Codex tracks usage against two windows at once — a 5-hour window and a weekly window — plus, on some plans, a monthly or credit-based limit. Whichever one you're closest to exhausting is the one that stops you. A reset clears or credits one of these windows; it doesn't change how the windows themselves work.
Codex tracks a 5-hour window and a separate weekly window at the same time (and, on some plans, a monthly or credit-based limit) — whichever one you're closest to exhausting is the one that stops you. The CLI's own /status command reports each window as NN% left (resets <time>); that per-window reset time, shown by the parser below, is the extent of what this site can point to about window timing — check yours rather than assuming a shared schedule.
Exact quota numbers (how much you get, per plan) aren't stated on this site — check chatgpt.com/codex/settings/usage for your own account's numbers, since they vary by plan and can change.
A regular reset clears usage on one or more of these windows immediately, per the announcement's own wording. A banked reset is described as loaded or credited instead, rather than applied on the spot — see /banked-reset/ for the exact wording of each one recorded and what is (and isn't) known about what happens after.
/status outputRun /status in the Codex CLI, then paste the whole output below. Everything happens in your browser — nothing is sent anywhere.
| Window | Left | Resets | In (your local time) |
|---|
No recognizable usage-limit rows found in that output — check you pasted the whole block, including the labels on the left.
Sponsored · synced from howtok.net
NovaAPI is a global AI token relay platform offering unified access to OpenAI, Claude, Gemini, and leading Chinese LLMs through low-latency, always-on routing. Pricing is fully transparent, with API calls discounted up to 15% off list rates, and referring a friend earns ongoing rewards.
A full-modality AI API supply layer aggregating 500+ models — Sora 2, Veo 3.1, Kling 3.0, Seedream 5.0, GPT-5, Claude, and more. Supports prepaid top-ups, dedicated enterprise channels, and revenue-share partnerships, serving relay platforms, AI app developers, and teams building for global markets.
An AI video API supply layer connecting to Seedance, HappyHorse, and other video-generation models. Supports prepaid top-ups, distribution codes, white-label API access, and revenue-share partnerships — built for relay platforms, video tool builders, and content teams.
These are sponsored links, synced from howtok.net's pinned relay-station listings — third-party API resellers, not official OpenAI access. CodexReset has no affiliation with them; use your own judgment.
They're two separate windows tracked at once: a shorter 5-hour window and a longer weekly window. Whichever one you're closer to exhausting is the one that determines when you can use Codex again. Exact quota numbers vary by plan — check https://chatgpt.com/codex/settings/usage for your own account's numbers, this site doesn't state them.
Not a fixed clock time shared by everyone, as far as this site has found published — the CLI's /status command reports each window's own reset time as "NN% left (resets <time>)"; paste it into the parser above, or check your usage page, for your own account's numbers.
Run /status in the Codex CLI and paste the output into the parser above, or visit https://chatgpt.com/codex/settings/usage directly.