Codex users blast OpenAI over opaque usage resets: 'tell us the limit and refill rate'
StewartalsopIII · x · 2026-09-21
Developer @buildwithrajath called out OpenAI's Codex usage reset system: users hit limits mid-task, babysit a countdown-style usage meter, kill unfinished agents early, avoid expensive prompts, and guess when their quota returns.
The ask is simple: a clear usage bucket per plan, predictable replenishment throughout the day, and optional purchased compute added to the meter — no surprise resets or usage anxiety. The post is resonating as a broader complaint about billing transparency in subscription AI coding tools.
Related event: Pro Users Swarm With Complaints Over Codex and Astra Usage Limits(14 posts)→
More from coding & agent
- Using a third-party inference provider with your coding harness hands it shell access to your machine — TheZachMueller · 2026-11-11
- Splash One: flight combat sandbox built with Opus 5.5 in PlayCanvas — willeastcott · 2026-11-11
- Next.js 16.5 delivers 3.3x faster builds for a leading AI lab — cramforce · 2026-11-11
- Plurai launches free agent simulation testing inside Claude Code and Cursor — PrajwalTomar_ · 2026-11-11
- PlayCanvas engine repo hits 10,000th issue/PR — and it's a Claude-authored merge — willeastcott · 2026-11-11
- AI-built game nerfed 40% after Claude playtest bot beat it in 6 minutes — builderjaydub · 2026-11-11