Codex
Seeing "Selected model is at capacity" in Codex? Day 11 makes it rarer and retries for you
Tibo's Day 11 ship: more compute and fixes so the "Selected model is at capacity" block shows up less, and when it still does, the task should continue on its own instead of staying stuck.
What changed
On Day 11 of the 28-day ship-or-reset series, Codex product lead Tibo (@thsottiaux) said OpenAI landed changes plus more compute that should sharply cut how often Codex and ChatGPT Work show "Selected model is at capacity. Please try a different model." When that message still appears, the run should eventually continue by itself instead of blocking forever.
Who is affected
Anyone who has lost mid-task progress to the capacity error in Codex or ChatGPT Work, especially during peak hours.
What to do now
- Keep using your usual model; you do not need a new setting for this change.
- If the capacity message still appears, wait briefly for the automatic continue before switching models.
- If it still sticks, report it to Tibo on X or use Codex feedback so the team can investigate.
What is not confirmed
No OpenAI help article or changelog entry names the exact services, regions, or models covered. How often the error still occurs, and how long "eventually continue" takes, are not quantified here.
Sources
Get updates like this every morning
- ② Card on Stripe
- ③ 7 days free
Then $2/month · cancel anytime in one click