Requesty

{
  "protocolVersion": "1.0",
  "name": "Requesty",
  "description": "AI gateway and LLM router for 600+ models. Intelligent routing, caching, failover, observability, and enterprise governance through a single OpenAI-compatible API.",
  "version": "1.0.0",
  "documentationUrl": "https://docs.requesty.ai",
  "iconUrl": "https://www.requesty.ai/Requesty_logo.svg",
  "provider": {
    "organization": "Requesty",
    "url": "https://www.requesty.ai"
  },
  "supportedInterfaces": [
    {
      "url": "https://router.requesty.ai/v1",
      "protocolBinding": "HTTP/REST",
      "protocolVersion": "1.0"
    }
  ],
  "capabilities": {
    "streaming": true,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/event-stream"
  ],
  "securitySchemes": {
    "bearer": {
      "type": "http",
      "scheme": "bearer",
      "description": "API key from https://app.requesty.ai"
    }
  },
  "security": [
    {
      "bearer": []
    }
  ],
  "skills": [
    {
      "id": "chat-completions",
      "name": "Chat Completions",
      "description": "POST /v1/chat/completions - Send chat completion requests to 600+ AI models. Supports streaming, function calling, structured outputs, vision, and extended thinking. Docs: https://docs.requesty.ai/api-reference/endpoint/chat-completions-create",
      "tags": [
        "llm",
        "chat",
        "completions",
        "openai-compatible"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/event-stream"
      ]
    },
    {
      "id": "responses-api",
      "name": "Responses API",
      "description": "POST /v1/responses - OpenAI Responses API for multi-turn conversations with built-in tool use, web search, file search, and computer use. Docs: https://docs.requesty.ai/api-reference/endpoint/responses-create",
      "tags": [
        "responses",
        "openai",
        "agents",
        "tool-use"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/event-stream"
      ]
    },
    {
      "id": "messages-api",
      "name": "Messages API",
      "description": "POST /v1/messages - Anthropic Messages API for Claude models with native support for extended thinking, tool use, and vision. Docs: https://docs.requesty.ai/api-reference/endpoint/messages-create",
      "tags": [
        "messages",
        "anthropic",
        "claude"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/event-stream"
      ]
    },
    {
      "id": "model-routing",
      "name": "Intelligent Model Routing",
      "description": "Route requests across 30+ providers by cost, latency, or availability. Weighted load balancing, automatic failover chains, and latency-based routing. Docs: https://docs.requesty.ai/features/fallback-policies",
      "tags": [
        "routing",
        "load-balancing",
        "failover"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "embeddings",
      "name": "Embeddings",
      "description": "POST /v1/embeddings - Generate text embeddings using models from OpenAI, Cohere, Voyage, and more. Docs: https://docs.requesty.ai/api-reference/endpoint/embeddings-create",
      "tags": [
        "embeddings",
        "vectors"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "mcp-gateway",
      "name": "MCP Gateway",
      "description": "Unified gateway connecting AI coding tools (Cursor, Claude Code, VS Code) to any MCP server with auth, analytics, and management. Docs: https://docs.requesty.ai/features/mcp-gateway",
      "tags": [
        "mcp",
        "gateway",
        "tools",
        "cursor",
        "claude-code"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "images",
      "name": "Image Generation and Editing",
      "description": "POST /v1/images/generations and /v1/images/edits - Generate and edit images using DALL-E, Stable Diffusion, and other models. Docs: https://docs.requesty.ai/api-reference/endpoint/images-generations-create",
      "tags": [
        "images",
        "generation",
        "editing",
        "dall-e"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "audio",
      "name": "Audio (TTS and Transcription)",
      "description": "POST /v1/audio/speech for text-to-speech, POST /v1/audio/transcriptions for speech-to-text. Docs: https://docs.requesty.ai/api-reference/endpoint/audio-speech-create",
      "tags": [
        "audio",
        "tts",
        "speech",
        "transcription"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    }
  ]
}