{
"version": "2.0",
"updated_at": "2026-03-07T04:37:00.000000Z",
"providers": {
"google": {
"label": "Google Gemini",
"endpoints": {
"global": {
"label": "Google Gemini",
"region": "global",
"base_url": "https://generativelanguage.googleapis.com/v1beta",
"price_currency": "USD",
"docs_url": "https://ai.google.dev/gemini-api/docs/models"
}
},
"models": [
{
"id": "gemini-3",
"name": "Gemini 3",
"description": "Next generation multimodal model with frontier intelligence",
"supports_tools": true,
"context_length": 2000000,
"input_price": 5.0,
"output_price": 20.0
},
{
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"description": "Preview model",
"supports_tools": true,
"context_length": null,
"input_price": 2.0,
"output_price": 12.0
},
{
"id": "gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"description": "Preview model with custom tools",
"supports_tools": true,
"context_length": null,
"input_price": 2.0,
"output_price": 12.0
},
{
"id": "gemini-3-pro-image-preview",
"name": "Gemini 3 Pro Image Preview",
"description": "Preview image generation model",
"supports_tools": true,
"context_length": null,
"input_price": 2.0,
"output_price": 12.0
},
{
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"description": "Preview flash model",
"supports_tools": true,
"context_length": null,
"input_price": 0.5,
"output_price": 3.0
},
{
"id": "gemini-embedding-001",
"name": "Gemini Embedding 001",
"description": "Embedding model",
"supports_tools": false,
"context_length": null,
"input_price": 0.15,
"output_price": 0.15
},
{
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Highly capable multimodal model for complex reasoning and tasks",
"supports_tools": true,
"context_length": 2000000,
"input_price": 1.25,
"output_price": 10.0
},
{
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast and versatile multimodal model for high-volume tasks",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.1,
"output_price": 0.4
},
{
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash-Lite",
"description": "Lite version of Gemini 2.5 Flash for ultra-fast response",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.05,
"output_price": 0.2
},
{
"id": "gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"description": "Previous flagship flash model, fast and efficient",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.1,
"output_price": 0.4
},
{
"id": "gemini-1.5-pro",
"name": "Gemini 1.5 Pro",
"description": "Mid-range model with massive context window",
"supports_tools": true,
"context_length": 2000000,
"input_price": 3.5,
"output_price": 10.5
},
{
"id": "gemini-1.5-flash",
"name": "Gemini 1.5 Flash",
"description": "Fast and cost-efficient multimodal model",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.075,
"output_price": 0.3
}
]
},
"openai": {
"label": "OpenAI",
"endpoints": {
"global": {
"label": "OpenAI",
"region": "global",
"base_url": "https://api.openai.com/v1",
"price_currency": "USD",
"docs_url": null
}
},
"models": [
{
"id": "gpt-5.2",
"name": "GPT-5.2",
"description": "Best general-purpose, complex reasoning, tool calling, vision",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.5,
"output_price": 10.0
},
{
"id": "gpt-5.2-pro",
"name": "GPT-5.2 Pro",
"description": "Harder thinking for tough problems",
"supports_tools": true,
"context_length": 128000,
"input_price": 5.0,
"output_price": 20.0
},
{
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"description": "Interactive coding products",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.5,
"output_price": 10.0
},
{
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Cost-optimized reasoning and chat",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.4,
"output_price": 1.6
},
{
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"description": "High-throughput, simple tasks",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.1,
"output_price": 0.4
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "Flagship multimodal model",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.5,
"output_price": 10.0
},
{
"id": "gpt-4o-mini",
"name": "GPT-4o Mini",
"description": "Fast and affordable",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.15,
"output_price": 0.6
},
{
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "Advanced reasoning",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.5,
"output_price": 10.0
},
{
"id": "o1",
"name": "o1",
"description": "Advanced reasoning model",
"supports_tools": false,
"context_length": 200000,
"input_price": 15.0,
"output_price": 60.0
},
{
"id": "o1-mini",
"name": "o1 Mini",
"description": "Efficient reasoning",
"supports_tools": false,
"context_length": 128000,
"input_price": 3.0,
"output_price": 12.0
},
{
"id": "gpt-3.5-turbo",
"name": "GPT-3.5 Turbo",
"description": "Fast and economical",
"supports_tools": true,
"context_length": 16385,
"input_price": 0.5,
"output_price": 1.5
}
]
},
"anthropic": {
"label": "Anthropic",
"endpoints": {
"global": {
"label": "Anthropic",
"region": "global",
"base_url": "https://api.anthropic.com",
"price_currency": "USD",
"docs_url": null
}
},
"models": [
{
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "Most intelligent for agents and coding",
"supports_tools": true,
"context_length": 200000,
"input_price": 5.0,
"output_price": 25.0
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Best balance of speed and intelligence",
"supports_tools": true,
"context_length": 200000,
"input_price": 3.0,
"output_price": 15.0
},
{
"id": "claude-haiku-4-5-20251001",
"name": "Claude Haiku 4.5",
"description": "Fastest with near-frontier intelligence",
"supports_tools": true,
"context_length": 200000,
"input_price": 1.0,
"output_price": 5.0
},
{
"id": "claude-sonnet-4-5-20250929",
"name": "Claude Sonnet 4.5",
"description": "Strong performance, 200K context",
"supports_tools": true,
"context_length": 200000,
"input_price": 3.0,
"output_price": 15.0
},
{
"id": "claude-opus-4-5-20251101",
"name": "Claude Opus 4.5",
"description": "Latest Opus generation",
"supports_tools": true,
"context_length": 200000,
"input_price": 5.0,
"output_price": 25.0
}
]
},
"deepseek": {
"label": "DeepSeek",
"endpoints": {
"cn": {
"label": "DeepSeek",
"region": "cn",
"base_url": "https://api.deepseek.com/v1",
"price_currency": "CNY",
"docs_url": "https://api-docs.deepseek.com/api/list-models"
},
"global": {
"label": "DeepSeek",
"region": "global",
"base_url": "https://api.deepseek.com/v1",
"price_currency": "USD",
"docs_url": "https://api-docs.deepseek.com/api/list-models"
}
},
"models": [
{
"id": "deepseek-chat",
"name": "DeepSeek Chat",
"description": "General chat model with 128K context",
"supports_tools": true,
"context_length": 131072,
"input_price": 2.0,
"output_price": 8.0
},
{
"id": "deepseek-reasoner",
"name": "DeepSeek Reasoner",
"description": "Reasoning model with 128K context, max 64K output",
"supports_tools": false,
"context_length": 131072,
"input_price": 4.0,
"output_price": 16.0
}
]
},
"aliyun": {
"label": "Aliyun Bailian",
"endpoints": {
"cn": {
"label": "Aliyun Bailian",
"region": "cn",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"price_currency": "CNY",
"docs_url": "https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction"
}
},
"models": [
{
"id": "qwen3-max",
"name": "Qwen3 Max",
"description": "Latest flagship, best for agentic coding and tool calling",
"supports_tools": true,
"context_length": 262144,
"input_price": 2.5,
"output_price": 10.0
},
{
"id": "qwen3.5-plus",
"name": "Qwen3.5 Plus",
"description": "Balanced performance, speed and cost, text/image/video input",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.8,
"output_price": 4.8
},
{
"id": "qwen3.5-flash",
"name": "Qwen3.5 Flash",
"description": "Fast model with low cost",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.2,
"output_price": 2.0
},
{
"id": "qwen-max",
"name": "Qwen Max",
"description": "Previous flagship for complex multi-step tasks",
"supports_tools": true,
"context_length": 262144,
"input_price": 2.4,
"output_price": 9.6
},
{
"id": "qwen-plus",
"name": "Qwen Plus",
"description": "Balanced performance, speed and cost, suitable for medium complexity tasks",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.8,
"output_price": 2.0
},
{
"id": "qwen-flash",
"name": "Qwen Flash",
"description": "Suitable for simple tasks with fast speed and low cost",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.15,
"output_price": 1.5
},
{
"id": "qwen-coder-turbo",
"name": "Qwen Coder Turbo",
"description": "Excellent code model, proficient in tool calling and environment interaction",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.001,
"output_price": 0.004
},
{
"id": "qwen-vl-max",
"name": "Qwen VL Max",
"description": "Multimodal model with powerful vision understanding",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.002,
"output_price": 0.02
},
{
"id": "qwen-audio-turbo",
"name": "Qwen Audio Turbo",
"description": "Audio understanding model",
"supports_tools": false,
"context_length": 131072,
"input_price": 0.0016,
"output_price": 0.01
},
{
"id": "qwen-long",
"name": "Qwen Long",
"description": "Long text processing model with longest context window",
"supports_tools": true,
"context_length": 10000000,
"input_price": 0.0005,
"output_price": 0.002
},
{
"id": "qwq-plus",
"name": "QwQ Plus",
"description": "Reasoning model with outstanding math and code capabilities",
"supports_tools": false,
"context_length": 131072,
"input_price": 0.0016,
"output_price": 0.004
}
]
},
"moonshot": {
"label": "Moonshot AI",
"endpoints": {
"cn": {
"label": "Moonshot AI",
"region": "cn",
"base_url": "https://api.moonshot.cn/v1",
"price_currency": "CNY",
"docs_url": "https://platform.moonshot.cn/docs/pricing/chat"
},
"global": {
"label": "Moonshot AI",
"region": "global",
"base_url": "https://api.moonshot.ai/v1",
"price_currency": "USD",
"docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2"
}
},
"models": [
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Latest flagship, 256K context, 1T params MoE, Agent Swarm",
"supports_tools": true,
"context_length": 262144,
"input_price": 4.0,
"output_price": 21.0
},
{
"id": "kimi-k2-0905-preview",
"name": "Kimi K2 0905",
"description": "Latest K2 model with 256K context, strong Agentic Coding",
"supports_tools": true,
"context_length": 262144,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "kimi-k2-turbo-preview",
"name": "Kimi K2 Turbo",
"description": "High-speed K2 with 256K context, 60-100 tokens/s",
"supports_tools": true,
"context_length": 262144,
"input_price": 8.0,
"output_price": 58.0
},
{
"id": "kimi-k2-0711-preview",
"name": "Kimi K2 0711",
"description": "Earlier K2 version with 128K context",
"supports_tools": true,
"context_length": 131072,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"description": "Deep reasoning model with 256K context",
"supports_tools": true,
"context_length": 262144,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "kimi-k2-thinking-turbo",
"name": "Kimi K2 Thinking Turbo",
"description": "High-speed deep reasoning with 256K context",
"supports_tools": true,
"context_length": 262144,
"input_price": 8.0,
"output_price": 58.0
},
{
"id": "kimi-latest",
"name": "Kimi Latest",
"description": "Auto-select model based on context (8K/32K/128K), vision support",
"supports_tools": true,
"context_length": 131072,
"input_price": 2.0,
"output_price": 10.0
},
{
"id": "moonshot-v1-8k",
"name": "Moonshot V1 8K",
"description": "Classic v1 model with 8K context",
"supports_tools": true,
"context_length": 8192,
"input_price": 2.0,
"output_price": 10.0
},
{
"id": "moonshot-v1-8k-vision-preview",
"name": "Moonshot V1 8K Vision Preview",
"description": "Vision model, understands image content and outputs text, context length 8K",
"supports_tools": true,
"context_length": 8192,
"input_price": 2.0,
"output_price": 10.0
},
{
"id": "moonshot-v1-32k",
"name": "Moonshot V1 32K",
"description": "Classic v1 model with 32K context",
"supports_tools": true,
"context_length": 32768,
"input_price": 5.0,
"output_price": 20.0
},
{
"id": "moonshot-v1-32k-vision-preview",
"name": "Moonshot V1 32K Vision Preview",
"description": "Vision model, understands image content and outputs text, context length 32K",
"supports_tools": true,
"context_length": 32768,
"input_price": 5.0,
"output_price": 20.0
},
{
"id": "moonshot-v1-128k",
"name": "Moonshot V1 128K",
"description": "Classic v1 model with 128K context",
"supports_tools": true,
"context_length": 131072,
"input_price": 10.0,
"output_price": 30.0
},
{
"id": "moonshot-v1-128k-vision-preview",
"name": "Moonshot V1 128K Vision Preview",
"description": "Vision model, understands image content and outputs text, context length 128K",
"supports_tools": true,
"context_length": 131072,
"input_price": 10.0,
"output_price": 30.0
}
]
},
"minimax": {
"label": "MiniMax",
"endpoints": {
"cn": {
"label": "MiniMax",
"region": "cn",
"base_url": "https://api.minimaxi.com/v1",
"price_currency": "CNY",
"docs_url": "https://platform.minimaxi.com/docs/guides/models-intro"
},
"global": {
"label": "MiniMax",
"region": "global",
"base_url": "https://api.minimax.io/v1",
"price_currency": "USD",
"docs_url": "https://platform.minimax.io/docs/guides/models-intro"
}
},
"models": [
{
"id": "MiniMax-M2.5",
"name": "MiniMax M2.5",
"description": "Latest flagship, 200K context, advanced reasoning",
"supports_tools": true,
"context_length": 204800,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-M2.5-highspeed",
"name": "MiniMax M2.5 Highspeed",
"description": "Same as M2.5 with faster inference (~100 tps)",
"supports_tools": true,
"context_length": 204800,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-M2.1",
"name": "MiniMax M2.1",
"description": "230B parameters, 10B activation, optimized for code generation and refactoring",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-M2.1-highspeed",
"name": "MiniMax M2.1 Highspeed",
"description": "Same performance as M2.1 with faster inference speed",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-M2",
"name": "MiniMax M2",
"description": "200K context, 128K output, supports function calling and advanced reasoning",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "M2-her",
"name": "MiniMax M2-her",
"description": "Multi-character roleplay, immersive long-horizon interaction",
"supports_tools": true,
"context_length": 204800,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "speech-2.8-hd",
"name": "Speech 2.8 HD",
"description": "Ultimate similarity, ultra-high quality voice generation",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "speech-2.8-turbo",
"name": "Speech 2.8 Turbo",
"description": "Best cost-performance, low latency voice generation",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "speech-2.6-hd",
"name": "Speech 2.6 HD",
"description": "Ultimate similarity, ultra-high quality voice generation, supports 40 languages",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "speech-2.6-turbo",
"name": "Speech 2.6 Turbo",
"description": "Best cost-performance, low latency voice generation, supports 40 languages",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "speech-02-hd",
"name": "Speech 02 HD",
"description": "Enhanced replication similarity, high quality voice generation, supports 24 languages",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "speech-02-turbo",
"name": "Speech 02 Turbo",
"description": "Excellent prosody and stability, low latency, supports 24 languages",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-Hailuo-2.3",
"name": "MiniMax Hailuo 2.3",
"description": "Text-to-video and image-to-video, 1080p/768p resolution, 6-10 seconds duration",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-Hailuo-2.3Fast",
"name": "MiniMax Hailuo 2.3 Fast",
"description": "Image-to-video with ultimate physics control, high cost-effectiveness",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "MiniMax-Hailuo-02",
"name": "MiniMax Hailuo 02",
"description": "Text-to-video and image-to-video with SOTA instruction following and ultimate physics control",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "image-01",
"name": "Image 01",
"description": "Text-to-image generation",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "image-01-live",
"name": "Image 01 Live",
"description": "Text-to-image generation (live)",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "music-2.5+",
"name": "Music 2.5+",
"description": "Text-to-music generation",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "music-2.5",
"name": "Music 2.5",
"description": "Text-to-music generation",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "Music-2.0",
"name": "Music 2.0",
"description": "Text-to-music with enhanced musicality, natural vocals and smooth melodies",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"zhipu": {
"label": "Zhipu AI",
"endpoints": {
"cn": {
"label": "Zhipu AI",
"region": "cn",
"base_url": "https://open.bigmodel.cn/api/paas/v4",
"price_currency": "CNY",
"docs_url": "https://docs.bigmodel.cn/cn/guide/start/model-overview"
},
"global": {
"label": "Zhipu AI",
"region": "global",
"base_url": "https://api.z.ai/api/paas/v4",
"price_currency": "USD",
"docs_url": "https://docs.z.ai/api-reference/introduction"
}
},
"endpoint_models": {
"cn": [
{
"id": "glm-5",
"name": "GLM-5",
"description": "Fifth gen flagship, 745B params, 200K context, SOTA reasoning",
"supports_tools": true,
"context_length": 200000,
"input_price": 4.0,
"output_price": 18.0
},
{
"id": "glm-5-code",
"name": "GLM-5-Code",
"description": "Coding optimized model",
"supports_tools": true,
"context_length": 200000,
"input_price": 6.0,
"output_price": 28.0
},
{
"id": "glm-4.7",
"name": "GLM-4.7",
"description": "Latest flagship model, released December 2025",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.0,
"output_price": 8.0
},
{
"id": "glm-4.7-flashx",
"name": "GLM-4.7-FlashX",
"description": "Ultra-fast model",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.5,
"output_price": 3.0
},
{
"id": "glm-4.7-flash",
"name": "GLM-4.7-Flash",
"description": "Free model",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "glm-4.6",
"name": "GLM-4.6",
"description": "Flagship model with 200K context, advanced coding ability",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.6v",
"name": "GLM-4.6V",
"description": "Vision model with multimodal capabilities",
"supports_tools": true,
"context_length": 128000,
"input_price": 1.0,
"output_price": 3.0
},
{
"id": "glm-4.6v-flashx",
"name": "GLM-4.6V-FlashX",
"description": "Ultra-fast vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.15,
"output_price": 1.5
},
{
"id": "glm-4.6v-flash",
"name": "GLM-4.6V-Flash",
"description": "Free vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "glm-4.5",
"name": "GLM-4.5",
"description": "Strong performance with powerful reasoning and code generation, 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.5v",
"name": "GLM-4.5V",
"description": "Vision model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 1.8
},
{
"id": "glm-4.5-x",
"name": "GLM-4.5-X",
"description": "Ultra-fast version with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.2,
"output_price": 8.9
},
{
"id": "glm-4.5-air",
"name": "GLM-4.5 Air",
"description": "Best performance at same parameter scale, 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.8,
"output_price": 2.0
},
{
"id": "glm-4.5-airx",
"name": "GLM-4.5 AirX",
"description": "Fast inference with cost-effective pricing",
"supports_tools": true,
"context_length": 128000,
"input_price": 1.1,
"output_price": 4.5
},
{
"id": "glm-4-32b-0414-128k",
"name": "GLM-4-32B-0414-128K",
"description": "32B parameter model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.1,
"output_price": 0.1
},
{
"id": "glm-4.6v-flash",
"name": "GLM-4.6V-Flash",
"description": "Free vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "glm-4.5v",
"name": "GLM-4.5V",
"description": "Vision model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.0,
"output_price": 6.0
},
{
"id": "glm-4.5-flash",
"name": "GLM-4.5-Flash",
"description": "Free model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
}
],
"global": [
{
"id": "glm-5",
"name": "GLM-5",
"description": "Fifth gen flagship, 745B params, 200K context, SOTA reasoning",
"supports_tools": true,
"context_length": 200000,
"input_price": 1.0,
"output_price": 3.2
},
{
"id": "glm-5-code",
"name": "GLM-5-Code",
"description": "Coding optimized model",
"supports_tools": true,
"context_length": 200000,
"input_price": 1.2,
"output_price": 5.0
},
{
"id": "glm-4.7",
"name": "GLM-4.7",
"description": "Latest flagship model, released December 2025",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.7-flashx",
"name": "GLM-4.7-FlashX",
"description": "Ultra-fast model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.07,
"output_price": 0.4
},
{
"id": "glm-4.6",
"name": "GLM-4.6",
"description": "Flagship model with 200K context, advanced coding ability",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.5",
"name": "GLM-4.5",
"description": "Strong performance with powerful reasoning and code generation, 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.5-x",
"name": "GLM-4.5-X",
"description": "Ultra-fast version with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.2,
"output_price": 8.9
},
{
"id": "glm-4.5-air",
"name": "GLM-4.5-Air",
"description": "Best performance at same parameter scale, 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.2,
"output_price": 1.1
},
{
"id": "glm-4.5-airx",
"name": "GLM-4.5-AirX",
"description": "Fast inference with cost-effective pricing",
"supports_tools": true,
"context_length": 128000,
"input_price": 1.1,
"output_price": 4.5
},
{
"id": "glm-4-32b-0414-128k",
"name": "GLM-4-32B-0414-128K",
"description": "32B parameter model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.1,
"output_price": 0.1
},
{
"id": "glm-4.7-flash",
"name": "GLM-4.7-Flash",
"description": "Free model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "glm-4.5-flash",
"name": "GLM-4.5-Flash",
"description": "Free model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "glm-4.6v",
"name": "GLM-4.6V",
"description": "Vision model with multimodal capabilities",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.3,
"output_price": 0.9
},
{
"id": "glm-ocr",
"name": "GLM-OCR",
"description": "OCR model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.03,
"output_price": 0.03
},
{
"id": "glm-4.6v-flashx",
"name": "GLM-4.6V-FlashX",
"description": "Ultra-fast vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.04,
"output_price": 0.4
},
{
"id": "glm-4.5v",
"name": "GLM-4.5V",
"description": "Vision model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 1.8
},
{
"id": "glm-4.6v-flash",
"name": "GLM-4.6V-Flash",
"description": "Free vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"models": [
{
"id": "glm-5",
"name": "GLM-5",
"description": "Fifth gen flagship, 745B params, 200K context, SOTA reasoning",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.7",
"name": "GLM-4.7",
"description": "Latest flagship model, released December 2025",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.6",
"name": "GLM-4.6",
"description": "Flagship model with 200K context, advanced coding ability",
"supports_tools": true,
"context_length": 200000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.6v",
"name": "GLM-4.6V",
"description": "Vision model with multimodal capabilities",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.3,
"output_price": 0.9
},
{
"id": "glm-4.6v-flashx",
"name": "GLM-4.6V-FlashX",
"description": "Ultra-fast vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.04,
"output_price": 0.4
},
{
"id": "glm-4.5",
"name": "GLM-4.5",
"description": "Strong performance with powerful reasoning and code generation, 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 2.2
},
{
"id": "glm-4.5v",
"name": "GLM-4.5V",
"description": "Vision model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.6,
"output_price": 1.8
},
{
"id": "glm-4.5-x",
"name": "GLM-4.5-X",
"description": "Ultra-fast version with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.2,
"output_price": 8.9
},
{
"id": "glm-4.5-air",
"name": "GLM-4.5 Air",
"description": "Best performance at same parameter scale, 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.2,
"output_price": 1.1
},
{
"id": "glm-4.5-airx",
"name": "GLM-4.5 AirX",
"description": "Fast inference with cost-effective pricing",
"supports_tools": true,
"context_length": 128000,
"input_price": 1.1,
"output_price": 4.5
},
{
"id": "glm-4-32b-0414-128k",
"name": "GLM-4-32B-0414-128K",
"description": "32B parameter model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.1,
"output_price": 0.1
},
{
"id": "glm-4.6v-flash",
"name": "GLM-4.6V-Flash",
"description": "Free vision model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "glm-4.5-flash",
"name": "GLM-4.5-Flash",
"description": "Free model with 128K context",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"tencent": {
"label": "Tencent Hunyuan",
"endpoints": {
"cn": {
"label": "Tencent Hunyuan",
"region": "cn",
"base_url": "https://hunyuan.tencentcloudapi.com",
"price_currency": "CNY",
"docs_url": "https://cloud.tencent.com/document/product/1729/104753"
}
},
"models": [
{
"id": "hunyuan-2.0-thinking-20251109",
"name": "Tencent HY 2.0 Think",
"description": "Hunyuan 2.0 thinking model with enhanced complex instruction following, multi-turn and long-text understanding, code, agent, and reasoning capabilities",
"supports_tools": true,
"context_length": 131072,
"input_price": 3.975,
"output_price": 15.9
},
{
"id": "hunyuan-2.0-instruct-20251111",
"name": "Tencent HY 2.0 Instruct",
"description": "Hunyuan 2.0 instruction model with enhanced instruction following, multi-turn and long-text understanding, creative writing, knowledge accuracy, code and reasoning capabilities",
"supports_tools": true,
"context_length": 131072,
"input_price": 3.18,
"output_price": 7.95
},
{
"id": "hunyuan-t1-latest",
"name": "Hunyuan T1 Latest",
"description": "Industry's first large-scale Hybrid-Transformer-Mamba reasoning model with extended reasoning capability and ultra-fast decoding speed",
"supports_tools": true,
"context_length": 32768,
"input_price": 1.0,
"output_price": 4.0
},
{
"id": "hunyuan-a13b",
"name": "Hunyuan A13B",
"description": "Hunyuan MoE structure with 80B total parameters, 13B activation, supports fast/slow thinking mode switching",
"supports_tools": true,
"context_length": 229376,
"input_price": 0.5,
"output_price": 2.0
},
{
"id": "hunyuan-turbos-latest",
"name": "Hunyuan TurboS Latest",
"description": "Latest version of Hunyuan flagship model with stronger thinking capabilities and better experience",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.8,
"output_price": 2.0
},
{
"id": "hunyuan-lite",
"name": "Hunyuan Lite",
"description": "Upgraded to MOE structure with 256K context window, leading many open-source models in multiple benchmarks",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "hunyuan-translation",
"name": "Hunyuan Translation",
"description": "Supports 33 language translations and 5 ethnic language translations, ranked 1st in 30 languages at WMT25",
"supports_tools": false,
"context_length": 4096,
"input_price": 1.2,
"output_price": 3.6
},
{
"id": "hunyuan-translation-lite",
"name": "Hunyuan Translation Lite",
"description": "Translation specialized model based on Hunyuan 2B-Dense, supports 16+ language translations",
"supports_tools": false,
"context_length": 4096,
"input_price": 1.0,
"output_price": 3.0
},
{
"id": "hunyuan-large-role-latest",
"name": "Hunyuan Large Role Latest",
"description": "Role-playing specialized model with significantly improved character consistency and dialogue depth",
"supports_tools": false,
"context_length": 28672,
"input_price": 2.4,
"output_price": 9.6
},
{
"id": "hunyuan-vision-1.5-instruct",
"name": "Tencent HY Vision 1.5 Instruct",
"description": "Image-to-text fast thinking model with significant improvements in image recognition, analysis and reasoning",
"supports_tools": true,
"context_length": 24576,
"input_price": 3.0,
"output_price": 9.0
},
{
"id": "hunyuan-t1-vision-20250916",
"name": "Hunyuan T1 Vision",
"description": "Vision deep thinking model with comprehensive improvements in general image-text Q&A, visual grounding, OCR, charts, problem solving, and image-based creation",
"supports_tools": true,
"context_length": 28672,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "hunyuan-large-vision",
"name": "Hunyuan Large Vision",
"description": "Vision-language model based on Hunyuan Large, supports arbitrary resolution multiple images + text input",
"supports_tools": true,
"context_length": 24576,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "hunyuan-turbos-vision-video",
"name": "Hunyuan TurboS Vision Video",
"description": "Video understanding model supporting video description, video Q&A and other basic video understanding capabilities",
"supports_tools": true,
"context_length": 24576,
"input_price": 3.0,
"output_price": 9.0
},
{
"id": "hunyuan-embedding",
"name": "Hunyuan Embedding",
"description": "Text embedding model",
"supports_tools": false,
"context_length": null,
"input_price": 0.7,
"output_price": 0.7
}
]
},
"volcengine": {
"label": "Volcengine",
"endpoints": {
"cn": {
"label": "Volcengine",
"region": "cn",
"base_url": "https://ark.cn-beijing.volces.com/api/v3",
"price_currency": "CNY",
"docs_url": "https://www.volcengine.com/docs/82379/1330310"
}
},
"models": [
{
"id": "GLM-4.7",
"name": "GLM-4.7",
"description": "Zhipu GLM model provided via Ark",
"supports_tools": true,
"context_length": 200000,
"input_price": 2.0,
"output_price": 8.0
},
{
"id": "deepseek-r1",
"name": "DeepSeek R1",
"description": "Deep thinking model",
"supports_tools": true,
"context_length": 131072,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "deepseek-v3.1",
"name": "DeepSeek V3.1",
"description": "Deep thinking, text generation, tool calling",
"supports_tools": true,
"context_length": 131072,
"input_price": 4.0,
"output_price": 12.0
},
{
"id": "deepseek-v3",
"name": "DeepSeek V3",
"description": "Deep thinking, text generation, tool calling",
"supports_tools": true,
"context_length": 131072,
"input_price": 2.0,
"output_price": 8.0
},
{
"id": "doubao-1.5-lite-32k",
"name": "Doubao 1.5 Lite 32K",
"description": "Lite 32K model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.3,
"output_price": 0.6
},
{
"id": "doubao-1.5-pro-32k",
"name": "Doubao 1.5 Pro 32K",
"description": "Pro 32K model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.8,
"output_price": 2.0
},
{
"id": "doubao-1.5-thinking-pro",
"name": "Doubao 1.5 Thinking Pro",
"description": "Thinking Pro model",
"supports_tools": true,
"context_length": 262144,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "doubao-1.5-thinking-vision-pro",
"name": "Doubao 1.5 Thinking Vision Pro",
"description": "Thinking + vision model",
"supports_tools": true,
"context_length": 262144,
"input_price": 3.0,
"output_price": 9.0
},
{
"id": "doubao-1.5-ui-tars",
"name": "Doubao 1.5 UI Tars",
"description": "GUI task model",
"supports_tools": true,
"context_length": 262144,
"input_price": 3.5,
"output_price": 12.0
},
{
"id": "doubao-1.5-vision-lite",
"name": "Doubao 1.5 Vision Lite",
"description": "Vision lite model",
"supports_tools": true,
"context_length": 262144,
"input_price": 1.5,
"output_price": 4.5
},
{
"id": "doubao-1.5-vision-pro",
"name": "Doubao 1.5 Vision Pro",
"description": "Vision pro model",
"supports_tools": true,
"context_length": 262144,
"input_price": 3.0,
"output_price": 9.0
},
{
"id": "doubao-lite-32k",
"name": "Doubao Lite 32K",
"description": "Lite 32K model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.3,
"output_price": 0.6
},
{
"id": "doubao-seed-2.0-code",
"name": "Doubao Seed 2.0 Code",
"description": "Seed 2.0 coding model",
"supports_tools": true,
"context_length": 262144,
"input_price": 3.2,
"output_price": 16.0
},
{
"id": "doubao-seed-2.0-lite",
"name": "Doubao Seed 2.0 Lite",
"description": "Seed 2.0 lite model",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.6,
"output_price": 3.6
},
{
"id": "doubao-seed-2.0-mini",
"name": "Doubao Seed 2.0 Mini",
"description": "Seed 2.0 mini model",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.2,
"output_price": 2.0
},
{
"id": "doubao-seed-2.0-pro",
"name": "Doubao Seed 2.0 Pro",
"description": "Seed 2.0 pro model",
"supports_tools": true,
"context_length": 262144,
"input_price": 3.2,
"output_price": 16.0
},
{
"id": "doubao-seed-code",
"name": "Doubao Seed Code",
"description": "Programming enhanced model",
"supports_tools": true,
"context_length": 262144,
"input_price": 1.2,
"output_price": 8.0
},
{
"id": "doubao-seed-1.6",
"name": "Doubao Seed 1.6",
"description": "General model with deep thinking, text generation and tool calling",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.8,
"output_price": 2.0
},
{
"id": "doubao-seed-1.6-thinking",
"name": "Doubao Seed 1.6 Thinking",
"description": "Deep thinking model",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.8,
"output_price": 8.0
},
{
"id": "doubao-seed-1-8-251215",
"name": "Doubao Seed 1.8",
"description": "Most powerful multimodal agent model with enhanced capabilities",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.8,
"output_price": 2.0
},
{
"id": "doubao-seed-code-preview-251028",
"name": "Doubao Seed Code Preview",
"description": "Programming enhanced - deep thinking, text generation, multimodal understanding, tool calling",
"supports_tools": true,
"context_length": 262144,
"input_price": 1.2,
"output_price": 8.0
},
{
"id": "doubao-seed-1-6-lite-251015",
"name": "Doubao Seed 1.6 Lite",
"description": "Lightweight model with deep thinking, text generation, multimodal understanding, tool calling",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.3,
"output_price": 0.6
},
{
"id": "doubao-seed-1-6-flash-250828",
"name": "Doubao Seed 1.6 Flash",
"description": "Fast model with deep thinking, text generation, vision grounding, multimodal understanding",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.15,
"output_price": 1.5
},
{
"id": "doubao-seed-1-6-vision-250815",
"name": "Doubao Seed 1.6 Vision",
"description": "Vision model with deep thinking, multimodal understanding, GUI task processing",
"supports_tools": true,
"context_length": 262144,
"input_price": 0.8,
"output_price": 8.0
},
{
"id": "doubao-seed-translation-250915",
"name": "Doubao Seed Translation",
"description": "Translation enhanced model",
"supports_tools": false,
"context_length": 4096,
"input_price": 1.2,
"output_price": 3.6
},
{
"id": "deepseek-v3-2-251201",
"name": "DeepSeek V3.2",
"description": "Deep thinking, text generation, tool calling",
"supports_tools": true,
"context_length": 131072,
"input_price": 2.0,
"output_price": 3.0
},
{
"id": "deepseek-v3-1-terminus",
"name": "DeepSeek V3.1 Terminus",
"description": "Deep thinking, text generation, tool calling",
"supports_tools": true,
"context_length": 131072,
"input_price": 4.0,
"output_price": 12.0
},
{
"id": "kimi-k2",
"name": "Kimi K2",
"description": "Kimi K2 model provided via Ark",
"supports_tools": true,
"context_length": 262144,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "kimi-k2-thinking-251104",
"name": "Kimi K2 Thinking",
"description": "Deep thinking, tool calling",
"supports_tools": true,
"context_length": 262144,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "doubao-seedance-1-5-pro-251215",
"name": "Doubao Seedance 1.5 Pro",
"description": "Powerful video generation model with high-precision audio-visual sync",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "doubao-seedream-4-5-251128",
"name": "Doubao Seedream 4.5",
"description": "Powerful image generation model with multi-image fusion and strong editing consistency",
"supports_tools": false,
"context_length": 4096,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"longcat": {
"label": "LongCat",
"endpoints": {
"cn": {
"label": "LongCat",
"region": "cn",
"base_url": "https://api.longcat.chat/openai/v1",
"price_currency": "CNY",
"docs_url": "https://longcat.chat/platform/docs/zh/"
}
},
"models": [
{
"id": "LongCat-Flash-Chat",
"name": "LongCat Flash Chat",
"description": "High-performance general chat model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "LongCat-Flash-Thinking",
"name": "LongCat Flash Thinking",
"description": "Deep thinking model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "LongCat-Flash-Thinking-2601",
"name": "LongCat Flash Thinking 2601",
"description": "Upgraded deep thinking model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "LongCat-Flash-Lite",
"name": "LongCat Flash Lite",
"description": "Efficient lightweight MoE model",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"openrouter": {
"label": "OpenRouter",
"endpoints": {
"global": {
"label": "OpenRouter",
"region": "global",
"base_url": "https://openrouter.ai/api/v1",
"price_currency": "USD",
"docs_url": "https://openrouter.ai/docs"
}
},
"models": [
{
"id": "openrouter/auto",
"name": "OpenRouter Auto",
"description": "Aggregator router; downstream model and pricing follow OpenRouter settings",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"zenmux": {
"label": "Zenmux.ai",
"endpoints": {
"global": {
"label": "Zenmux.ai",
"region": "global",
"base_url": "https://api.zenmux.ai/v1",
"price_currency": "USD",
"docs_url": "https://docs.zenmux.ai"
}
},
"models": [
{
"id": "zenmux/auto",
"name": "Zenmux Auto",
"description": "Aggregator router; downstream model and pricing follow Zenmux routing",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"baseten": {
"label": "Baseten",
"endpoints": {
"global": {
"label": "Baseten",
"region": "global",
"base_url": "https://bridge.baseten.co/v1",
"price_currency": "USD",
"docs_url": "https://docs.baseten.co"
}
},
"models": [
{
"id": "baseten/auto",
"name": "Baseten Auto",
"description": "Router selects deployed Baseten model",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"cerebras": {
"label": "Cerebras",
"endpoints": {
"global": {
"label": "Cerebras",
"region": "global",
"base_url": "https://api.cerebras.ai/v1",
"price_currency": "USD",
"docs_url": "https://inference-docs.cerebras.ai/introduction"
}
},
"models": [
{
"id": "llama3.1-8b",
"name": "Llama 3.1 8B",
"description": "Production Llama 3.1 8B served by Cerebras",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "gpt-oss-120b",
"name": "OpenAI GPT OSS",
"description": "Production OpenAI GPT OSS 120B served by Cerebras",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "qwen-3-235b-a22b-instruct-2507",
"name": "Qwen 3 235B Instruct",
"description": "Preview Qwen 3 235B Instruct served by Cerebras",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "zai-glm-4.7",
"name": "Z.ai GLM 4.7",
"description": "Preview Zhipu GLM 4.7 served by Cerebras",
"supports_tools": true,
"context_length": null,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"grok": {
"label": "Grok (xAI)",
"endpoints": {
"global": {
"label": "Grok",
"region": "global",
"base_url": "https://api.x.ai/v1",
"price_currency": "USD",
"docs_url": "https://docs.x.ai"
}
},
"models": [
{
"id": "grok-4.1-fast-reasoning",
"name": "grok-4.1-fast-reasoning",
"description": "Fast reasoning model (tools, 2M context)",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5
},
{
"id": "grok-4.1-fast-non-reasoning",
"name": "grok-4.1-fast-non-reasoning",
"description": "Fast non-reasoning model (tools, 2M context)",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5
},
{
"id": "grok-code-fast-1",
"name": "grok-code-fast-1",
"description": "Fast code model (tools)",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.2,
"output_price": 1.5
},
{
"id": "grok-4-fast-reasoning",
"name": "grok-4-fast-reasoning",
"description": "Reasoning model (tools, 2M context)",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5
},
{
"id": "grok-4-fast-non-reasoning",
"name": "grok-4-fast-non-reasoning",
"description": "Non-reasoning model (tools, 2M context)",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5
},
{
"id": "grok-4-0709",
"name": "grok-4-0709",
"description": "Grok 4 0709 (tools)",
"supports_tools": true,
"context_length": 256000,
"input_price": 3.0,
"output_price": 15.0
},
{
"id": "grok-3-mini",
"name": "grok-3-mini",
"description": "Grok 3 mini (tools)",
"supports_tools": true,
"context_length": 131072,
"input_price": 0.3,
"output_price": 0.5
},
{
"id": "grok-3",
"name": "grok-3",
"description": "Grok 3 (tools)",
"supports_tools": true,
"context_length": 131072,
"input_price": 3.0,
"output_price": 15.0
},
{
"id": "grok-realtime-api",
"name": "Realtime API",
"description": "Realtime API (per minute)",
"supports_tools": false,
"context_length": null,
"input_price": 0.05,
"output_price": 0.05
},
{
"id": "grok-text-to-speech",
"name": "Text to Speech",
"description": "Text to Speech (per 1M tokens)",
"supports_tools": false,
"context_length": null,
"input_price": 4.2,
"output_price": 4.2
}
]
},
"mistral": {
"label": "Mistral AI",
"endpoints": {
"global": {
"label": "Mistral AI",
"region": "global",
"base_url": "https://api.mistral.ai/v1",
"price_currency": "USD",
"docs_url": "https://docs.mistral.ai"
}
},
"models": [
{
"id": "mistral-large-latest",
"name": "Mistral Large Latest",
"description": "Flagship reasoning and multimodal model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mistral-small-latest",
"name": "Mistral Small Latest",
"description": "Fast and economical general model",
"supports_tools": true,
"context_length": 32000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "codestral-latest",
"name": "Codestral Latest",
"description": "Code-specialized model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "pixtral-12b-vision",
"name": "Pixtral 12B Vision",
"description": "Vision-capable Pixtral model",
"supports_tools": true,
"context_length": 128000,
"input_price": 0.0,
"output_price": 0.0
}
]
}
}
}