{
"version": "3.0",
"updated_at": "2026-06-03T00:00:00.000000Z",
"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-3.5-flash",
"name": "Gemini 3.5 Flash",
"description": "Latest stable Flash model with frontier intelligence and search grounding",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.5,
"output_price": 9.0,
"published_at": "2026-05-01"
},
{
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"description": "Preview of Gemini 3.1 Pro with enhanced reasoning and agentic capabilities",
"supports_tools": true,
"context_length": 1000000,
"input_price": 2.0,
"output_price": 12.0,
"published_at": "2026-02-19"
},
{
"id": "gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"description": "Gemini 3.1 Pro Preview variant optimized for custom tool use",
"supports_tools": true,
"context_length": 1000000,
"input_price": 2.0,
"output_price": 12.0,
"published_at": "2026-02-19"
},
{
"id": "gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash-Lite",
"description": "Stable cost-efficient model for high-volume agentic tasks",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.25,
"output_price": 1.5,
"published_at": "2026-05-01"
},
{
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"description": "Intelligent model built for speed with frontier intelligence and search grounding",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.5,
"output_price": 3.0,
"published_at": "2025-12-17"
},
{
"id": "gemini-3-pro-image",
"name": "Gemini 3 Pro Image",
"description": "Native image generation model optimized for speed and contextual understanding",
"supports_tools": true,
"context_length": 1000000,
"input_price": 2.0,
"output_price": 12.0,
"published_at": "2025-11-20"
},
{
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Advanced reasoning model with 1M context window",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.25,
"output_price": 10.0,
"published_at": "2025-06-17"
},
{
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Hybrid reasoning model for low-latency, high-volume tasks",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.3,
"output_price": 2.5,
"published_at": "2025-06-17"
},
{
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash-Lite",
"description": "Smallest and most cost-effective model for at-scale usage",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.1,
"output_price": 0.4,
"published_at": "2025-06-17"
},
{
"id": "gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"description": "Deprecated previous generation flash model",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.1,
"output_price": 0.4,
"published_at": "2024-12-11"
},
{
"id": "gemini-1.5-pro",
"name": "Gemini 1.5 Pro",
"description": "Legacy model with 2M context window",
"supports_tools": true,
"context_length": 2000000,
"input_price": 1.25,
"output_price": 5.0,
"published_at": "2024-05-14"
},
{
"id": "gemini-1.5-flash",
"name": "Gemini 1.5 Flash",
"description": "Legacy fast and cost-efficient multimodal model",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.075,
"output_price": 0.3,
"published_at": "2024-05-14"
},
{
"id": "gemini-embedding-001",
"name": "Gemini Embedding 001",
"description": "Text embedding model",
"supports_tools": false,
"context_length": null,
"input_price": 0.15,
"output_price": 0.0
}
]
},
"openai": {
"label": "OpenAI",
"endpoints": {
"global": {
"label": "OpenAI",
"region": "global",
"base_url": "https://api.openai.com/v1",
"price_currency": "USD",
"docs_url": "https://developers.openai.com/api/docs/models"
}
},
"models": [
{
"id": "gpt-5.5",
"name": "GPT-5.5",
"description": "Flagship model for complex reasoning, coding, and professional work",
"supports_tools": true,
"context_length": 1050000,
"input_price": 5.0,
"output_price": 30.0,
"published_at": "2026-04-24"
},
{
"id": "gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"description": "High-compute variant of GPT-5.5 for smarter and more precise responses",
"supports_tools": true,
"context_length": 1050000,
"input_price": 30.0,
"output_price": 180.0,
"published_at": "2026-04-24"
},
{
"id": "gpt-5.4",
"name": "GPT-5.4",
"description": "Frontier model for coding and professional work at lower cost than GPT-5.5",
"supports_tools": true,
"context_length": 1050000,
"input_price": 2.5,
"output_price": 15.0,
"published_at": "2026-03-05"
},
{
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"description": "Maximum capability GPT-5.4 variant for complex high-stakes tasks",
"supports_tools": true,
"context_length": 1050000,
"input_price": 30.0,
"output_price": 180.0,
"published_at": "2026-03-05"
},
{
"id": "gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"description": "Strong mini model for coding, computer use, and subagents",
"supports_tools": true,
"context_length": 400000,
"input_price": 0.75,
"output_price": 4.5,
"published_at": "2026-03-17"
},
{
"id": "gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"description": "Ultra-low-cost model for classification, routing, and simple tasks",
"supports_tools": true,
"context_length": 400000,
"input_price": 0.2,
"output_price": 1.25,
"published_at": "2026-03-17"
},
{
"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,
"published_at": "2024-11-01"
},
{
"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,
"published_at": "2024-12-01"
},
{
"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,
"published_at": "2024-11-15"
},
{
"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,
"published_at": "2024-10-01"
},
{
"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,
"published_at": "2024-10-01"
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "Flagship multimodal model",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.5,
"output_price": 10.0,
"published_at": "2024-05-13"
},
{
"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,
"published_at": "2024-07-18"
},
{
"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,
"published_at": "2024-08-01"
},
{
"id": "o1",
"name": "o1",
"description": "Advanced reasoning model",
"supports_tools": false,
"context_length": 200000,
"input_price": 15.0,
"output_price": 60.0,
"published_at": "2024-09-12"
},
{
"id": "o1-mini",
"name": "o1 Mini",
"description": "Efficient reasoning",
"supports_tools": false,
"published_at": "2024-09-12",
"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": "https://docs.anthropic.com/en/docs/about-claude/models"
}
},
"models": [
{
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"description": "Latest flagship model for coding, agentic tasks, and professional work with 1M context",
"supports_tools": true,
"context_length": 1000000,
"input_price": 5.0,
"output_price": 25.0,
"published_at": "2026-05-28"
},
{
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Previous generation Opus for complex reasoning and agentic coding",
"supports_tools": true,
"context_length": 1000000,
"input_price": 5.0,
"output_price": 25.0,
"published_at": "2026-02-01"
},
{
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "Previous generation Opus for agents and coding",
"supports_tools": true,
"context_length": 1000000,
"input_price": 5.0,
"output_price": 25.0,
"published_at": "2025-10-01"
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Best balance of speed and intelligence for production workloads",
"supports_tools": true,
"context_length": 1000000,
"input_price": 3.0,
"output_price": 15.0,
"cache_read_price": 0.3,
"cache_write_price": 3.75,
"published_at": "2026-02-01"
},
{
"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"
}
},
"endpoint_models": {
"cn": [
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Efficient V4 model with 1M context, hybrid thinking/non-thinking modes",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2026-04-24"
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Flagship V4 model with 1M context and frontier agentic reasoning",
"supports_tools": true,
"context_length": 1000000,
"input_price": 3.0,
"output_price": 6.0,
"published_at": "2026-04-24"
},
{
"id": "deepseek-chat",
"name": "DeepSeek Chat",
"description": "Legacy alias for deepseek-v4-flash non-thinking mode (deprecated 2026-07-24)",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2024-05-01",
"deprecated_at": "2026-07-24",
"replacement_id": "deepseek-v4-flash"
},
{
"id": "deepseek-reasoner",
"name": "DeepSeek Reasoner",
"description": "Legacy alias for deepseek-v4-flash thinking mode (deprecated 2026-07-24)",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2025-01-01",
"deprecated_at": "2026-07-24",
"replacement_id": "deepseek-v4-flash"
}
],
"global": [
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Efficient V4 model with 1M context, hybrid thinking/non-thinking modes",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.14,
"output_price": 0.28,
"published_at": "2026-04-24"
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Flagship V4 model with 1M context and frontier agentic reasoning",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.435,
"output_price": 0.87,
"published_at": "2026-04-24"
},
{
"id": "deepseek-chat",
"name": "DeepSeek Chat",
"description": "Legacy alias for deepseek-v4-flash non-thinking mode (deprecated 2026-07-24)",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.14,
"output_price": 0.28,
"published_at": "2024-05-01",
"deprecated_at": "2026-07-24",
"replacement_id": "deepseek-v4-flash"
},
{
"id": "deepseek-reasoner",
"name": "DeepSeek Reasoner",
"description": "Legacy alias for deepseek-v4-flash thinking mode (deprecated 2026-07-24)",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.14,
"output_price": 0.28,
"published_at": "2025-01-01",
"deprecated_at": "2026-07-24",
"replacement_id": "deepseek-v4-flash"
}
]
},
"models": [
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Efficient V4 model with 1M context, hybrid thinking/non-thinking modes",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2026-04-24"
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Flagship V4 model with 1M context and frontier agentic reasoning",
"supports_tools": true,
"context_length": 1000000,
"input_price": 3.0,
"output_price": 6.0,
"published_at": "2026-04-24"
},
{
"id": "deepseek-chat",
"name": "DeepSeek Chat",
"description": "Legacy alias for deepseek-v4-flash non-thinking mode (deprecated 2026-07-24)",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2024-05-01",
"deprecated_at": "2026-07-24",
"replacement_id": "deepseek-v4-flash"
},
{
"id": "deepseek-reasoner",
"name": "DeepSeek Reasoner",
"description": "Legacy alias for deepseek-v4-flash thinking mode (deprecated 2026-07-24)",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2025-01-01",
"deprecated_at": "2026-07-24",
"replacement_id": "deepseek-v4-flash"
}
]
},
"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": "qwen3.6-max-preview",
"name": "Qwen3.6 Max Preview",
"description": "Preview flagship for complex tasks with the strongest capability",
"supports_tools": true,
"context_length": 262144,
"input_price": 9.0,
"output_price": 54.0,
"published_at": "2025-04-01"
},
{
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"description": "Balanced quality, speed, and cost with a 1M-token context window",
"supports_tools": true,
"context_length": 1000000,
"input_price": 2.0,
"output_price": 12.0
},
{
"id": "qwen3.6-flash",
"name": "Qwen3.6 Flash",
"description": "Fast low-cost model for simple tasks with a 1M-token context window",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.2,
"output_price": 7.2
},
{
"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"
}
},
"endpoint_models": {
"cn": [
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Latest flagship with Agent Swarm, multimodal input, and 256K context",
"supports_tools": true,
"context_length": 256000,
"input_price": 6.5,
"output_price": 27.0,
"published_at": "2026-04-21"
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "256K context, 1T params MoE, Agent Swarm",
"supports_tools": true,
"context_length": 256000,
"input_price": 4.0,
"output_price": 21.0
},
{
"id": "kimi-k2-0905-preview",
"name": "Kimi K2 0905",
"description": "K2 model with 256K context, strong Agentic Coding",
"supports_tools": true,
"context_length": 256000,
"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": 256000,
"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": 256000,
"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": 256000,
"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
}
],
"global": [
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Latest flagship with Agent Swarm, multimodal input, and 256K context",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.95,
"output_price": 4.0,
"published_at": "2026-04-21"
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "256K context, 1T params MoE, Agent Swarm",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.6,
"output_price": 3.0
},
{
"id": "kimi-k2-0905-preview",
"name": "Kimi K2 0905",
"description": "K2 model with 256K context, strong Agentic Coding",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.6,
"output_price": 2.4
},
{
"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": 256000,
"input_price": 1.2,
"output_price": 8.0
},
{
"id": "kimi-k2-0711-preview",
"name": "Kimi K2 0711",
"description": "Earlier K2 version with 128K context",
"supports_tools": true,
"context_length": 131072,
"input_price": 0.6,
"output_price": 2.4
},
{
"id": "kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"description": "Deep reasoning model with 256K context",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.6,
"output_price": 2.4
},
{
"id": "kimi-k2-thinking-turbo",
"name": "Kimi K2 Thinking Turbo",
"description": "High-speed deep reasoning with 256K context",
"supports_tools": true,
"context_length": 256000,
"input_price": 1.2,
"output_price": 8.0
},
{
"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": 0.3,
"output_price": 1.5
},
{
"id": "moonshot-v1-8k",
"name": "Moonshot V1 8K",
"description": "Classic v1 model with 8K context",
"supports_tools": true,
"context_length": 8192,
"input_price": 0.3,
"output_price": 1.5
},
{
"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": 0.3,
"output_price": 1.5
},
{
"id": "moonshot-v1-32k",
"name": "Moonshot V1 32K",
"description": "Classic v1 model with 32K context",
"supports_tools": true,
"context_length": 32768,
"input_price": 0.75,
"output_price": 3.0
},
{
"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": 0.75,
"output_price": 3.0
},
{
"id": "moonshot-v1-128k",
"name": "Moonshot V1 128K",
"description": "Classic v1 model with 128K context",
"supports_tools": true,
"context_length": 131072,
"input_price": 1.5,
"output_price": 4.5
},
{
"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": 1.5,
"output_price": 4.5
}
]
},
"models": [
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Latest flagship with Agent Swarm, multimodal input, and 256K context",
"supports_tools": true,
"context_length": 256000,
"input_price": 6.5,
"output_price": 27.0,
"published_at": "2026-04-21"
},
{
"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"
}
},
"endpoint_models": {
"cn": [
{
"id": "MiniMax-M3",
"name": "MiniMax M3",
"description": "Frontier multimodal coding and agentic model with 1M MSA context, native vision, tool use, and long-horizon task execution",
"supports_tools": true,
"context_length": 1000000,
"input_price": 4.2,
"output_price": 16.8,
"published_at": "2026-06-01"
},
{
"id": "MiniMax-M2.7",
"name": "MiniMax M2.7",
"description": "Recursive self-improvement for real-world engineering, office delivery, and rich interaction",
"supports_tools": true,
"context_length": 204800,
"input_price": 2.1,
"output_price": 8.4,
"published_at": "2026-03-18"
},
{
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax M2.7 Highspeed",
"description": "Same M2.7 performance with significantly faster inference",
"supports_tools": true,
"context_length": 204800,
"input_price": 4.2,
"output_price": 16.8,
"published_at": "2026-03-18"
}
],
"global": [
{
"id": "MiniMax-M3",
"name": "MiniMax M3",
"description": "Frontier multimodal coding and agentic model with 1M MSA context, native vision, tool use, and long-horizon task execution",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.6,
"output_price": 2.4,
"published_at": "2026-06-01"
},
{
"id": "MiniMax-M2.7",
"name": "MiniMax M2.7",
"description": "Recursive self-improvement for real-world engineering, office delivery, and rich interaction",
"supports_tools": true,
"context_length": 204800,
"input_price": 0.3,
"output_price": 1.2,
"published_at": "2026-03-18"
},
{
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax M2.7 Highspeed",
"description": "Same M2.7 performance with significantly faster inference",
"supports_tools": true,
"context_length": 204800,
"input_price": 0.6,
"output_price": 2.4,
"published_at": "2026-03-18"
}
]
},
"models": [
{
"id": "MiniMax-M3",
"name": "MiniMax M3",
"description": "Frontier multimodal coding and agentic model with 1M MSA context, native vision, tool use, and long-horizon task execution",
"supports_tools": true,
"context_length": 1000000,
"input_price": 4.2,
"output_price": 16.8,
"published_at": "2026-06-01"
},
{
"id": "MiniMax-M2.7",
"name": "MiniMax M2.7",
"description": "Recursive self-improvement for real-world engineering, office delivery, and rich interaction",
"supports_tools": true,
"context_length": 204800,
"input_price": 2.1,
"output_price": 8.4,
"published_at": "2026-03-18"
},
{
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax M2.7 Highspeed",
"description": "Same M2.7 performance with significantly faster inference",
"supports_tools": true,
"context_length": 204800,
"input_price": 4.2,
"output_price": 16.8,
"published_at": "2026-03-18"
},
{
"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
}
]
},
"xiaomi": {
"label": "Xiaomi MiMo",
"endpoints": {
"cn": {
"label": "Xiaomi MiMo",
"region": "cn",
"base_url": "https://api.xiaomimimo.com/v1",
"price_currency": "CNY",
"docs_url": "https://platform.xiaomimimo.com/docs/en-US/quick-start/model"
},
"global": {
"label": "Xiaomi MiMo",
"region": "global",
"base_url": "https://api.xiaomimimo.com/v1",
"price_currency": "USD",
"docs_url": "https://platform.xiaomimimo.com/docs/en-US/quick-start/model"
}
},
"endpoint_models": {
"cn": [
{
"id": "mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"description": "Pro-series model for complex reasoning and long documents; 1M context, 128K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 1000000,
"input_price": 7.0,
"output_price": 21.0,
"published_at": "2026-04-30"
},
{
"id": "mimo-v2-pro",
"name": "MiMo V2 Pro",
"description": "Legacy Pro model; auto-routes to mimo-v2.5-pro from 2026-06-01 and will be deprecated on 2026-06-30",
"supports_tools": true,
"context_length": 1000000,
"input_price": 7.0,
"output_price": 21.0
},
{
"id": "mimo-v2.5",
"name": "MiMo V2.5",
"description": "Omni-series full-modal model for image, audio, and video understanding; 1M context, 128K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 1000000,
"input_price": 2.8,
"output_price": 14.0,
"published_at": "2026-04-30"
},
{
"id": "mimo-v2-omni",
"name": "MiMo V2 Omni",
"description": "Legacy Omni model with 256K context; auto-routes to mimo-v2.5 from 2026-06-01 and will be deprecated on 2026-06-30",
"supports_tools": true,
"context_length": 256000,
"input_price": 2.8,
"output_price": 14.0
},
{
"id": "mimo-v2-flash",
"name": "MiMo V2 Flash",
"description": "Flash-series low-cost text model; 256K context, 64K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.7,
"output_price": 2.1
},
{
"id": "mimo-v2.5-tts",
"name": "MiMo V2.5 TTS",
"description": "Speech synthesis with standard preset voices; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2.5-tts-voiceclone",
"name": "MiMo V2.5 TTS Voice Clone",
"description": "Speech synthesis with timbre cloning from uploaded audio samples; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2.5-tts-voicedesign",
"name": "MiMo V2.5 TTS Voice Design",
"description": "Speech synthesis with custom voice design; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2-tts",
"name": "MiMo V2 TTS",
"description": "Legacy speech synthesis model; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
}
],
"global": [
{
"id": "mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"description": "Pro-series model for complex reasoning and long documents; 1M context, 128K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 3.0,
"published_at": "2026-04-30"
},
{
"id": "mimo-v2-pro",
"name": "MiMo V2 Pro",
"description": "Legacy Pro model; auto-routes to mimo-v2.5-pro from 2026-06-01 and will be deprecated on 2026-06-30",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 3.0
},
{
"id": "mimo-v2.5",
"name": "MiMo V2.5",
"description": "Omni-series full-modal model for image, audio, and video understanding; 1M context, 128K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.4,
"output_price": 2.0,
"published_at": "2026-04-30"
},
{
"id": "mimo-v2-omni",
"name": "MiMo V2 Omni",
"description": "Legacy Omni model with 256K context; auto-routes to mimo-v2.5 from 2026-06-01 and will be deprecated on 2026-06-30",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.4,
"output_price": 2.0
},
{
"id": "mimo-v2-flash",
"name": "MiMo V2 Flash",
"description": "Flash-series low-cost text model; 256K context, 64K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.1,
"output_price": 0.3
},
{
"id": "mimo-v2.5-tts",
"name": "MiMo V2.5 TTS",
"description": "Speech synthesis with standard preset voices; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2.5-tts-voiceclone",
"name": "MiMo V2.5 TTS Voice Clone",
"description": "Speech synthesis with timbre cloning from uploaded audio samples; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2.5-tts-voicedesign",
"name": "MiMo V2.5 TTS Voice Design",
"description": "Speech synthesis with custom voice design; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2-tts",
"name": "MiMo V2 TTS",
"description": "Legacy speech synthesis model; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
}
]
},
"models": [
{
"id": "mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"description": "Pro-series model for complex reasoning and long documents; 1M context, 128K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 1000000,
"input_price": 7.0,
"output_price": 21.0,
"published_at": "2026-04-30"
},
{
"id": "mimo-v2-pro",
"name": "MiMo V2 Pro",
"description": "Legacy Pro model; auto-routes to mimo-v2.5-pro from 2026-06-01 and will be deprecated on 2026-06-30",
"supports_tools": true,
"context_length": 1000000,
"input_price": 7.0,
"output_price": 21.0
},
{
"id": "mimo-v2.5",
"name": "MiMo V2.5",
"description": "Omni-series full-modal model for image, audio, and video understanding; 1M context, 128K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 1000000,
"input_price": 2.8,
"output_price": 14.0,
"published_at": "2026-04-30"
},
{
"id": "mimo-v2-omni",
"name": "MiMo V2 Omni",
"description": "Legacy Omni model with 256K context; auto-routes to mimo-v2.5 from 2026-06-01 and will be deprecated on 2026-06-30",
"supports_tools": true,
"context_length": 256000,
"input_price": 2.8,
"output_price": 14.0
},
{
"id": "mimo-v2-flash",
"name": "MiMo V2 Flash",
"description": "Flash-series low-cost text model; 256K context, 64K max output; deep thinking, tools, structured output, web search",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.7,
"output_price": 2.1
},
{
"id": "mimo-v2.5-tts",
"name": "MiMo V2.5 TTS",
"description": "Speech synthesis with standard preset voices; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2.5-tts-voiceclone",
"name": "MiMo V2.5 TTS Voice Clone",
"description": "Speech synthesis with timbre cloning from uploaded audio samples; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2.5-tts-voicedesign",
"name": "MiMo V2.5 TTS Voice Design",
"description": "Speech synthesis with custom voice design; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "mimo-v2-tts",
"name": "MiMo V2 TTS",
"description": "Legacy speech synthesis model; 8K context, limited-time free",
"supports_tools": false,
"context_length": 8000,
"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-5.1",
"name": "GLM-5.1",
"description": "Latest flagship with stronger coding and long-horizon autonomous execution",
"supports_tools": true,
"context_length": 200000,
"input_price": 6.0,
"output_price": 24.0,
"published_at": "2026-04-07"
},
{
"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-5-turbo",
"name": "GLM-5-Turbo",
"description": "Agent-optimized turbo variant with stronger long-task execution",
"supports_tools": true,
"context_length": 200000,
"input_price": 4.8,
"output_price": 19.2
},
{
"id": "glm-5v-turbo",
"name": "GLM-5V-Turbo",
"description": "Multimodal coding model with vision and tool use",
"supports_tools": true,
"context_length": 200000,
"input_price": 5.0,
"output_price": 22.0
},
{
"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-5.1",
"name": "GLM-5.1",
"description": "Latest flagship with stronger coding and long-horizon autonomous execution",
"supports_tools": true,
"context_length": 200000,
"input_price": 1.4,
"output_price": 4.4,
"published_at": "2026-04-07"
},
{
"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-5-turbo",
"name": "GLM-5-Turbo",
"description": "Agent-optimized turbo variant with stronger long-task execution",
"supports_tools": true,
"context_length": 200000,
"input_price": 1.2,
"output_price": 4.0
},
{
"id": "glm-5v-turbo",
"name": "GLM-5V-Turbo",
"description": "Multimodal coding model with vision and tool use",
"supports_tools": true,
"context_length": 200000,
"input_price": 1.2,
"output_price": 4.0
},
{
"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-5.1",
"name": "GLM-5.1",
"description": "Latest flagship with stronger coding and long-horizon autonomous execution",
"supports_tools": true,
"context_length": 200000,
"input_price": 6.0,
"output_price": 24.0,
"published_at": "2026-04-07"
},
{
"id": "glm-5-turbo",
"name": "GLM-5-Turbo",
"description": "Agent-optimized turbo variant with stronger long-task execution",
"supports_tools": true,
"context_length": 200000,
"input_price": 4.8,
"output_price": 19.2
},
{
"id": "glm-5v-turbo",
"name": "GLM-5V-Turbo",
"description": "Multimodal coding model with vision and tool use",
"supports_tools": true,
"context_length": 200000,
"input_price": 5.0,
"output_price": 22.0
},
{
"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 TokenHub",
"endpoints": {
"cn": {
"label": "Tencent TokenHub",
"region": "cn",
"base_url": "https://tokenhub.tencentmaas.com/v1",
"price_currency": "CNY",
"docs_url": "https://cloud.tencent.com/document/product/1823/130078"
},
"global": {
"label": "Tencent TokenHub",
"region": "global",
"base_url": "https://tokenhub-intl.tencentmaas.com/v1",
"price_currency": "USD",
"docs_url": "https://cloud.tencent.com/document/product/1823/130078"
}
},
"models": [
{
"id": "hy3-preview",
"name": "Hy3 Preview",
"description": "Latest flagship model with 256K context, supporting fast and slow thinking fusion, optimized for agentic tasks",
"supports_tools": true,
"context_length": 256000,
"input_price": 1.2,
"output_price": 4.0
},
{
"id": "hunyuan-2.0-thinking-20251109",
"name": "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": 192000,
"input_price": 3.975,
"output_price": 15.9
},
{
"id": "hunyuan-2.0-instruct-20251111",
"name": "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": 144000,
"input_price": 3.18,
"output_price": 7.95
},
{
"id": "hunyuan-role-latest",
"name": "Hunyuan Role Latest",
"description": "Role-playing specialized model with significantly improved character consistency and dialogue depth",
"supports_tools": false,
"context_length": 32000,
"input_price": 2.4,
"output_price": 9.6
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "DeepSeek V4 Flash model with 1M context window, supporting deep thinking and structured output",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "DeepSeek V4 Pro model with 1M context window, supporting deep thinking and structured output",
"supports_tools": true,
"context_length": 1000000,
"input_price": 12.0,
"output_price": 24.0
},
{
"id": "deepseek-v3.2",
"name": "DeepSeek V3.2",
"description": "DeepSeek V3.2 model with 128K context, supporting deep thinking and structured output",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.0,
"output_price": 3.0
},
{
"id": "deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"description": "DeepSeek V3.1 Terminus model with 128K context, supporting deep thinking and structured output",
"supports_tools": true,
"context_length": 128000,
"input_price": 4.0,
"output_price": 12.0
},
{
"id": "deepseek-r1-0528",
"name": "DeepSeek R1 0528",
"description": "DeepSeek R1 0528 reasoning model with 128K context, supporting deep thinking and structured output",
"supports_tools": true,
"context_length": 128000,
"input_price": 4.0,
"output_price": 16.0
},
{
"id": "deepseek-v3-0324",
"name": "DeepSeek V3 0324",
"description": "DeepSeek V3 0324 model with 128K context, supporting function calling",
"supports_tools": true,
"context_length": 128000,
"input_price": 2.0,
"output_price": 8.0
},
{
"id": "glm-5.1",
"name": "GLM 5.1",
"description": "GLM 5.1 model with 200K context, supporting deep thinking, structured output and cache",
"supports_tools": true,
"context_length": 200000,
"input_price": 6.0,
"output_price": 24.0
},
{
"id": "glm-5v-turbo",
"name": "GLM 5V Turbo",
"description": "GLM 5V Turbo model with 200K context, supporting deep thinking, structured output and cache",
"supports_tools": true,
"context_length": 200000,
"input_price": 5.0,
"output_price": 22.0
},
{
"id": "glm-5-turbo",
"name": "GLM 5 Turbo",
"description": "GLM 5 Turbo model with 200K context, supporting deep thinking, structured output and cache",
"supports_tools": true,
"context_length": 200000,
"input_price": 5.0,
"output_price": 22.0
},
{
"id": "glm-5",
"name": "GLM 5",
"description": "GLM 5 model with 200K context, supporting deep thinking and cache",
"supports_tools": true,
"context_length": 200000,
"input_price": 4.0,
"output_price": 18.0
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Kimi K2.6 model with 256K context, supporting deep thinking, structured output and cache",
"supports_tools": true,
"context_length": 256000,
"input_price": 6.5,
"output_price": 27.0
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Kimi K2.5 model with 256K context, supporting deep thinking, structured output and cache",
"supports_tools": true,
"context_length": 256000,
"input_price": 4.0,
"output_price": 21.0
},
{
"id": "minimax-m2.7",
"name": "MiniMax M2.7",
"description": "MiniMax M2.7 model with 200K context, supporting deep thinking and cache",
"supports_tools": true,
"context_length": 200000,
"input_price": 2.1,
"output_price": 8.4
},
{
"id": "minimax-m2.5",
"name": "MiniMax M2.5",
"description": "MiniMax M2.5 model with 200K context, supporting deep thinking and cache",
"supports_tools": true,
"context_length": 200000,
"input_price": 2.1,
"output_price": 8.4
}
]
},
"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": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Efficient V4 model with 1M context, hybrid thinking and tool calling",
"supports_tools": true,
"context_length": 1000000,
"input_price": 1.0,
"output_price": 2.0,
"published_at": "2026-04-24"
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Flagship V4 model with 1M context and frontier agentic reasoning",
"supports_tools": true,
"context_length": 1000000,
"input_price": 12.0,
"output_price": 24.0,
"published_at": "2026-04-24"
},
{
"id": "glm-5.1",
"name": "GLM-5.1",
"description": "Zhipu GLM-5.1 with 200K context, deep thinking and prefix completion",
"supports_tools": true,
"context_length": 200000,
"input_price": 6.0,
"output_price": 24.0,
"published_at": "2026-04-07"
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Moonshot K2.6 with 256K context, multimodal input and agentic tool use",
"supports_tools": true,
"context_length": 256000,
"input_price": 6.5,
"output_price": 27.0,
"published_at": "2026-04-21"
},
{
"id": "MiniMax-M2.7",
"name": "MiniMax M2.7",
"description": "MiniMax M2.7 with 200K context, agent harness and tool calling",
"supports_tools": true,
"context_length": 200000,
"input_price": 2.1,
"output_price": 8.4,
"published_at": "2026-03-18"
},
{
"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-2.0-Preview",
"name": "LongCat 2.0 Preview",
"description": "Trillion-parameter MoE flagship with 1M context, agentic tool use, and 128K max output",
"supports_tools": true,
"context_length": 1000000,
"input_price": 0.0,
"output_price": 0.0,
"published_at": "2026-04-24"
},
{
"id": "LongCat-Flash-Omni-2603",
"name": "LongCat Flash Omni 2603",
"description": "Multimodal omni model with vision and audio understanding, max 8K output",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.0,
"output_price": 0.0,
"published_at": "2026-03-01"
},
{
"id": "LongCat-Flash-Chat-2602-Exp",
"name": "LongCat Flash Chat 2602 Exp",
"description": "Experimental chat model with improved general dialogue and instruction following",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.0,
"output_price": 0.0,
"published_at": "2026-02-01"
},
{
"id": "LongCat-Flash-Thinking-2601",
"name": "LongCat Flash Thinking 2601",
"description": "560B MoE reasoning model with agentic tool use, Heavy Thinking mode, and 256K max output",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.0,
"output_price": 0.0,
"published_at": "2026-01-01"
},
{
"id": "LongCat-Flash-Thinking",
"name": "LongCat Flash Thinking",
"description": "560B MoE deep reasoning model with formal and agentic reasoning, 256K max output",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.0,
"output_price": 0.0,
"published_at": "2025-09-22"
},
{
"id": "LongCat-Flash-Chat",
"name": "LongCat Flash Chat",
"description": "High-performance general chat model with 256K max output",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.0,
"output_price": 0.0
},
{
"id": "LongCat-Flash-Lite",
"name": "LongCat Flash Lite",
"description": "Efficient lightweight MoE model with 256K max output",
"supports_tools": true,
"context_length": 256000,
"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": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"description": "Google DeepMind 30.7B dense multimodal instruct model with 256K context, vision input, native function calling, configurable thinking/reasoning, and 140+ languages; Apache 2.0",
"supports_tools": true,
"supports_vision": true,
"supports_reasoning": true,
"context_length": 262144,
"input_price": 0.12,
"output_price": 0.37,
"cache_read_price": 0.1,
"published_at": "2026-04-02"
},
{
"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-5.1",
"name": "Z.ai GLM 5.1",
"description": "Preview Zhipu GLM 5.1 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/developers/models/grok-4"
}
},
"models": [
{
"id": "grok-4.3",
"name": "Grok 4.3",
"description": "xAI flagship with 1M context, vision input, agentic tool calling, structured outputs, and configurable reasoning effort (none/low/medium/high)",
"supports_tools": true,
"supports_vision": true,
"supports_reasoning": true,
"context_length": 1000000,
"input_price": 1.25,
"output_price": 2.5,
"cache_read_price": 0.2,
"published_at": "2026-04-30"
},
{
"id": "grok-4.1-fast-reasoning",
"name": "grok-4.1-fast-reasoning",
"description": "Fast reasoning model (tools, 2M context); retires 2026-05-15 and redirects to grok-4.3",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-4.3"
},
{
"id": "grok-4.1-fast-non-reasoning",
"name": "grok-4.1-fast-non-reasoning",
"description": "Fast non-reasoning model (tools, 2M context); retires 2026-05-15 and redirects to grok-4.3",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-4.3"
},
{
"id": "grok-code-fast-1",
"name": "grok-code-fast-1",
"description": "Fast code model (tools); retires 2026-05-15 and redirects to grok-build-0.1",
"supports_tools": true,
"context_length": 256000,
"input_price": 0.2,
"output_price": 1.5,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-build-0.1"
},
{
"id": "grok-4-fast-reasoning",
"name": "grok-4-fast-reasoning",
"description": "Reasoning model (tools, 2M context); retires 2026-05-15 and redirects to grok-4.3",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-4.3"
},
{
"id": "grok-4-fast-non-reasoning",
"name": "grok-4-fast-non-reasoning",
"description": "Non-reasoning model (tools, 2M context); retires 2026-05-15 and redirects to grok-4.3",
"supports_tools": true,
"context_length": 2000000,
"input_price": 0.2,
"output_price": 0.5,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-4.3"
},
{
"id": "grok-4-0709",
"name": "grok-4-0709",
"description": "Grok 4 0709 (tools); retires 2026-05-15 and redirects to grok-4.3",
"supports_tools": true,
"context_length": 256000,
"input_price": 3.0,
"output_price": 15.0,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-4.3"
},
{
"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); retires 2026-05-15 and redirects to grok-4.3",
"supports_tools": true,
"context_length": 131072,
"input_price": 3.0,
"output_price": 15.0,
"deprecated_at": "2026-05-15",
"replacement_id": "grok-4.3"
},
{
"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
}
]
}
}
}