--- title: WebSocket support for OpenAI Responses API live on AI... description: Vercel's AI Gateway now supports WebSocket mode for the OpenAI Responses API, enabling persistent connections that avoid re-sending full context on each turn.... canonical: https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: WebSocket support for OpenAI Responses API live on AI Gateway | daily.dev og:description: Vercel's AI Gateway now supports WebSocket mode for the OpenAI Responses API, enabling persistent connections that avoid re-sending full context on each turn.... og:url: https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0 og:image: https://api.daily.dev/og/posts/On3VOMHH0.png og:image:alt: WebSocket support for OpenAI Responses API live on AI Gateway og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # WebSocket support for OpenAI Responses API live on AI Gateway **[Vercel](https://daily.dev/sources/vercel)** · 1 min read · 3 upvotes · 0 comments ## Summary Vercel's AI Gateway now supports WebSocket mode for the OpenAI Responses API, enabling persistent connections that avoid re-sending full context on each turn. Developers can continue multi-turn conversations by passing only new input plus a `previous_response_id`. OpenAI reports up to ~40% faster end-to-end execution for agentic workflows with 20+ tool calls. The feature is compatible with `store=false` and Zero Data Retention, and follows OpenAI's WebSocket mode specification. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I use WebSocket mode with the OpenAI Responses API through Vercel AI Gateway? Connect to wss://ai-gateway.vercel.sh/v1/responses with your AI Gateway API key as a bearer token, then send response.create frames over the persistent connection. For follow-up turns, send only new input plus the previous_response_id from the prior response.completed event instead of resending full context. The mode supports store=false and Zero Data Retention, following OpenAI's WebSocket mode specification. _Developers building multi-turn agent workflows can track API changes like this one on daily.dev._ ### What performance benefit does WebSocket mode offer over HTTP for the OpenAI Responses API? OpenAI reports up to approximately 40% faster end-to-end execution when using WebSockets instead of repeated HTTP requests for agentic rollouts involving 20 or more tool calls. The gain comes from keeping a persistent connection open and continuing turns with previous_response_id rather than re-sending full context on every request. _Anyone optimizing latency in tool-heavy AI agents can follow updates like this on daily.dev._ ## Similar posts on daily.dev - [OpenAI Introduces Websocket-Based Execution Mode to Reduce Latency in Agentic Workflows](https://daily.dev/posts/openai-introduces-websocket-based-execution-mode-to-reduce-latency-in-agentic-workflows-dp5874ff1) · InfoQ · 1 upvotes · 0 comments - [Stateful Continuation for AI Agents: Why Transport Layers Now Matter](https://daily.dev/posts/stateful-continuation-for-ai-agents-why-transport-layers-now-matter-uxcjv9tl6) · InfoQ · 0 upvotes · 0 comments - [AI Gateway now supports streaming transcription](https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl) · Vercel · 0 upvotes · 0 comments --- Tags: [#openai](https://daily.dev/tags/openai), [#vercel](https://daily.dev/tags/vercel), [#websocket](https://daily.dev/tags/websocket), [#ai-gateway](https://daily.dev/tags/ai-gateway) [View this post on daily.dev](https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"WebSocket support for OpenAI Responses API live on AI Gateway","url":"https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0"},"datePublished":"2026-07-27T18:03:19.826Z","dateModified":"2026-09-13T19:29:25.219Z","description":"Vercel's AI Gateway now supports WebSocket mode for the OpenAI Responses API, enabling persistent connections that avoid re-sending full context on each turn....","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7c43bce2eea5aa94ad08eeab41d40c83?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7c43bce2eea5aa94ad08eeab41d40c83?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Vercel","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Vercel","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/04cca7235cf84db092f24b7ba427b3e1","url":"https://daily.dev/sources/vercel"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"openai,vercel,websocket,ai-gateway","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Vercel","item":"https://daily.dev/sources/vercel"},{"@type":"ListItem","position":3,"name":"WebSocket support for OpenAI Responses API live on AI Gateway"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/websocket-support-for-openai-responses-api-live-on-ai-gateway-on3vomhh0#faq","mainEntity":[{"@type":"Question","name":"How do I use WebSocket mode with the OpenAI Responses API through Vercel AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Connect to wss://ai-gateway.vercel.sh/v1/responses with your AI Gateway API key as a bearer token, then send response.create frames over the persistent connection. For follow-up turns, send only new input plus the previous_response_id from the prior response.completed event instead of resending full context. The mode supports store=false and Zero Data Retention, following OpenAI's WebSocket mode specification. Developers building multi-turn agent workflows can track API changes like this one on daily.dev."}},{"@type":"Question","name":"What performance benefit does WebSocket mode offer over HTTP for the OpenAI Responses API?","acceptedAnswer":{"@type":"Answer","text":"OpenAI reports up to approximately 40% faster end-to-end execution when using WebSockets instead of repeated HTTP requests for agentic rollouts involving 20 or more tool calls. The gain comes from keeping a persistent connection open and continuing turns with previous_response_id rather than re-sending full context on every request. Anyone optimizing latency in tool-heavy AI agents can follow updates like this on daily.dev."}}]} ```