codexPOST
OpenAI eases Codex "model at capacity" errors with more compute
OpenAI added compute and shipped changes to Codex that cut how often the "selected model is at capacity" error appears, and long tasks can now resume on their own.
Kai
@hqmankArchived 14 days agoOriginally posted 2026.10.16
Kai @hqmankOriginally posted 2026.10.16
OpenAI is finally tackling that annoying "Selected model is at capacity" error in Codex. They've added more compute and shipped a series of changes to significantly cut how often it shows up. And when it does happen, Codex should eventually continue on its own instead of getting stuck. That matters most for long-running tasks you don't want to babysit.
This post quotes another post: x.com/thsottiaux/status/2110750421367287996
x.com/hqmank/status/2110930696747225555Archived 2026.10.17 10:19