What Is the Conversations API?

The Conversations API is OpenAI's dedicated endpoint for managing persistent, server-side conversation state. It replaces the manual pattern of tracking message arrays client-side or using the legacy Assistants API Threads.

Why It Exists

With Chat Completions, developers had to store and re-send the entire message history on every request - leading to token waste, context truncation bugs, and complex client-side state management. The Conversations API eliminates this by letting OpenAI manage the conversation server-side.

Relationship to the Responses API

The Conversations API works hand-in-hand with the Responses API. When you set store: true and use previous_response_id in a Responses API call, you are implicitly creating a Conversation. The Conversations API gives you explicit CRUD control over these stored conversations - list, retrieve, and delete them programmatically.

API Usage Patterns

import OpenAI from "openai";
const openai = new OpenAI();

// Start a new conversation via the Responses API
const r1 = await openai.responses.create({
  model: "o3-mini",
  store: true,
  input: "I need help planning a product launch."
});

// Continue the conversation - server remembers context
const r2 = await openai.responses.create({
  model: "o3-mini",
  store: true,
  previous_response_id: r1.id,
  input: "What marketing channels should I prioritize?"
});

// List all stored conversations
const conversations = await openai.responses.list();

// Delete a conversation when no longer needed
await openai.responses.del(r1.id);

Key Benefits

• Zero client-side state: No message arrays, no truncation logic, no local databases.
• Automatic prompt caching: Stored conversations get automatic prefix caching for up to 90% input token savings.
• Seamless migration: Replaces Assistants API Threads - use Conversations API + Responses API instead.
• Full audit trail: Every response is stored with metadata for compliance and debugging.