/v1/responses endpoint is an advanced OpenAI-compatible API format designed for conversational state management and built-in server-side tools. It eliminates the need to manage and resend large message histories on every turn and supports server-executed tools like web search and code execution.
Quickstart
- Python
- Node.js
- cURL
Stateful Multi-turn Conversations
The Responses API allows stateful multi-turn conversations usingprevious_response_id. You only need to pass the ID of the previous response — Routeway server-side reconstructs the conversation context.
Multi-turn Code Example
Built-in Server Tools
Unlike custom tool calling where your application code must execute the function locally, Responses API includes built-in server-side tools that execute automatically during inference.Request Parameters
Supported Models
To check which models support the Responses API, verify that"/v1/responses" is listed in the model’s endpoints array on the Models page or via GET /v1/models.