WebSocket support for OpenAI Responses API live on AI Gateway
- Source
- vercel.com
- Author
- Kevin Dawkins
- Date

Context
Vercel's AI Gateway supports a persistent WebSocket connection for OpenAI's Responses API. Instead of opening a fresh HTTP request and resending the full every turn, an application keeps one connection open and continues by sending only new input plus the previous response's identifier. The release says OpenAI reports faster end-to-end execution for runs with 20 or more tool calls.
That pattern matters for agents that repeatedly request a tool, receive its result and continue, because each step is another turn. The speedup is OpenAI's report for tool-heavy runs, not a general guarantee for every application.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
“AI Gateway now supports WebSocket mode for the OpenAI Responses API.”
“You can keep a persistent connection open and continue each turn by sending only new input items plus previous_response_id , instead of re-sending the full context over a fresh HTTP request every turn.”
“OpenAI reports up to ~40% faster end-to-end execution on WebSockets for agentic rollouts with 20 or more tool calls.”
Checking sign-in…
Loading comments…






