Codex users hit persistent "model at capacity" errors despite ample quota
charleswang916 · ghdev · 2026-10-13
A ChatGPT Pro ($200) subscriber filed an issue on openai/codex reporting frequent "Selected model is at capacity" errors since October 9, 2026.
- Affects Codex Desktop, Web, and CLI intermittently
- The account still had substantial remaining quota, ruling out usage limits
- Switching models, changing reasoning effort, or starting fresh conversations didn't help
- The user argues requests should proceed when quota is sufficient
Low engagement so far, but if widespread it points to capacity strain under heavy Pro-tier load.
More from Models
- ChatGPT web can actually listen to audio, but the same model can't via API or Codex — Possible_Statement84 · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23
- TLA+ expert corrects Grok: TLC only exhausts finite state spaces, not all behaviors — tianyin_xu · 2026-10-23
- Open LLM cost calculator shows Arabic tokenization and 6x price gaps across models — Moham-saed · 2026-10-23
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23