X Feed Intel beta

individual tinkerer enterprises
Weekly Prep Posts Topics History
789 relevant 273 topics 2290 posts $1.633 cost fetched 02-23T23:00
789
Relevant
273
Topics
2290
Total Posts
$1.633
Cost This Week
$1.633
Total Cost
2026-02-23T23:00
Last Fetch
← Back to Topics
Inference Stack

WebSocket optimization for agentic tool-calling latency reduction

Responses API WebSocket implementation achieving 30-40% latency improvements in agent tool-calling workflows, representing inference stack optimization for agentic workloads.

8 posts · First seen 2026-02-23 · Last activity 2026-02-23
TimeAuthorPost
2026-02-23T22:20 @OpenAIDevs Teams are using WebSockets in the Responses API to speed up agentic workflows https://t.co/CNKDniYfe1
2026-02-23T21:23 @migtissera RT @OpenAIDevs: Introducing WebSockets in the Responses API. Built for low-latency, long-running agents with heavy tool calls. https://t.…
2026-02-23T21:21 @martin_casado RT @leerob: All OpenAI models in Cursor are now up to 30% faster! We've upgraded all users to WebSockets with their Responses API.
2026-02-23T21:14 @romainhuet We built WebSockets support to keep up with the speed of GPT-5.3-Codex-Spark! ✨ Excited to make this available to everyone building on the platform. https://t.co/QtixmgnVQY
2026-02-23T20:16 @stevenheidel WebSockets are the reason we were able to speed up Codex recently - across all models https://t.co/BzC6uVBz3u ↩ reply parent
2026-02-23T20:10 @stevenheidel the Responses API now supports WebSockets! this can make your agents run 30-40% faster, especially when they make a lot of tool calls https://t.co/sBgoat2gsX https://t.co/pTPaqlKPvl
2026-02-23T20:04 @OpenAIDevs WebSockets keep a persistent connection to the Responses API, allowing you to send only new inputs instead of round-tripping the entire context on every turn. By maintaining in-memory state across interactions, it avoids repeated work and speeds up agentic runs with 20+ tool calls by 20%-40%. ↩ reply parent
2026-02-23T20:04 @OpenAIDevs Introducing WebSockets in the Responses API. Built for low-latency, long-running agents with heavy tool calls. https://t.co/qmOAhidk7o https://t.co/feiGpewQaE
@OpenAIDevs 2026-02-23T22:20
Teams are using WebSockets in the Responses API to speed up agentic workflows https://t.co/CNKDniYfe1
@migtissera 2026-02-23T21:23
RT @OpenAIDevs: Introducing WebSockets in the Responses API. Built for low-latency, long-running agents with heavy tool calls. https://t.…
@martin_casado 2026-02-23T21:21
RT @leerob: All OpenAI models in Cursor are now up to 30% faster! We've upgraded all users to WebSockets with their Responses API.
@romainhuet 2026-02-23T21:14
We built WebSockets support to keep up with the speed of GPT-5.3-Codex-Spark! ✨ Excited to make this available to everyone building on the platform. https://t.co/QtixmgnVQY
@stevenheidel 2026-02-23T20:16
WebSockets are the reason we were able to speed up Codex recently - across all models https://t.co/BzC6uVBz3u
↩ reply parent
@stevenheidel 2026-02-23T20:10
the Responses API now supports WebSockets! this can make your agents run 30-40% faster, especially when they make a lot of tool calls https://t.co/sBgoat2gsX https://t.co/pTPaqlKPvl
@OpenAIDevs 2026-02-23T20:04
WebSockets keep a persistent connection to the Responses API, allowing you to send only new inputs instead of round-tripping the entire context on every turn. By maintaining in-memory state across interactions, it avoids repeated work and speeds up agentic runs with 20+ tool calls by 20%-40%.
↩ reply parent
@OpenAIDevs 2026-02-23T20:04
Introducing WebSockets in the Responses API. Built for low-latency, long-running agents with heavy tool calls. https://t.co/qmOAhidk7o https://t.co/feiGpewQaE

Markdown Export

Loading...