Codex eating your quota? A 1M-token context setting is killing your cache
altryne · x · 2026-09-27
The author traced sudden Codex quota drain to an old experimental setting: a 1M-token context window, which destroys OpenAI's cache and rips through limits. After removing it and moving sub-agents to a cheaper model, usage went back to normal. Lesson: check your codex.toml for leftover experimental settings.
Related event: Codex users warned: 1M context setting destroys cache and burns quota(3 posts)→
More from coding & agent
- dhh: programmers who can beat a pair of collaborating frontier models round to zero — suchenzang · 2026-09-27
- Claude subscribers can claim $100–$250 in free Claude Code cloud session credits until Oct 7 — Expert_Annual_19 · 2026-09-27
- Agent fixed what its reviewer flagged—then the next review passed the new bug it created — Fit-Ant2238 · 2026-09-27
- Meta Muse hits 3.4M downloads; an indie dev is building the on-device, privacy-first alternative — jonathancheckwise · 2026-09-27
- Qiaomu Home open-sourced: a calm AI-enabled start page plugin for Obsidian — vista8 · 2026-09-27
- The best post on evals: a demo doesn't prove your AI agent is reliable in production — alex_verem · 2026-09-27