This commit is contained in:
Harivansh Rathi 2026-03-10 13:17:18 -04:00
parent 536241053c
commit 7896a91262
2 changed files with 222 additions and 103 deletions

View file

@ -889,6 +889,23 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"bedrock-converse-stream">,
"mistral.devstral-2-123b": {
id: "mistral.devstral-2-123b",
name: "Devstral 2 135B",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: false,
input: ["text"],
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"mistral.ministral-3-14b-instruct": {
id: "mistral.ministral-3-14b-instruct",
name: "Ministral 14B 3.0",
@ -3393,9 +3410,9 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
input: 0.5,
output: 3,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1048576,
@ -4714,7 +4731,7 @@ export const MODELS = {
mistral: {
"codestral-latest": {
id: "codestral-latest",
name: "Codestral",
name: "Codestral (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -4765,7 +4782,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"devstral-medium-latest": {
id: "devstral-medium-latest",
name: "Devstral 2",
name: "Devstral 2 (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -4833,7 +4850,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"magistral-medium-latest": {
id: "magistral-medium-latest",
name: "Magistral Medium",
name: "Magistral Medium (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -4867,7 +4884,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"ministral-3b-latest": {
id: "ministral-3b-latest",
name: "Ministral 3B",
name: "Ministral 3B (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -4884,7 +4901,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"ministral-8b-latest": {
id: "ministral-8b-latest",
name: "Ministral 8B",
name: "Ministral 8B (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -4935,7 +4952,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"mistral-large-latest": {
id: "mistral-large-latest",
name: "Mistral Large",
name: "Mistral Large (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -4986,7 +5003,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"mistral-medium-latest": {
id: "mistral-medium-latest",
name: "Mistral Medium",
name: "Mistral Medium (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -5037,7 +5054,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"mistral-small-latest": {
id: "mistral-small-latest",
name: "Mistral Small",
name: "Mistral Small (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -5122,7 +5139,7 @@ export const MODELS = {
} satisfies Model<"mistral-conversations">,
"pixtral-large-latest": {
id: "pixtral-large-latest",
name: "Pixtral Large",
name: "Pixtral Large (latest)",
api: "mistral-conversations",
provider: "mistral",
baseUrl: "https://api.mistral.ai",
@ -6401,6 +6418,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"mimo-v2-flash-free": {
id: "mimo-v2-flash-free",
name: "MiMo V2 Flash 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: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"minimax-m2.1": {
id: "minimax-m2.1",
name: "MiniMax M2.1",
@ -7017,6 +7051,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"bytedance-seed/seed-2.0-lite": {
id: "bytedance-seed/seed-2.0-lite",
name: "ByteDance Seed: Seed-2.0-Lite",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.25,
output: 2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"bytedance-seed/seed-2.0-mini": {
id: "bytedance-seed/seed-2.0-mini",
name: "ByteDance Seed: Seed-2.0-Mini",
@ -7096,11 +7147,11 @@ export const MODELS = {
cost: {
input: 0.19999999999999998,
output: 0.77,
cacheRead: 0.13,
cacheRead: 0.135,
cacheWrite: 0,
},
contextWindow: 163840,
maxTokens: 163840,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-chat-v3.1": {
id: "deepseek/deepseek-chat-v3.1",
@ -7468,9 +7519,9 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.04,
output: 0.15,
cacheRead: 0.02,
input: 0.03,
output: 0.11,
cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 128000,
@ -7774,13 +7825,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.295,
output: 1.2,
cacheRead: 0.03,
input: 0.27,
output: 0.95,
cacheRead: 0.0299999997,
cacheWrite: 0,
},
contextWindow: 196608,
maxTokens: 196608,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/codestral-2508": {
id: "mistralai/codestral-2508",
@ -9836,7 +9887,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"qwen/qwen3-next-80b-a3b-instruct:free": {
@ -10060,6 +10111,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-9b": {
id: "qwen/qwen3.5-9b",
name: "Qwen: Qwen3.5-9B",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-flash-02-23": {
id: "qwen/qwen3.5-flash-02-23",
name: "Qwen: Qwen3.5-Flash",
@ -10154,13 +10222,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.65,
output: 0.75,
input: 0.85,
output: 0.85,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 32768,
contextWindow: 131072,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"stepfun/step-3.5-flash": {
id: "stepfun/step-3.5-flash",
@ -10731,7 +10799,7 @@ export const MODELS = {
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
reasoning: false,
input: ["text"],
cost: {
input: 0.5,
@ -11915,23 +11983,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"openai/codex-mini": {
id: "openai/codex-mini",
name: "Codex Mini",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.5,
output: 6,
cacheRead: 0.375,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 100000,
} satisfies Model<"anthropic-messages">,
"openai/gpt-4-turbo": {
id: "openai/gpt-4-turbo",
name: "GPT-4 Turbo",
@ -12337,7 +12388,7 @@ export const MODELS = {
cacheRead: 0.25,
cacheWrite: 0,
},
contextWindow: 1050000,
contextWindow: 200000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"openai/gpt-5.4-pro": {
@ -12354,7 +12405,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1050000,
contextWindow: 200000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"openai/gpt-oss-120b": {
@ -12918,6 +12969,23 @@ export const MODELS = {
contextWindow: 202752,
maxTokens: 120000,
} satisfies Model<"anthropic-messages">,
"zai/glm-4.7-flash": {
id: "zai/glm-4.7-flash",
name: "GLM 4.7 Flash",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 0.07,
output: 0.39999999999999997,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 131000,
} satisfies Model<"anthropic-messages">,
"zai/glm-4.7-flashx": {
id: "zai/glm-4.7-flashx",
name: "GLM 4.7 FlashX",
@ -12937,20 +13005,20 @@ export const MODELS = {
} satisfies Model<"anthropic-messages">,
"zai/glm-5": {
id: "zai/glm-5",
name: "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,
input: 0.7999999999999999,
output: 2.56,
cacheRead: 0.16,
cacheWrite: 0,
},
contextWindow: 202800,
maxTokens: 131072,
maxTokens: 131100,
} satisfies Model<"anthropic-messages">,
},
xai: {
@ -13277,6 +13345,57 @@ export const MODELS = {
contextWindow: 2000000,
maxTokens: 30000,
} satisfies Model<"openai-completions">,
"grok-4.20-experimental-beta-0304-non-reasoning": {
id: "grok-4.20-experimental-beta-0304-non-reasoning",
name: "Grok 4.20 (Experimental, Non-Reasoning)",
api: "openai-completions",
provider: "xai",
baseUrl: "https://api.x.ai/v1",
reasoning: false,
input: ["text", "image"],
cost: {
input: 2,
output: 6,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
maxTokens: 30000,
} satisfies Model<"openai-completions">,
"grok-4.20-experimental-beta-0304-reasoning": {
id: "grok-4.20-experimental-beta-0304-reasoning",
name: "Grok 4.20 (Experimental, Reasoning)",
api: "openai-completions",
provider: "xai",
baseUrl: "https://api.x.ai/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 2,
output: 6,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
maxTokens: 30000,
} satisfies Model<"openai-completions">,
"grok-4.20-multi-agent-experimental-beta-0304": {
id: "grok-4.20-multi-agent-experimental-beta-0304",
name: "Grok 4.20 Multi-Agent (Experimental)",
api: "openai-completions",
provider: "xai",
baseUrl: "https://api.x.ai/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 2,
output: 6,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
maxTokens: 30000,
} satisfies Model<"openai-completions">,
"grok-beta": {
id: "grok-beta",
name: "Grok Beta",