Codex Capacity Improvements and Auto-Resume
Thu, Oct 15, 2026 · logged Oct 15
OpenAI deployed more compute and updates to significantly reduce 'Selected model is at capacity' errors in Codex, allowing requests to continue automatically instead of blocking.
Tibo’s 28-day Codex challenge · Day 11 →WHO IT'S FOR
Codex users
WHEN
Thu, Oct 15, 2026, 11:11 AM
We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive "Selected model is at capacity. Please try a different model". When it does happen, it should also eventually just continue by itself and not just block on it.
Original source · x.comGo to the original ↗