|
|
|
|
@@ -3463,6 +3463,23 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 65536,
|
|
|
|
|
} satisfies Model<"google-generative-ai">,
|
|
|
|
|
"gemma-3-27b-it": {
|
|
|
|
|
id: "gemma-3-27b-it",
|
|
|
|
|
name: "Gemma 3 27B",
|
|
|
|
|
api: "google-generative-ai",
|
|
|
|
|
provider: "google",
|
|
|
|
|
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
|
|
|
|
|
reasoning: false,
|
|
|
|
|
input: ["text", "image"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0,
|
|
|
|
|
output: 0,
|
|
|
|
|
cacheRead: 0,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 8192,
|
|
|
|
|
} satisfies Model<"google-generative-ai">,
|
|
|
|
|
},
|
|
|
|
|
"google-antigravity": {
|
|
|
|
|
"claude-opus-4-5-thinking": {
|
|
|
|
|
@@ -3981,6 +3998,40 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 8192,
|
|
|
|
|
maxTokens: 8192,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"groq/compound": {
|
|
|
|
|
id: "groq/compound",
|
|
|
|
|
name: "Compound",
|
|
|
|
|
api: "openai-completions",
|
|
|
|
|
provider: "groq",
|
|
|
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0,
|
|
|
|
|
output: 0,
|
|
|
|
|
cacheRead: 0,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 8192,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"groq/compound-mini": {
|
|
|
|
|
id: "groq/compound-mini",
|
|
|
|
|
name: "Compound Mini",
|
|
|
|
|
api: "openai-completions",
|
|
|
|
|
provider: "groq",
|
|
|
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0,
|
|
|
|
|
output: 0,
|
|
|
|
|
cacheRead: 0,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 8192,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"llama-3.1-8b-instant": {
|
|
|
|
|
id: "llama-3.1-8b-instant",
|
|
|
|
|
name: "Llama 3.1 8B Instant",
|
|
|
|
|
@@ -4168,6 +4219,23 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 65536,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"openai/gpt-oss-safeguard-20b": {
|
|
|
|
|
id: "openai/gpt-oss-safeguard-20b",
|
|
|
|
|
name: "Safety GPT OSS 20B",
|
|
|
|
|
api: "openai-completions",
|
|
|
|
|
provider: "groq",
|
|
|
|
|
baseUrl: "https://api.groq.com/openai/v1",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0.075,
|
|
|
|
|
output: 0.3,
|
|
|
|
|
cacheRead: 0.037,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 65536,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"qwen-qwq-32b": {
|
|
|
|
|
id: "qwen-qwq-32b",
|
|
|
|
|
name: "Qwen QwQ 32B",
|
|
|
|
|
@@ -4200,7 +4268,7 @@ export const MODELS = {
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 131072,
|
|
|
|
|
maxTokens: 16384,
|
|
|
|
|
maxTokens: 40960,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
},
|
|
|
|
|
"huggingface": {
|
|
|
|
|
@@ -7521,6 +7589,23 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 256000,
|
|
|
|
|
maxTokens: 128000,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"kwaipilot/kat-coder-pro-v2": {
|
|
|
|
|
id: "kwaipilot/kat-coder-pro-v2",
|
|
|
|
|
name: "Kwaipilot: KAT-Coder-Pro V2",
|
|
|
|
|
api: "openai-completions",
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
|
|
|
reasoning: false,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0.3,
|
|
|
|
|
output: 1.2,
|
|
|
|
|
cacheRead: 0.06,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 256000,
|
|
|
|
|
maxTokens: 80000,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"meituan/longcat-flash-chat": {
|
|
|
|
|
id: "meituan/longcat-flash-chat",
|
|
|
|
|
name: "Meituan: LongCat Flash Chat",
|
|
|
|
|
@@ -7717,9 +7802,9 @@ export const MODELS = {
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0.19999999999999998,
|
|
|
|
|
output: 1.17,
|
|
|
|
|
cacheRead: 0.09999999999999999,
|
|
|
|
|
input: 0.19,
|
|
|
|
|
output: 1.15,
|
|
|
|
|
cacheRead: 0.095,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 196608,
|
|
|
|
|
@@ -8048,23 +8133,6 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 262144,
|
|
|
|
|
maxTokens: 4096,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"mistralai/mistral-small-3.1-24b-instruct:free": {
|
|
|
|
|
id: "mistralai/mistral-small-3.1-24b-instruct:free",
|
|
|
|
|
name: "Mistral: Mistral Small 3.1 24B (free)",
|
|
|
|
|
api: "openai-completions",
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
|
|
|
reasoning: false,
|
|
|
|
|
input: ["text", "image"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0,
|
|
|
|
|
output: 0,
|
|
|
|
|
cacheRead: 0,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 128000,
|
|
|
|
|
maxTokens: 4096,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"mistralai/mistral-small-3.2-24b-instruct": {
|
|
|
|
|
id: "mistralai/mistral-small-3.2-24b-instruct",
|
|
|
|
|
name: "Mistral: Mistral Small 3.2 24B",
|
|
|
|
|
@@ -9663,23 +9731,6 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 40960,
|
|
|
|
|
maxTokens: 40960,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"qwen/qwen3-4b:free": {
|
|
|
|
|
id: "qwen/qwen3-4b:free",
|
|
|
|
|
name: "Qwen: Qwen3 4B (free)",
|
|
|
|
|
api: "openai-completions",
|
|
|
|
|
provider: "openrouter",
|
|
|
|
|
baseUrl: "https://openrouter.ai/api/v1",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0,
|
|
|
|
|
output: 0,
|
|
|
|
|
cacheRead: 0,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 40960,
|
|
|
|
|
maxTokens: 4096,
|
|
|
|
|
} satisfies Model<"openai-completions">,
|
|
|
|
|
"qwen/qwen3-8b": {
|
|
|
|
|
id: "qwen/qwen3-8b",
|
|
|
|
|
name: "Qwen: Qwen3 8B",
|
|
|
|
|
@@ -11518,6 +11569,23 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 32000,
|
|
|
|
|
maxTokens: 16384,
|
|
|
|
|
} satisfies Model<"anthropic-messages">,
|
|
|
|
|
"kwaipilot/kat-coder-pro-v2": {
|
|
|
|
|
id: "kwaipilot/kat-coder-pro-v2",
|
|
|
|
|
name: "Kat Coder Pro V2",
|
|
|
|
|
api: "anthropic-messages",
|
|
|
|
|
provider: "vercel-ai-gateway",
|
|
|
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 0.3,
|
|
|
|
|
output: 1.2,
|
|
|
|
|
cacheRead: 0.06,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 256000,
|
|
|
|
|
maxTokens: 256000,
|
|
|
|
|
} satisfies Model<"anthropic-messages">,
|
|
|
|
|
"meituan/longcat-flash-chat": {
|
|
|
|
|
id: "meituan/longcat-flash-chat",
|
|
|
|
|
name: "LongCat Flash Chat",
|
|
|
|
|
@@ -13218,23 +13286,6 @@ export const MODELS = {
|
|
|
|
|
contextWindow: 200000,
|
|
|
|
|
maxTokens: 128000,
|
|
|
|
|
} satisfies Model<"anthropic-messages">,
|
|
|
|
|
"zai/glm-5": {
|
|
|
|
|
id: "zai/glm-5",
|
|
|
|
|
name: "GLM 5",
|
|
|
|
|
api: "anthropic-messages",
|
|
|
|
|
provider: "vercel-ai-gateway",
|
|
|
|
|
baseUrl: "https://ai-gateway.vercel.sh",
|
|
|
|
|
reasoning: true,
|
|
|
|
|
input: ["text"],
|
|
|
|
|
cost: {
|
|
|
|
|
input: 1,
|
|
|
|
|
output: 3.1999999999999997,
|
|
|
|
|
cacheRead: 0.19999999999999998,
|
|
|
|
|
cacheWrite: 0,
|
|
|
|
|
},
|
|
|
|
|
contextWindow: 202800,
|
|
|
|
|
maxTokens: 131100,
|
|
|
|
|
} satisfies Model<"anthropic-messages">,
|
|
|
|
|
"zai/glm-5-turbo": {
|
|
|
|
|
id: "zai/glm-5-turbo",
|
|
|
|
|
name: "GLM 5 Turbo",
|
|
|
|
|
|