AI & RoboticsMore in AI & Robotics→
OpenAI Says Persistent WebSocket Sessions Cut Agent Loop Latency by Roughly 40%
Key Takeaways
- OpenAI says agent loops using the Responses API became roughly 40% faster end to end.
- The company says inference speed gains made API overhead a much larger bottleneck.
- Persistent WebSocket sessions let OpenAI keep state and caching attached to a connection.
DE
DT Editorial Team··via openai.com