Responses API
OpenAI's current API for generating model output, which takes input items and returns a list of output items with usage.
In more detail
It replaced the Assistants API, which was sunset on 2026-08-26, and is recommended over Chat Completions for new work. It can keep conversation state on the server when asked, and adds built-in tools such as file search.
Related terms
- Chat Completions API — OpenAI's older, widely copied API that takes a list of role-tagged messages and returns choices, each with a message and a finish reason.
- Messages API — Anthropic's main API for Claude: you send a model name, an optional system prompt and a list of messages, and get back content blocks, a stop reason and usage.
- Assistants API — A retired OpenAI API for stateful assistants with threads and runs, sunset on 2026-08-26 in favour of the Responses API.
Taught in
- The Request And The Response — AI Engineering: LLM Apps, RAG & Agents
- Streaming Responses — AI Engineering: LLM Apps, RAG & Agents
- Function Calling — AI Engineering: LLM Apps, RAG & Agents