RAP Sheet home
Install the bug reporting skill
Its theme's rank, 14 days: 4 on the Codex sheet
9 people reported

All time, since Oct 13.

Model at capacity errors

“I am experiencing persistent and intermittent Codex capacity errors on my ChatGPT Plus account, even though my usage limits are far from exhausted.”

Is this your bug? What gets counted gets fixed. Pile on.

Paste this into your agent. It files your report, with your error and version.

I hit this bug: rapsheet.dev/sheets/codex/issues/24075/file
Follow it to file my report. Show me the text before you send.

No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends

Growing. 1 report in the last 7 days and none the week before, down from 5 a week at the late-October peak.

Codex returns "Selected model is at capacity" despite remaining usage quota. Errors appear in new and existing sessions, even for minimal prompts, across multiple models, and switching models or retrying does not reliably help.

Is this your bug?

File my report
Where
Codex CLI and desktop
Error text
Selected model is at capacity. Please try a different model.
Versions
0.147.0 to 26.1016.62342
Platforms
macOS, Windows
How bad
Stops work: a core feature can't be used. Some reports say it blocks them completely.

Part of: Model at capacity errors24 bugs

  1. Model at capacity errors127 people
  2. Model at capacity error34 people
  3. Model at capacity errors40 people
  4. Model at capacity errors31 people
  5. Model at capacity error14 people
  6. Model at capacity errors15 people
  7. Model at capacity error10 people
  8. Tasks interrupted by repeated "Selected model is at capacity" errors and reconnects6 people
  9. Existing long conversations fail with model-at-capacity error4 people
  10. Model at capacity interruptions7 people
Show all 23Show only the largest 10
  1. Model at capacity error5 people
  2. Model at capacity errors3 people
  3. No retry on capacity error2 people
  4. Selected model at capacity4 people
  5. At-capacity and stream disconnects3 people
  6. Model at capacity error3 people
  7. Model at capacity errors4 people
  8. Model at capacity errors2 people
  9. Sol model at capacity2 people
  10. Model at capacity error3 people
  11. Model at capacity error2 people
  12. Spurious model capacity error7 people
  13. Model at capacity errors7 people

Original reports9, newest first

  1. Codex returns "Selected model is at capacity" across models despite sufficient Plus allowanceOn GitHub#58858
  2. Persistent "Selected model is at capacity" and server_overloaded errors across multiple PCs despite 94%/98% remaining quotaOn GitHub#56347
  3. [macOS][Codex Desktop][Plus] All models return "Selected model is at capacity" (server_overloaded) at 2-4% usage; /feedback upload also fails with Sentry 429On GitHub#56135
  4. Subject: Urgent Escalation — Persistent Codex "Selected Model Is at Capacity" Errors | 69 Confirmed Server Overload FailuresOn GitHub#56105
  5. All Codex projects report model capacity despite remaining Plus quota (GPT-6 Astra also fails)On GitHub#56039
  6. [Critical Bug] All Codex Models Repeatedly Fail with Capacity Errors Despite 50%+ Remaining Plus QuotaOn GitHub#55851
  7. Codex still returns "Selected model is at capacity" (server_overloaded) after 7h41m — public Codex incident is resolved, my usage is 27%On GitHub#53952
  8. [Windows] Codex Desktop: repeated "Selected model is at capacity" (server_is_overloaded, NO_MORE_RETRY) with weekly usage at 1% - 171 failed turns over 3 daysOn GitHub#53594
  9. [Windows 10 19045] GPT-6.1 Sol: persistent "at capacity" / HTTP 503 with 94% quota remaining (Oct 12-13), corroborating #52812 / #53407On GitHub#53559

Do you work on Codex?

Claim its RAP Sheet to see what your users report and answer them in one place.

Claim a tool