free (Unlimited)",
- api: "openai-completions",
- provider: "opencode",
- baseUrl: "https://opencode.ai/zen/v1",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1000000,
- maxTokens: 131072,
- } satisfies Model<"openai-completions">,
},
"opencode-go": {
"deepseek-v4-flash": {
@@ -9996,6 +9948,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "glm-5.3-flash": {
+ id: "glm-5.3-flash",
+ name: "GLM-5.3-Flash (2x usage)",
+ api: "openai-completions",
+ provider: "opencode-go",
+ baseUrl: "https://opencode.ai/zen/go/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.075,
+ output: 0.25,
+ cacheRead: 0.015,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"gpt-5.6-luna": {
id: "gpt-5.6-luna",
name: "GPT-5.6 Luna",
@@ -10014,9 +9983,9 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
- "grok-4.5": {
- id: "grok-4.5",
- name: "Grok 4.5",
+ "grok-4.6": {
+ id: "grok-4.6",
+ name: "Grok 4.6",
api: "openai-responses",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
@@ -10202,23 +10171,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-responses">,
- "ox-alpha-free": {
- id: "ox-alpha-free",
- name: "Ox Alpha Free (Unlimited)",
- api: "openai-completions",
- provider: "opencode-go",
- baseUrl: "https://opencode.ai/zen/go/v1",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1000000,
- maxTokens: 131072,
- } satisfies Model<"openai-completions">,
"qwen3.6-plus": {
id: "qwen3.6-plus",
name: "Qwen3.6 Plus",
@@ -10271,25 +10223,42 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
- "qwen3.8-max": {
- id: "qwen3.8-max",
- name: "Qwen3.8 Max",
+ "qwen3.8-flash": {
+ id: "qwen3.8-flash",
+ name: "Qwen3.8 Flash",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
reasoning: true,
input: ["text", "image"],
cost: {
- input: 2,
- output: 6,
- cacheRead: 0.25,
- cacheWrite: 2.5,
+ input: 0.15,
+ output: 0.47,
+ cacheRead: 0.016,
+ cacheWrite: 0.2,
},
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
- },
- "openrouter": {
+ "qwen3.8-max": {
+ id: "qwen3.8-max",
+ name: "Qwen3.8 Max",
+ api: "openai-completions",
+ provider: "opencode-go",
+ baseUrl: "https://opencode.ai/zen/go/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.25,
+ cacheWrite: 2.5,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
+ },
+ "openrouter": {
"aion-labs/aion-2.0": {
id: "aion-labs/aion-2.0",
name: "AionLabs: Aion-2.0",
@@ -10762,7 +10731,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"arcee-ai/virtuoso-large": {
id: "arcee-ai/virtuoso-large",
@@ -10853,7 +10822,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"bytedance-seed/seed-2.0-code": {
id: "bytedance-seed/seed-2.0-code",
@@ -10994,7 +10963,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 163840,
+ maxTokens: 147456,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-chat-v3.1": {
id: "deepseek/deepseek-chat-v3.1",
@@ -11013,7 +10982,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 161000,
+ maxTokens: 144900,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-r1": {
id: "deepseek/deepseek-r1",
@@ -11083,13 +11052,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.26,
- output: 0.38,
- cacheRead: 0.13,
+ input: 0.26899999999999996,
+ output: 0.39999999999999997,
+ cacheRead: 0.13449999999999998,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 163840,
+ maxTokens: 65536,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2-exp": {
id: "deepseek/deepseek-v3.2-exp",
@@ -11121,9 +11090,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.0854,
- output: 0.1708,
- cacheRead: 0.01708,
+ input: 0.088606,
+ output: 0.177212,
+ cacheRead: 0.017721200000000003,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11140,13 +11109,13 @@ 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: 0.028,
+ input: 0.07,
+ output: 0.14,
+ cacheRead: 0.014,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 131072,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-flash-vision-exp": {
id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -11159,9 +11128,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text", "image"],
cost: {
- input: 0.22,
- output: 0.66,
- cacheRead: 0.007,
+ input: 0.44,
+ output: 1.32,
+ cacheRead: 0.014,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11178,9 +11147,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.5790719999999999,
- output: 1.1581439999999998,
- cacheRead: 0.048256,
+ input: 0.87,
+ output: 1.74,
+ cacheRead: 0.0725,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11197,13 +11166,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 1.122,
- output: 3.366,
- cacheRead: 0.037399999999999996,
+ input: 1.32,
+ output: 3.9600000000000004,
+ cacheRead: 0.044,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 4096,
+ maxTokens: 384000,
} satisfies Model<"openai-completions">,
"dots-studio/dots-3-note-preview:free": {
id: "dots-studio/dots-3-note-preview:free",
@@ -11222,7 +11191,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 512000,
- maxTokens: 512000,
+ maxTokens: 460800,
} satisfies Model<"openai-completions">,
"google/gemini-2.5-flash": {
id: "google/gemini-2.5-flash",
@@ -11532,7 +11501,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"google/gemma-4-26b-a4b-it": {
id: "google/gemma-4-26b-a4b-it",
@@ -11583,13 +11552,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.09999999999999999,
+ input: 0.09,
output: 0.33999999999999997,
- cacheRead: 0.09999999999999999,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it:free": {
id: "google/gemma-4-31b-it:free",
@@ -11625,7 +11594,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"inception/mercury-2": {
id: "inception/mercury-2",
@@ -11664,6 +11633,25 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
+ "inclusionai/ling-3.0-flash-fin:free": {
+ id: "inclusionai/ling-3.0-flash-fin:free",
+ name: "Ling 3.0 Flash Fin (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: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -11712,7 +11700,7 @@ export const MODELS = {
cacheRead: 0.15,
cacheWrite: 0,
},
- contextWindow: 256000,
+ contextWindow: 262144,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"liquid/lfm-2.5-2.6b:free": {
@@ -11785,7 +11773,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.3-70b-instruct": {
id: "meta-llama/llama-3.3-70b-instruct",
@@ -11796,13 +11784,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.09999999999999999,
- output: 0.32,
- cacheRead: 0,
+ input: 0.71,
+ output: 0.71,
+ cacheRead: 0.71,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 16384,
+ maxTokens: 115200,
} satisfies Model<"openai-completions">,
"meta-llama/llama-4-maverick": {
id: "meta-llama/llama-4-maverick",
@@ -11830,13 +11818,13 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.09999999999999999,
- output: 0.3,
- cacheRead: 0,
+ input: 0.11,
+ output: 0.33999999999999997,
+ cacheRead: 0.055,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 16384,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
"meta/muse-glimmer-30b": {
id: "meta/muse-glimmer-30b",
@@ -11854,7 +11842,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 4096,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"meta/muse-spark-1.1": {
id: "meta/muse-spark-1.1",
@@ -11872,7 +11860,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 4096,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"meta/muse-spark-1.2": {
id: "meta/muse-spark-1.2",
@@ -11890,7 +11878,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 4096,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"meta/muse-spark-1.2-contributor": {
id: "meta/muse-spark-1.2-contributor",
@@ -11908,7 +11896,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 4096,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"minimax/minimax-m1": {
id: "minimax/minimax-m1",
@@ -12003,7 +11991,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 4096,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"minimax/minimax-m2.7:free": {
id: "minimax/minimax-m2.7:free",
@@ -12022,7 +12010,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 196608,
- maxTokens: 4096,
+ maxTokens: 176947,
} satisfies Model<"openai-completions">,
"minimax/minimax-m3": {
id: "minimax/minimax-m3",
@@ -12060,7 +12048,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 4096,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"mistralai/codestral-2508": {
id: "mistralai/codestral-2508",
@@ -12077,7 +12065,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 256000,
- maxTokens: 4096,
+ maxTokens: 204800,
} satisfies Model<"openai-completions">,
"mistralai/devstral-2512": {
id: "mistralai/devstral-2512",
@@ -12094,7 +12082,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/ministral-14b-2512": {
id: "mistralai/ministral-14b-2512",
@@ -12111,7 +12099,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/ministral-3b-2512": {
id: "mistralai/ministral-3b-2512",
@@ -12128,7 +12116,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 4096,
+ maxTokens: 104857,
} satisfies Model<"openai-completions">,
"mistralai/ministral-8b-2512": {
id: "mistralai/ministral-8b-2512",
@@ -12145,7 +12133,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/mistral-large": {
id: "mistralai/mistral-large",
@@ -12162,7 +12150,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 128000,
- maxTokens: 4096,
+ maxTokens: 102400,
} satisfies Model<"openai-completions">,
"mistralai/mistral-large-2407": {
id: "mistralai/mistral-large-2407",
@@ -12179,7 +12167,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 4096,
+ maxTokens: 104857,
} satisfies Model<"openai-completions">,
"mistralai/mistral-large-2512": {
id: "mistralai/mistral-large-2512",
@@ -12196,7 +12184,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/mistral-medium-3": {
id: "mistralai/mistral-medium-3",
@@ -12213,7 +12201,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 4096,
+ maxTokens: 104857,
} satisfies Model<"openai-completions">,
"mistralai/mistral-medium-3-5": {
id: "mistralai/mistral-medium-3-5",
@@ -12231,7 +12219,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/mistral-medium-3.1": {
id: "mistralai/mistral-medium-3.1",
@@ -12248,7 +12236,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 4096,
+ maxTokens: 104857,
} satisfies Model<"openai-completions">,
"mistralai/mistral-nemo": {
id: "mistralai/mistral-nemo",
@@ -12282,7 +12270,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 32768,
- maxTokens: 4096,
+ maxTokens: 26214,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small-2603": {
id: "mistralai/mistral-small-2603",
@@ -12300,7 +12288,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small-3.2-24b-instruct": {
id: "mistralai/mistral-small-3.2-24b-instruct",
@@ -12334,7 +12322,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 65536,
- maxTokens: 4096,
+ maxTokens: 52428,
} satisfies Model<"openai-completions">,
"mistralai/voxtral-small-24b-2507": {
id: "mistralai/voxtral-small-24b-2507",
@@ -12351,7 +12339,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 32000,
- maxTokens: 4096,
+ maxTokens: 25600,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2": {
id: "moonshotai/kimi-k2",
@@ -12442,7 +12430,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.7-code": {
id: "moonshotai/kimi-k2.7-code",
@@ -12455,13 +12443,13 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.67,
+ input: 0.66,
output: 3.4,
- cacheRead: 0.19,
+ cacheRead: 0.18,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k3": {
id: "moonshotai/kimi-k3",
@@ -12498,7 +12486,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"nex-agi/nex-n2-pro": {
id: "nex-agi/nex-n2-pro",
@@ -12517,7 +12505,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-30b-a3b": {
id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -12532,11 +12520,11 @@ export const MODELS = {
cost: {
input: 0.049999999999999996,
output: 0.19999999999999998,
- cacheRead: 0.03,
+ cacheRead: 0.024999999999999998,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 228000,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -12591,7 +12579,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b": {
id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -12603,13 +12591,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.6,
- output: 3.5999999999999996,
- cacheRead: 0.19999999999999998,
+ input: 0.5,
+ output: 2.2,
+ cacheRead: 0.09999999999999999,
cacheWrite: 0,
},
- contextWindow: 512288,
- maxTokens: 4096,
+ contextWindow: 262144,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b:free": {
id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -12640,13 +12628,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.08,
- output: 0.19999999999999998,
- cacheRead: 0.04,
+ input: 0.09999999999999999,
+ output: 0.25,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 131072,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3.5-lightning:free": {
id: "nvidia/nemotron-3.5-lightning:free",
@@ -12699,7 +12687,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 4095,
- maxTokens: 4096,
+ maxTokens: 3685,
} satisfies Model<"openai-completions">,
"openai/gpt-3.5-turbo-16k": {
id: "openai/gpt-3.5-turbo-16k",
@@ -13439,7 +13427,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
@@ -13457,7 +13445,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-safeguard-20b": {
id: "openai/gpt-oss-safeguard-20b",
@@ -13768,7 +13756,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 32768,
- maxTokens: 32768,
+ maxTokens: 29491,
} satisfies Model<"openai-completions">,
"qwen/qwen-plus": {
id: "qwen/qwen-plus",
@@ -13804,25 +13792,6 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
- "qwen/qwen-plus-2025-07-28:thinking": {
- id: "qwen/qwen-plus-2025-07-28:thinking",
- name: "Qwen: Qwen Plus 0728 (thinking)",
- 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: 0.26,
- output: 0.78,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1000000,
- maxTokens: 32768,
- } satisfies Model<"openai-completions">,
"qwen/qwen3-14b": {
id: "qwen/qwen3-14b",
name: "Qwen: Qwen3 14B",
@@ -13870,13 +13839,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.09,
- output: 0.55,
- cacheRead: 0,
+ input: 0.0875,
+ output: 0.35,
+ cacheRead: 0.0175,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-235b-a22b-thinking-2507": {
id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -13895,7 +13864,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 4096,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"qwen/qwen3-30b-a3b": {
id: "qwen/qwen3-30b-a3b",
@@ -14022,7 +13991,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-coder-flash": {
id: "qwen/qwen3-coder-flash",
@@ -14056,7 +14025,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-coder-plus": {
id: "qwen/qwen3-coder-plus",
@@ -14126,7 +14095,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-next-80b-a3b-thinking": {
id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14289,7 +14258,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-27b": {
id: "qwen/qwen3.5-27b",
@@ -14327,7 +14296,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-397b-a17b": {
id: "qwen/qwen3.5-397b-a17b",
@@ -14340,13 +14309,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.5,
- output: 3.5999999999999996,
- cacheRead: 0.3,
+ input: 0.39,
+ output: 2.34,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 65536,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-9b": {
id: "qwen/qwen3.5-9b",
@@ -14365,7 +14334,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-flash-02-23": {
id: "qwen/qwen3.5-flash-02-23",
@@ -14435,13 +14404,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.32,
- output: 3.1999999999999997,
- cacheRead: 0,
+ input: 0.6,
+ output: 3.5999999999999996,
+ cacheRead: 0.12,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 81920,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -14454,13 +14423,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.14,
- output: 1,
+ input: 0.09999999999999999,
+ output: 0.8999999999999999,
cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-flash": {
id: "qwen/qwen3.6-flash",
@@ -14592,7 +14561,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 131072,
+ maxTokens: 262144,
} satisfies Model<"openai-completions">,
"qwen/qwen3.8-27b": {
id: "qwen/qwen3.8-27b",
@@ -14612,6 +14581,25 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "qwen/qwen3.8-flash": {
+ id: "qwen/qwen3.8-flash",
+ name: "Qwen: Qwen3.8 Flash",
+ 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: 0.15,
+ output: 0.47,
+ cacheRead: 0.016,
+ cacheWrite: 0.19999999999999998,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"qwen/qwen3.8-max": {
id: "qwen/qwen3.8-max",
name: "Qwen: Qwen3.8 Max",
@@ -14645,7 +14633,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 16384,
- maxTokens: 16384,
+ maxTokens: 14745,
} satisfies Model<"openai-completions">,
"relace/relace-search": {
id: "relace/relace-search",
@@ -14717,24 +14705,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
- "stealth/ox-alpha": {
- id: "stealth/ox-alpha",
- name: "Ox Alpha",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
- input: ["text", "image"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1048576,
- maxTokens: 131072,
- } satisfies Model<"openai-completions">,
"stepfun/step-3.5-flash": {
id: "stepfun/step-3.5-flash",
name: "StepFun: Step 3.5 Flash",
@@ -14770,7 +14740,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 256000,
+ maxTokens: 230400,
} satisfies Model<"openai-completions">,
"tencent/hy3": {
id: "tencent/hy3",
@@ -14806,7 +14776,25 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 4096,
+ maxTokens: 235929,
+ } satisfies Model<"openai-completions">,
+ "tencent/hy4-preview": {
+ id: "tencent/hy4-preview",
+ name: "Tencent: Hy4 preview",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text"],
+ cost: {
+ input: 0.834,
+ output: 2.501,
+ cacheRead: 0.041999999999999996,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 64000,
} satisfies Model<"openai-completions">,
"thedrummer/unslopnemo-12b": {
id: "thedrummer/unslopnemo-12b",
@@ -14823,7 +14811,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1024000,
- maxTokens: 32768,
+ maxTokens: 26214,
} satisfies Model<"openai-completions">,
"thinkingmachines/inkling": {
id: "thinkingmachines/inkling",
@@ -14914,7 +14902,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"upstage/solar-pro4": {
id: "upstage/solar-pro4",
@@ -14952,7 +14940,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 2000000,
- maxTokens: 4096,
+ maxTokens: 1800000,
} satisfies Model<"openai-completions">,
"x-ai/grok-4.3": {
id: "x-ai/grok-4.3",
@@ -14970,7 +14958,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1000000,
- maxTokens: 4096,
+ maxTokens: 900000,
} satisfies Model<"openai-completions">,
"x-ai/grok-4.5": {
id: "x-ai/grok-4.5",
@@ -14988,7 +14976,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 500000,
- maxTokens: 4096,
+ maxTokens: 450000,
} satisfies Model<"openai-completions">,
"x-ai/grok-4.6": {
id: "x-ai/grok-4.6",
@@ -15006,7 +14994,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 500000,
- maxTokens: 4096,
+ maxTokens: 450000,
} satisfies Model<"openai-completions">,
"x-ai/grok-build-0.1": {
id: "x-ai/grok-build-0.1",
@@ -15025,7 +15013,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 256000,
- maxTokens: 4096,
+ maxTokens: 230400,
} satisfies Model<"openai-completions">,
"xiaomi/mimo-v2.5": {
id: "xiaomi/mimo-v2.5",
@@ -15133,13 +15121,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.5,
- output: 2,
- cacheRead: 0.09999999999999999,
+ input: 0.43,
+ output: 1.75,
+ cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 131072,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.6v": {
id: "z-ai/glm-4.6v",
@@ -15253,7 +15241,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 202752,
+ maxTokens: 182476,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2": {
id: "z-ai/glm-5.2",
@@ -15289,7 +15277,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 256000,
- maxTokens: 256000,
+ maxTokens: 230400,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.3": {
id: "z-ai/glm-5.3",
@@ -15309,6 +15297,24 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "z-ai/glm-5.3-flash": {
+ id: "z-ai/glm-5.3-flash",
+ name: "Z.ai: GLM 5.3 Flash",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.075,
+ output: 0.25,
+ cacheRead: 0.015,
+ cacheWrite: 0,
+ },
+ contextWindow: 1310720,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"z-ai/glm-5v-turbo": {
id: "z-ai/glm-5v-turbo",
name: "Z.ai: GLM 5V Turbo",
@@ -15412,13 +15418,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.035,
+ input: 0.03,
output: 0.09999999999999999,
- cacheRead: 0.008,
+ cacheRead: 0.007,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 1048576,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"~google/gemini-flash-latest": {
id: "~google/gemini-flash-latest",
@@ -15466,13 +15472,13 @@ 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,
- cacheRead: 0.29,
+ input: 2.5500000000000003,
+ output: 12.75,
+ cacheRead: 0.25599998999999996,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 1048576,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"~openai/gpt-latest": {
id: "~openai/gpt-latest",
@@ -15526,7 +15532,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 500000,
- maxTokens: 4096,
+ maxTokens: 450000,
} satisfies Model<"openai-completions">,
"~z-ai/glm-latest": {
id: "~z-ai/glm-latest",
@@ -15794,8 +15800,8 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.5,
- output: 1.5,
+ input: 0.4,
+ output: 1.3,
cacheRead: 0,
cacheWrite: 0,
},
@@ -15812,13 +15818,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 1.25,
- output: 1.5,
+ input: 0.27,
+ output: 1.12,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 163840,
+ maxTokens: 147456,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-chat-v3.1": {
id: "deepseek/deepseek-chat-v3.1",
@@ -15831,13 +15837,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.56,
- output: 1.68,
+ input: 0.6,
+ output: 1.7,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 161000,
+ maxTokens: 144900,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.1-terminus": {
id: "deepseek/deepseek-v3.1-terminus",
@@ -15850,8 +15856,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.45,
- output: 1.5,
+ input: 0.27,
+ output: 1,
cacheRead: 0,
cacheWrite: 0,
},
@@ -15869,13 +15875,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.28,
- output: 0.42,
+ input: 0.3705,
+ output: 1.1115,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 163840,
+ maxTokens: 65536,
featured: true,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2-exp": {
@@ -15889,8 +15895,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.28,
- output: 0.42,
+ input: 0.27,
+ output: 0.41,
cacheRead: 0,
cacheWrite: 0,
},
@@ -15908,8 +15914,8 @@ 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,
+ input: 0.44,
+ output: 1.32,
cacheRead: 0,
cacheWrite: 0,
},
@@ -15928,13 +15934,13 @@ 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,
+ input: 0.44,
+ output: 1.32,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 131072,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
@@ -15947,8 +15953,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 2.1,
- output: 4.4,
+ input: 1.91,
+ output: 3.83,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16089,6 +16095,25 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
+ "google/gemini-3.7-flash": {
+ id: "google/gemini-3.7-flash",
+ name: "Gemini 3.7 Flash",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 1.35,
+ output: 6.75,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 65536,
+ } satisfies Model<"openai-completions">,
"google/gemma-3-27b-it": {
id: "google/gemma-3-27b-it",
name: "Gemma 3 27B IT",
@@ -16105,7 +16130,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"meta-llama/Llama-3.2-1B-Instruct": {
id: "meta-llama/Llama-3.2-1B-Instruct",
@@ -16117,13 +16142,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.03,
- output: 0.21,
+ input: 0.027,
+ output: 0.201,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 60000,
- maxTokens: 60000,
+ maxTokens: 54000,
} satisfies Model<"openai-completions">,
"meta-llama/Llama-3.2-3B-Instruct": {
id: "meta-llama/Llama-3.2-3B-Instruct",
@@ -16135,8 +16160,8 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.1,
- output: 0.34,
+ input: 0.0509,
+ output: 0.335,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16153,13 +16178,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.9,
- output: 0.9,
+ input: 1.04,
+ output: 2.253,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 16384,
+ maxTokens: 115200,
} satisfies Model<"openai-completions">,
"meta-llama/llama-4-maverick": {
id: "meta-llama/llama-4-maverick",
@@ -16171,8 +16196,8 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.27,
- output: 0.88,
+ input: 0.35,
+ output: 1.15,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16190,8 +16215,8 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.3,
- output: 1.2,
+ input: 0.6,
+ output: 2.4,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16253,7 +16278,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 8192,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/mistral-nemo": {
id: "mistralai/mistral-nemo",
@@ -16265,8 +16290,8 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.1,
- output: 0.25,
+ input: 0.165,
+ output: 0.17,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16284,13 +16309,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.1875,
- output: 0.75,
+ input: 0.165,
+ output: 0.66,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 8192,
+ maxTokens: 209715,
} satisfies Model<"openai-completions">,
"mistralai/mixtral-8x22b-instruct": {
id: "mistralai/mixtral-8x22b-instruct",
@@ -16302,13 +16327,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 2,
- output: 6,
+ input: 2.2,
+ output: 6.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 65536,
- maxTokens: 8192,
+ maxTokens: 52428,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2-0905": {
id: "moonshotai/kimi-k2-0905",
@@ -16320,8 +16345,8 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 1.2,
- output: 5,
+ input: 0.6,
+ output: 2.5,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16340,7 +16365,7 @@ export const MODELS = {
input: ["text", "image"],
cost: {
input: 0.6,
- output: 3.2,
+ output: 3,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16377,13 +16402,13 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 1.0925,
- output: 4.6,
+ input: 1.9,
+ output: 8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
featured: true,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k3": {
@@ -16397,8 +16422,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 3,
- output: 15,
+ input: 3.45,
+ output: 17.25,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16417,13 +16442,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.05,
- output: 0.2,
+ input: 0.06,
+ output: 0.24,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 228000,
featured: true,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b": {
@@ -16438,7 +16463,7 @@ export const MODELS = {
input: ["text"],
cost: {
input: 0.3,
- output: 0.9,
+ output: 0.65,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16631,25 +16656,6 @@ export const MODELS = {
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
- "openai/gpt-5.2-chat": {
- id: "openai/gpt-5.2-chat",
- name: "GPT 5.2 Chat",
- api: "openai-completions",
- provider: "prime-inference",
- baseUrl: "https://api.pinference.ai/api/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- thinkingLevelMap: {"xhigh":"xhigh"},
- input: ["text", "image"],
- cost: {
- input: 1.75,
- output: 14,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 32000,
- } satisfies Model<"openai-completions">,
"openai/gpt-5.2-pro": {
id: "openai/gpt-5.2-pro",
name: "GPT 5.2 PRO",
@@ -16932,13 +16938,13 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.15,
- output: 0.6,
+ input: 0.35,
+ output: 0.75,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
@@ -16970,8 +16976,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.1,
- output: 0.19,
+ input: 0.09,
+ output: 0.18,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16989,8 +16995,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.065,
- output: 0.13,
+ input: 0.06,
+ output: 0.12,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17007,13 +17013,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.22,
- output: 0.88,
+ input: 0.25,
+ output: 1,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-30b-a3b-instruct-2507": {
id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -17025,8 +17031,8 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.2,
- output: 0.8,
+ input: 0.13,
+ output: 0.52,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17063,7 +17069,7 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 2,
+ input: 0.975,
output: 4.875,
cacheRead: 0,
cacheWrite: 0,
@@ -17081,13 +17087,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.5,
+ input: 0.3,
output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
featured: true,
} satisfies Model<"openai-completions">,
"qwen/qwen3-max": {
@@ -17119,8 +17125,8 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.4,
- output: 1.9,
+ input: 0.3,
+ output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17138,7 +17144,7 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 1,
+ input: 0.98,
output: 4,
cacheRead: 0,
cacheWrite: 0,
@@ -17157,8 +17163,8 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.25,
- output: 1,
+ input: 0.2,
+ output: 0.7,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17175,8 +17181,8 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.18,
- output: 0.7,
+ input: 0.117,
+ output: 0.455,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17194,13 +17200,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.3125,
- output: 1.8,
+ input: 0.25,
+ output: 1.3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-397b-a17b": {
id: "qwen/qwen3.5-397b-a17b",
@@ -17238,7 +17244,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 81920,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -17251,13 +17257,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.3,
- output: 1.8,
+ input: 0.25,
+ output: 1.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.7-flash": {
id: "qwen/qwen3.7-flash",
@@ -17349,8 +17355,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.4,
- output: 2,
+ input: 0.168,
+ output: 0.336,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17368,8 +17374,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 1,
- output: 3,
+ input: 0.48024,
+ output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17431,7 +17437,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 131072,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.7": {
id: "z-ai/glm-4.7",
@@ -17445,7 +17451,7 @@ export const MODELS = {
input: ["text"],
cost: {
input: 0.6,
- output: 2.65,
+ output: 2.2,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17463,8 +17469,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.1,
- output: 0.43,
+ input: 0.07,
+ output: 0.4,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17482,8 +17488,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 1.2,
- output: 3.5,
+ input: 1,
+ output: 3.2,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17502,13 +17508,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 1.75,
- output: 5.5,
+ input: 1.4,
+ output: 4.4,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 202752,
+ maxTokens: 182476,
featured: true,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2": {
@@ -17522,8 +17528,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":null},
input: ["text"],
cost: {
- input: 1.68,
- output: 5.28,
+ input: 1.54,
+ output: 4.84,
cacheRead: 0,
cacheWrite: 0,
},
@@ -17550,6 +17556,25 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "z-ai/glm-5.3-flash": {
+ id: "z-ai/glm-5.3-flash",
+ name: "GLM 5.3 Flash",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"zai"},
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.5,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1310720,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
},
"vercel-ai-gateway": {
"alibaba/qwen-3-14b": {
@@ -18011,6 +18036,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
+ "alibaba/qwen3.8-flash": {
+ id: "alibaba/qwen3.8-flash",
+ name: "Qwen 3.8 Flash",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.16,
+ output: 0.47,
+ cacheRead: 0.016,
+ cacheWrite: 0.19999999999999998,
+ },
+ contextWindow: 991000,
+ maxTokens: 128000,
+ } satisfies Model<"anthropic-messages">,
"alibaba/qwen3.8-max": {
id: "alibaba/qwen3.8-max",
name: "Qwen 3.8 Max",
@@ -18870,6 +18912,40 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
+ "inclusionai/ling-3.0-flash-fin": {
+ id: "inclusionai/ling-3.0-flash-fin",
+ name: "Ling 3.0 Flash Fin",
+ 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: 256000,
+ maxTokens: 32000,
+ } satisfies Model<"anthropic-messages">,
+ "inclusionai/ling-3.0-flash-fin-free": {
+ id: "inclusionai/ling-3.0-flash-fin-free",
+ name: "Ling 3.0 Flash Fin (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: 256000,
+ maxTokens: 32000,
+ } satisfies Model<"anthropic-messages">,
"interfaze/interfaze-beta": {
id: "interfaze/interfaze-beta",
name: "Interfaze Beta",
@@ -19681,8 +19757,8 @@ export const MODELS = {
input: ["text"],
cost: {
input: 0.049999999999999996,
- output: 0.19999999999999998,
- cacheRead: 0.01,
+ output: 0.15,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -21307,6 +21383,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 12800,
} satisfies Model<"anthropic-messages">,
+ "zai/glm-5.3-flash": {
+ id: "zai/glm-5.3-flash",
+ name: "GLM 5.3 Flash",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.5,
+ cacheRead: 0.03,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131000,
+ } satisfies Model<"anthropic-messages">,
"zai/glm-5v-turbo": {
id: "zai/glm-5v-turbo",
name: "GLM 5V Turbo",
@@ -21953,5 +22046,41 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "glm-5.3-flash": {
+ id: "glm-5.3-flash",
+ name: "GLM-5.3-Flash",
+ api: "openai-completions",
+ provider: "zai",
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
+ compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
+ "glm-5.3-highspeed": {
+ id: "glm-5.3-highspeed",
+ name: "GLM-5.3 Highspeed",
+ api: "openai-completions",
+ provider: "zai",
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
+ compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
},
} as const;
diff --git a/packages/ai/test/fireworks-models.test.ts b/packages/ai/test/fireworks-models.test.ts
index 897968df4b..e8ac50398c 100644
--- a/packages/ai/test/fireworks-models.test.ts
+++ b/packages/ai/test/fireworks-models.test.ts
@@ -32,15 +32,6 @@ describe("Fireworks models", () => {
});
});
- it("registers the Fire Pass turbo router model", () => {
- const model = getModel("fireworks", "accounts/fireworks/routers/kimi-k2p6-turbo");
-
- expect(model).toBeDefined();
- expect(model.api).toBe("anthropic-messages");
- expect(model.baseUrl).toBe("https://api.fireworks.ai/inference");
- expect(model.input).toEqual(["text", "image"]);
- });
-
it("resolves FIREWORKS_API_KEY from the environment", () => {
process.env.FIREWORKS_API_KEY = "test-fireworks-key";
diff --git a/packages/ai/test/prime-inference-models.test.ts b/packages/ai/test/prime-inference-models.test.ts
index 7c774924d9..cd79d4a177 100644
--- a/packages/ai/test/prime-inference-models.test.ts
+++ b/packages/ai/test/prime-inference-models.test.ts
@@ -96,8 +96,8 @@ describe("Prime Inference models", () => {
expect(model.input).toEqual(["text", "image"]);
expect(model.contextWindow).toBe(1048576);
expect(model.maxTokens).toBe(1048576);
- expect(model.cost.input).toBe(3);
- expect(model.cost.output).toBe(15);
+ expect(model.cost.input).toBe(provider === "prime-inference" ? 3.45 : 3);
+ expect(model.cost.output).toBe(provider === "prime-inference" ? 17.25 : 15);
}
});