Codex reset notices, history, and probability
Check Codex reset forecasts, official updates, and recent reset history in one place.
Current status
Tibo (@thsottiaux)
Replying to
@udiWertheimer
ok tibo you guys didn’t ship anything interesting this week you owe us a banked reset sorry i don’t make the rules
Tibo's reply
OK fine. But it’s also still coming in Tuesday
Reset history
The timing of regular resets may vary by user.
Past random reset times are grouped by hour on desktop and by two-hour blocks on mobile.
Reset records: n=…
Past intervals between consecutive random resets are grouped by elapsed time. Each interval runs from one random reset to the next.
Codex Reset Observatory is an unofficial site that organizes public information about Codex usage-limit resets. It summarizes the current situation using confirmed global resets and account-specific reset grants, official notices from OpenAI and people involved in development, and OpenAI Status.
The 24-hour and 48-hour reset likelihoods are statistical reference values calculated from past random reset intervals and current observed signals. They are not official probabilities from OpenAI. Confirmed cases are listed in the reset history, while the FAQ explains how the forecast is calculated and how the site's terms are used.
Codex is an essential agentic coding companion, but hitting weekly allowance limits or rate caps halts productive development. This observatory aggregates confirmed global reset events, official notices, and incident-driven compensation resets (wabi-resets) in real time to help developers plan ahead and prevent costly downtime.
The 24-hour and 48-hour reset likelihoods combine an empirical baseline derived from historical event cadence with real-time indicators: OpenAI Status incidents, developer teaser posts (evaluating hinted time windows and confidence levels), and community signals. These statistical reference values serve as practical guidance for pacing tasks or deciding when to redeem a Banked Reset.
Key points regarding Codex and ChatGPT Work usage limit resets.
It is a statistical reference forecast indicating the likelihood of an upcoming reset. An empirical baseline derived from historical cadence is dynamically calibrated using official notices, OpenAI Status incident logs, and community signals. It is not an official probability from OpenAI.
Regular resets follow scheduled periodic refreshes. Special or compensation resets (often called wabi-resets or celebration resets) are unscheduled events executed by OpenAI following service outages, capacity issues, or milestone events.
Yes. On eligible plans, Codex and ChatGPT Work share the same agentic usage and credits pool. A reset affecting that shared pool restores limits for both Codex and ChatGPT Work, though applicability may vary depending on plan specifics.
Teaser posts are analyzed separately from official notices. When terms like tomorrow, tonight, weekdays, or specific hours are resolved, the forecast weighs the hinted window overlap and hint strength against the 24h and 48h windows. Unresolvable hints decay gradually over time.
A Banked Reset allows you to manually refresh your usage limits on demand. It is best used strategically: when reset likelihood is low and immediate progress is essential, use your Banked Reset; when likelihood is high or an official notice is imminent, consider waiting for a potential global reset.