WebSocket support for OpenAI Responses API live on AI Gateway

Vercel's AI Gateway now supports WebSocket mode for the OpenAI Responses API, enabling persistent connections that send only new input items plus previous_response_id per turn instead of full context over fresh HTTP requests. OpenAI reports up to ~40% faster end-to-end execution on WebSockets for agentic rollouts with 20 or more tool calls.

AI Gateway https://vercel.com/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 https://developers.openai.com/api/docs/guides/websocket-mode up to ~40% faster end-to-end execution on WebSockets for agentic rollouts with 20 or more tool calls. The Responses route opens at GET /v1/responses and accepts raw response.create frames over a persistent WebSocket connection. The mode is compatible with store=false and Zero Data Retention https://vercel.com/docs/ai-gateway/security-and-compliance/zdr , and follows OpenAI's WebSocket mode https://developers.openai.com/api/docs/guides/websocket-mode specification upstream. See the AI Gateway documentation https://vercel.com/docs/ai-gateway/sdks-and-apis/responses/websockets for setup and the full route list.