upgrade to websocket mode over response api?

Resolved 💬 4 comments Opened Feb 25, 2026 by GeLi2001 Closed Feb 25, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor) responded on this thread — see the highlighted reply below.

What variant of Codex are you using?

cli & app

What feature would you like to see?

just curious about timeline of supporting websocket mode

Additional information

_No response_

View original on GitHub ↗

4 Comments

etraut-openai contributor · 6 months ago

This feature is already in place. What question do you have about it?

GeLi2001 · 6 months ago

my bad didn't notice. Any datapoints on how fast it is now compared to pre-websocket latency? also wonder if there's a way to generally see these updates somewhere

etraut-openai contributor · 6 months ago

Improvements vary significantly across models, network speeds, etc. The effect is most pronounced for very fast models like our "spark" model.

You can check out our changelogs here.

GeLi2001 · 6 months ago

got it thank you!