Stateful Context & Tool Search

Persistent Conversations

Unlike Chat Completions where you manually manage message history, the Responses API can persist conversations server-side.

// First message
const r1 = await openai.responses.create({
  model: "gpt-5.4",
  store: true,
  input: "My name is Alex and I'm building a SaaS app."
});

// Follow-up — references the previous response
const r2 = await openai.responses.create({
  model: "gpt-5.4",
  store: true,
  previous_response_id: r1.id,
  input: "What tech stack would you recommend for my project?"
});

Tool Search

When you have dozens of function tools or MCP servers, loading all their schemas into context wastes tokens. Tool Search defers tool loading until the model needs them.

const response = await openai.responses.create({
  model: "gpt-5.4",
  tools: [
    { type: "function", name: "get_weather", ... },
    { type: "function", name: "book_flight", ... },
    // ... 50 more functions
  ],
  tool_search: true, // Only inject relevant tools
  input: "What's the weather in London?"
});