# WebSocket support for OpenAI Responses API live on AI Gateway

By Steven Van · 2026-07-27

OpenAI says the change cuts end-to-end latency by up to 40% in agentic loops with 20 or more tool calls.

[Vercel](<https://creatorstoolbox.com/tools/vercel>)'s AI Gateway now supports WebSocket mode for the OpenAI Responses API, so a connection can stay open across turns instead of opening a new HTTP request for each one. Each turn sends only the new input plus a previous\_response\_id, rather than re-sending the full conversation context. OpenAI reports up to **~40% faster** end-to-end execution over WebSockets for agentic rollouts with 20 or more tool calls.

The [Responses route](<https://vercel.com/docs/ai-gateway/sdks-and-apis/responses/websockets>) opens at GET /v1/responses and accepts response.create frames over the persistent connection. It is compatible with store=false and Zero Data Retention, and follows OpenAI's WebSocket mode specification.

[![](<https://vercel.com/api/docs-og?title=Responses%20API%20over%20WebSocket&format=docs&sig=e6713a5c59c65a06a0ee5607032ab1236d7eceee1ff89541efdeb7c2d1ad8270&category=Build%20AI%20apps&subcategory=AI%20Gateway&subcategory2=SDKs%20%26%20APIs>)](<https://vercel.com/docs/ai-gateway/sdks-and-apis/responses/websockets>)

![Vercel](<https://www.google.com/s2/favicons?domain=vercel.com&sz=128>)

Vercel

The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.

[View Vercel →](<https://creatorstoolbox.com/tools/vercel>)

Sources

[Original source](<https://vercel.com/docs/ai-gateway/sdks-and-apis/responses/websockets>)

[Read WebSocket support for OpenAI Responses API live on AI Gateway on Creators Toolbox](<https://creatorstoolbox.com/blog/vercel-websocket-support-for-openai-responses-api-live-on-ai-gateway>)

---
Canonical source: https://creatorstoolbox.com/blog/vercel-websocket-support-for-openai-responses-api-live-on-ai-gateway