WebSocket support for OpenAI Responses API live on AI Gateway
Cloudflare AI Gateway adds WebSocket support for the OpenAI Responses API, enabling persistent connections and stateful turns via previous_response_id with up to 40% faster execution for agentic workloads.
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 , instead of re-sending the full context over a fresh HTTP request every turn.AI Gatewayprevious_response_id up to ~40% faster end-to-end execution on WebSockets for agentic rollouts with 20 or more tool calls.OpenAI reports The Responses route opens at and accepts raw frames over a persistent WebSocket connection.
The mode is compatible with and , and follows OpenAI's specification upstream.GET /v1/responsesresponse.createstore=falseZero Data RetentionWebSocket mode See the for setup and the full route list.AI Gateway documentation Read more Route Responses API traffic over WebSocket