Skip to main content
The runResponses() method provides access to OpenAI’s Responses API, designed for reasoning models like o1 and o3-mini.
The Responses API is OpenAI-specific and uses a different input format than runLocal().

When to Use Responses API

Use runResponses() when working with:
  • Reasoning models (o1, o3-mini, o4-mini) that benefit from the Responses API format
  • Multi-turn conversations where you want to pass output items back as input
  • Structured reasoning where you want to capture reasoning summaries
For standard chat completions, use runLocal() instead.

Basic Usage

Input Format

The Responses API uses different roles than the Chat API:

Streaming

Enable streaming to receive responses in real-time:

Event Types

When streaming, you receive different event types:

Multi-Turn Conversations

Pass previous output items back as input for multi-turn conversations:

Tool Calling

The Responses API supports function calling:

RunResponsesInput

RunResponsesResult

Supported Models

The Responses API works with OpenAI’s reasoning models:
Standard models like gpt-4o can also be used with the Responses API, but runLocal() is recommended for those.