gpt.buzz
Sign in

news

Speeding up agentic workflows with WebSockets in the Responses API

April 22, 2026

OpenAI’s Codex agent loop now uses WebSockets and connection-scoped caching in the Responses API to cut API overhead and improve model latency. The change matters because agentic workflows often make many back-and-forth calls, so reducing per-call overhead can noticeably speed up interactive coding and tool-using agents.

A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.

Source: openai.com

← All news