Responses API Beta

OpenRouter’s Responses API Beta provides OpenAI-compatible access to multiple AI models through a unified interface, designed to be a drop-in replacement for OpenAI’s Responses API. This stateless API offers enhanced capabilities including reasoning, tool calling, and web search integration, with each request being independent and no server-side state persisted.

Base URL

https://openrouter.ai/api/v1/responses

Authentication

All requests require authentication using your OpenRouter API key:

1
const response = await fetch('https://openrouter.ai/api/v1/responses', {
2
  method: 'POST',
3
  headers: {
4
    'Authorization': 'Bearer YOUR_OPENROUTER_API_KEY',
5
    'Content-Type': 'application/json',
6
  },
7
  body: JSON.stringify({
8
    model: 'openai/o4-mini',
9
    input: 'Hello, world!',
10
  }),
11
});

Core Features

Basic Usage

Learn the fundamentals of making requests with simple text input and handling responses.

Reasoning

Access advanced reasoning capabilities with configurable effort levels and encrypted reasoning chains.

Tool Calling

Integrate function calling with support for parallel execution and complex tool interactions.

Web Search

Enable web search capabilities with real-time information retrieval and citation annotations.

Error Handling

The API returns structured error responses:

1
{
2
  "error": {
3
    "code": "invalid_prompt",
4
    "message": "Missing required parameter: 'model'."
5
  },
6
  "metadata": null
7
}

For comprehensive error handling guidance, see Error Handling.

Rate Limits

Standard OpenRouter rate limits apply. See API Limits for details.