update chat

This commit is contained in:
Harivansh Rathi 2026-03-12 01:51:33 -04:00
parent 4dc5e1b376
commit 08717ea6d1
2 changed files with 283 additions and 117 deletions

View file

@ -3010,7 +3010,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
contextWindow: 264000,
maxTokens: 64000,
} satisfies Model<"openai-responses">,
"gpt-5.2-codex": {
@ -3033,7 +3033,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 272000,
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.3-codex": {
@ -6486,6 +6486,23 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"nemotron-3-super-free": {
id: "nemotron-3-super-free",
name: "Nemotron 3 Super Free",
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
},
"opencode-go": {
"glm-5": {
@ -7230,13 +7247,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.25,
output: 0.39999999999999997,
cacheRead: 0,
input: 0.26,
output: 0.38,
cacheRead: 0.13,
cacheWrite: 0,
},
contextWindow: 163840,
maxTokens: 65536,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2-exp": {
id: "deepseek/deepseek-v3.2-exp",
@ -8360,6 +8377,23 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b:free": {
id: "nvidia/nemotron-3-super-120b-a12b:free",
name: "NVIDIA: Nemotron 3 Super (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: 262144,
maxTokens: 262144,
} 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)",
@ -9346,6 +9380,40 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"openrouter/healer-alpha": {
id: "openrouter/healer-alpha",
name: "Healer Alpha",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"openrouter/hunter-alpha": {
id: "openrouter/hunter-alpha",
name: "Hunter Alpha",
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: 1048576,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"prime-intellect/intellect-3": {
id: "prime-intellect/intellect-3",
name: "Prime Intellect: INTELLECT-3",
@ -9848,13 +9916,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.15,
output: 1.2,
input: 0.0975,
output: 0.78,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"qwen/qwen3-vl-235b-a22b-instruct": {
id: "qwen/qwen3-vl-235b-a22b-instruct",
@ -9882,8 +9950,8 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
input: 0.26,
output: 2.6,
cacheRead: 0,
cacheWrite: 0,
},
@ -9916,8 +9984,8 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
input: 0.13,
output: 1.56,
cacheRead: 0,
cacheWrite: 0,
},
@ -10649,13 +10717,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.09999999999999999,
output: 0.3,
input: 0.29,
output: 0.59,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 40960,
maxTokens: 16384,
contextWindow: 131072,
maxTokens: 40960,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3-235b-a22b-thinking": {
id: "alibaba/qwen3-235b-a22b-thinking",
@ -10700,13 +10768,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.07,
output: 0.27,
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 160000,
maxTokens: 32768,
contextWindow: 262144,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3-coder-next": {
id: "alibaba/qwen3-coder-next",
@ -10742,6 +10810,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 65536,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3-max": {
id: "alibaba/qwen3-max",
name: "Qwen3 Max",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 1.2,
output: 6,
cacheRead: 0.24,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3-max-preview": {
id: "alibaba/qwen3-max-preview",
name: "Qwen3 Max Preview",
@ -10889,8 +10974,8 @@ export const MODELS = {
cost: {
input: 3,
output: 15,
cacheRead: 0,
cacheWrite: 0,
cacheRead: 0.3,
cacheWrite: 3.75,
},
contextWindow: 200000,
maxTokens: 8192,
@ -11099,6 +11184,23 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 8000,
} satisfies Model<"anthropic-messages">,
"deepseek/deepseek-r1": {
id: "deepseek/deepseek-r1",
name: "DeepSeek-R1",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1.35,
output: 5.4,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"deepseek/deepseek-v3": {
id: "deepseek/deepseek-v3",
name: "DeepSeek V3 0324",
@ -11125,13 +11227,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.21,
output: 0.7899999999999999,
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 163840,
maxTokens: 128000,
maxTokens: 16384,
} satisfies Model<"anthropic-messages">,
"deepseek/deepseek-v3.1-terminus": {
id: "deepseek/deepseek-v3.1-terminus",
@ -11184,6 +11286,40 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"google/gemini-2.0-flash": {
id: "google/gemini-2.0-flash",
name: "Gemini 2.0 Flash",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"google/gemini-2.0-flash-lite": {
id: "google/gemini-2.0-flash-lite",
name: "Gemini 2.0 Flash Lite",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.075,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"google/gemini-2.5-flash": {
id: "google/gemini-2.5-flash",
name: "Gemini 2.5 Flash",
@ -11191,11 +11327,11 @@ export const MODELS = {
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
input: ["text", "image"],
cost: {
input: 0.3,
output: 2.5,
cacheRead: 0,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 1000000,
@ -11259,11 +11395,11 @@ export const MODELS = {
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
input: ["text", "image"],
cost: {
input: 1.25,
output: 10,
cacheRead: 0,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 1048576,
@ -11284,7 +11420,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 64000,
maxTokens: 65000,
} satisfies Model<"anthropic-messages">,
"google/gemini-3-pro-preview": {
id: "google/gemini-3-pro-preview",
@ -11386,7 +11522,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
maxTokens: 100000,
} satisfies Model<"anthropic-messages">,
"meituan/longcat-flash-thinking": {
id: "meituan/longcat-flash-thinking",
@ -11414,13 +11550,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.39999999999999997,
output: 0.39999999999999997,
input: 0.72,
output: 0.72,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 16384,
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"meta/llama-3.1-8b": {
id: "meta/llama-3.1-8b",
@ -11431,12 +11567,12 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.03,
output: 0.049999999999999996,
input: 0.09999999999999999,
output: 0.09999999999999999,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
contextWindow: 128000,
maxTokens: 16384,
} satisfies Model<"anthropic-messages">,
"meta/llama-3.2-11b": {
@ -11499,12 +11635,12 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
input: 0.24,
output: 0.9700000000000001,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"meta/llama-4-scout": {
@ -11516,12 +11652,12 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.08,
output: 0.3,
input: 0.16999999999999998,
output: 0.66,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"minimax/minimax-m2": {
@ -11552,8 +11688,8 @@ export const MODELS = {
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.15,
cacheWrite: 0,
cacheRead: 0.03,
cacheWrite: 0.375,
},
contextWindow: 204800,
maxTokens: 131072,
@ -11788,14 +11924,31 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.5,
output: 2,
input: 0.6,
output: 2.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 16384,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-0905": {
id: "moonshotai/kimi-k2-0905",
name: "Kimi K2 0905",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 0.6,
output: 2.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-thinking": {
id: "moonshotai/kimi-k2-thinking",
name: "Kimi K2 Thinking",
@ -11805,13 +11958,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.47,
output: 2,
cacheRead: 0.14100000000000001,
input: 0.6,
output: 2.5,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 216144,
maxTokens: 216144,
contextWindow: 262114,
maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-thinking-turbo": {
id: "moonshotai/kimi-k2-thinking-turbo",
@ -11856,13 +12009,13 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.5,
output: 2.8,
cacheRead: 0,
input: 0.6,
output: 3,
cacheRead: 0.09999999999999999,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 256000,
contextWindow: 262114,
maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"nvidia/nemotron-nano-12b-v2-vl": {
id: "nvidia/nemotron-nano-12b-v2-vl",
@ -11890,8 +12043,8 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.04,
output: 0.16,
input: 0.06,
output: 0.22999999999999998,
cacheRead: 0,
cacheWrite: 0,
},
@ -11960,7 +12113,7 @@ export const MODELS = {
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
cacheRead: 0.03,
cacheRead: 0.024999999999999998,
cacheWrite: 0,
},
contextWindow: 1047576,
@ -12011,7 +12164,7 @@ export const MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12041,11 +12194,11 @@ export const MODELS = {
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
input: ["text"],
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12062,7 +12215,7 @@ export const MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.03,
cacheRead: 0.024999999999999998,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12079,7 +12232,7 @@ export const MODELS = {
cost: {
input: 0.049999999999999996,
output: 0.39999999999999997,
cacheRead: 0.01,
cacheRead: 0.005,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12113,7 +12266,7 @@ export const MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12164,7 +12317,7 @@ export const MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 128000,
@ -12181,7 +12334,7 @@ export const MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12198,7 +12351,7 @@ export const MODELS = {
cost: {
input: 1.75,
output: 14,
cacheRead: 0.18,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 400000,
@ -12303,7 +12456,7 @@ export const MODELS = {
cacheRead: 0.25,
cacheWrite: 0,
},
contextWindow: 200000,
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"openai/gpt-5.4-pro": {
@ -12320,26 +12473,9 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 200000,
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"openai/gpt-oss-120b": {
id: "openai/gpt-oss-120b",
name: "gpt-oss-120b",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 0.09999999999999999,
output: 0.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
name: "gpt-oss-20b",
@ -12757,9 +12893,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.09,
output: 0.29,
cacheRead: 0,
input: 0.09999999999999999,
output: 0.3,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 262144,
@ -12776,11 +12912,11 @@ export const MODELS = {
cost: {
input: 0.6,
output: 2.2,
cacheRead: 0,
cacheRead: 0.11,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
contextWindow: 128000,
maxTokens: 96000,
} satisfies Model<"anthropic-messages">,
"zai/glm-4.5-air": {
id: "zai/glm-4.5-air",
@ -12805,16 +12941,16 @@ export const MODELS = {
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.6,
output: 1.7999999999999998,
cacheRead: 0,
cacheRead: 0.11,
cacheWrite: 0,
},
contextWindow: 65536,
maxTokens: 16384,
contextWindow: 66000,
maxTokens: 16000,
} satisfies Model<"anthropic-messages">,
"zai/glm-4.6": {
id: "zai/glm-4.6",
@ -12876,12 +13012,12 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.43,
output: 1.75,
cacheRead: 0.08,
input: 0.6,
output: 2.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 202752,
contextWindow: 200000,
maxTokens: 120000,
} satisfies Model<"anthropic-messages">,
"zai/glm-4.7-flash": {
@ -12927,9 +13063,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.7999999999999999,
output: 2.56,
cacheRead: 0.16,
input: 1,
output: 3.1999999999999997,
cacheRead: 0.19999999999999998,
cacheWrite: 0,
},
contextWindow: 202800,