OpenAI Codex temporarily lifts its 5-hour limit
majidmanzarpour · x · 2026-07-20
The post asks how OpenAI is able to temporarily remove the 5-hour limit for Codex and keep resetting usage throughout the week, speculating that the extra capacity must be coming from somewhere and wondering whether training work was paused to support the rollout.
The quoted OpenAI reply says the higher limit was only temporary, and that users should expect the old limit to return at some point.
Related event: OpenAI Frequently Resets Limits, Upping Codex Daily Cap to 10 Million(4 posts)→
More from Models
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27