Per the official pricing docs, Codex limits are not a fixed message count: they depend on the model, the size and complexity of your tasks, and whether you work locally or in the cloud. A five-hour period is documented for Plus and Standard Business (the docs say Pro currently has no five-hour limit), weekly limits “may also apply”, and once you reach your included limits, credits can let you keep working. A reset refreshes these allowances; it doesn't change how the windows themselves work. OpenAI’s Help Center, Using Codex with your ChatGPT plan, says OpenAI Support does not reset usage limits. This site states no quota numbers — they change, so the official pricing page is the place to read them. Checked against official sources on Oct 13, 2026.
The pricing docs describe a five-hour period for Plus and Standard Business and say weekly limits may also apply, with no weekly figure published for any plan; local messages and cloud chats share your plan's usage allowance. The pricing docs and Help Center article checked here do not say whether the five-hour window is rolling or fixed, when exactly it starts, or what day or time a weekly window resets — they point to the usage dashboard and any reset time shown there. The open-source CLI also has a “Monthly limit” row label in its /status card; that is a string in source code, and none of the pages checked here says which plans have such a limit.
The CLI's /status output shows each limit as NN% left (resets HH:MM) (the layout comes from the CLI's own test snapshots; see how to check Codex usage for the sources and where they contradict each other). The parser below reads that line, and it 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.
In OpenAI’s Help Center wording, an automatic or global reset is applied directly to eligible usage limits and does not create a saved reset (delivery can lag the announcement by hours), while a banked reset is saved to your account and must be applied by you. Using a full banked reset refreshes your 5-hour and weekly windows and changes your weekly reset date. A third kind, a paid instant reset, can be bought by eligible Plus and Pro plans. See /banked-reset/ and how to reset a usage limit for each one with sources.
| Plan | What the pricing docs say about Codex |
|---|---|
| Free and Go | The Help Center says Codex is included across ChatGPT plans, including Free and Go, with usage limits that vary by plan; Codex cloud is not included with Free or Go. The pricing cards for those plans mention only the desktop app, “subject to rollout”. |
| Plus | Codex on the web, in the CLI, in the IDE extension and on iOS. |
| Pro | Pro plans currently have no five-hour limit; no weekly figure is published. Differences between Pro tiers are covered in OpenAI’s Help Center article About ChatGPT Pro tiers. |
| Business, Edu, Enterprise | Listed. Enterprise and Edu plans with flexible pricing have no fixed rate limits and usage scales with credits; without flexible pricing they have the same per-seat limits as Plus for most features. |
One discrepancy is left: the open-source README names only Plus, Pro, Business, Edu and Enterprise, and the CLI’s limit-reached message for Free/Go tells users to upgrade to Plus to continue using Codex (a string in error.rs, not documentation). The Help Center article and the docs index agree on Free and Go being included, so the README looks like the older of the statements. Plan terms: pricing page and the Help Center article above. Checked against official sources on Oct 13, 2026.
Per OpenAI’s Help Center article Using Credits for Flexible Usage in ChatGPT (Personal plans), credits let you continue using eligible features after reaching your plan’s included limits. Your plan’s included usage is used first; after you hit plan limits, usage draws from your credit balance. Credits are a pay-as-you-go add-on, and nothing about your plan changes.
OpenAI offers Codex credits to verified university students in the United States and Canada. Eligibility is subject to successful verification, with a limit of one credit offer per student; the credits are ChatGPT credits that extend Codex usage beyond the limits included in your plan, they expire 12 months after the grant date, and the balance can be viewed on the usage page. The offer’s amount and full terms are in Codex credits for Students – Terms of Service. Checked against official sources on Oct 13, 2026.
The Codex weekly limit is the longer of the two windows, and its reset time is whatever your own /status line shows for it (NN% left (resets HH:MM)), not a clock time shared by every account; the Help Center also says to check Settings or your usage dashboard for any reset time shown. A search for the codex weekly limit reset, or for codex reset weekly limit, covers three different questions: when the window refreshes on its own (read your own line with the parser below); whether you can reset it early yourself, with a saved banked reset or, on an eligible Plus or Pro plan, a paid instant reset (both in how to reset a usage limit); and whether OpenAI has announced an automatic or global reset that applies to it directly (the home page shows the latest one recorded, /history/ lists them all, and each announcement's own wording says what it covers).
Whether you searched codex limit reset, codex limits reset, codex reset limit or codex usage resets, the answer has the same two halves:
/status.Your own OpenAI Codex usage limits are shown on your usage page at chatgpt.com/codex/settings/usage and by /status in the CLI. If you searched chatgpt codex limits, those are the two places that can see your account; this site can't, and it states no quota numbers because they vary by plan and can change.
/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.
Checked against official sources on Oct 13, 2026. This site is not affiliated with OpenAI; where a statement below comes from a user report or a string in the open-source CLI rather than documentation, it says so.
Sponsored · synced from howtok.net
NovaAPI describes itself as a global AI token relay platform offering unified access to OpenAI, Claude, Gemini, and Chinese LLMs through low-latency, always-on routing. It advertises transparent pricing with API calls discounted up to 15% off list rates, plus a referral program with ongoing rewards.
CodeKey describes itself as an AI API relay for developers, individuals, and teams, with access to Claude, GPT, DeepSeek, GLM, Kimi, Grok, and Gemini. It provides an English-language site, accepts WeChat Pay, Alipay, and USDT, and states that ¥1 paid gives $1 in platform credit. The operator also states that ordinary invoices are available from ¥200 without a fee and that refunds are available at any time without a fee.
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.
Per the pricing docs, a five-hour period is documented for Plus and Standard Business (Pro currently has no five-hour limit), and weekly limits may also apply; local messages and cloud chats share your plan's usage allowance. OpenAI's Help Center says to open Settings or your usage dashboard to check which allowance is exhausted, your credit balance and any reset time shown. Quota numbers change, so this site states none: see https://learn.chatgpt.com/docs/pricing and your own usage dashboard at https://chatgpt.com/codex/settings/usage.
There is no single clock time shared by everyone: each window shows its own reset time. The Help Center says to open Settings or your usage dashboard and look for any reset time shown, and in an active CLI session to enter /status, which reports each window as "NN% left (resets HH:MM)"; paste it into the parser above.
Open Settings or your usage dashboard (https://chatgpt.com/codex/settings/usage), or enter /status in an active Codex CLI session and paste the output into the parser above. /usage-check/ lists every place the official sources point to and where they contradict each other.
OpenAI describes three kinds. A banked reset is saved to your account and you apply it from settings → usage; a paid instant reset can be bought by eligible Plus and Pro plans in ChatGPT Desktop; an automatic or global reset is applied directly by OpenAI with nothing for you to do, and this site tracks those. OpenAI Support does not reset usage limits. Otherwise you can add credits, upgrade, or wait for the displayed reset time. See /how-to-reset-usage-limit/ for each one with sources.
Yes. OpenAI's Help Center says Codex is included across ChatGPT plans, including Free and Go, with usage limits that vary by plan; Codex cloud is not included with Free or Go. The Plus plan lists Codex on the web, in the CLI, in the IDE extension and on iOS (https://learn.chatgpt.com/docs/pricing). One discrepancy worth knowing: the open-source README names only Plus, Pro, Business, Edu and Enterprise, so treat the Help Center and the docs as the more current statements.
No fixed message count. The docs say the number of messages depends on the model, the size and complexity of your tasks, and local versus cloud use. A five-hour period is documented for Plus, weekly limits may also apply, and cloud tasks may use more of the allowance than local messages. The Help Center says to check the pricing page for current limits, rates and credit options, and that eligible Plus and Pro users can buy credits without changing plans. This site states no numbers because they change; OpenAI Support does not reset usage limits.
The pricing docs say Pro plans currently have no five-hour limit and publish no weekly figure for any plan. Differences between Pro tiers have their own Help Center article, About ChatGPT Pro tiers (https://help.openai.com/en/articles/9793128-about-chatgpt-pro-tiers), which this site has not summarized; read it there. Eligible Plus and Pro users can buy credits without changing plans, and Plus and Pro plans can buy an instant reset (see /how-to-reset-usage-limit/).
Searches like "when does codex tokens reset" and "how often does codex tokens reset" are asking about timing, and no single clock time is published. Each window reports its own reset in the CLI's /status line, "NN% left (resets <time>)"; paste it into the parser above. OpenAI describes automatic or global resets as occasional, one-time events rather than a schedule: the home page shows the typical gap between recorded ones (from whenreset.app) and /history/ lists every one. This site states no token counts for any plan.
That depends on the announcement. Per the Help Center, using a full banked reset refreshes both the 5-hour and weekly windows, while an automatic or global reset applies directly to the limits its announcement covers; delivery can lag the post by hours (each /history/ row shows Announced and Delivered times when known). This site doesn't infer which window an announcement covers; open the linked post for that.
Different things. Resetting the CLI's own local configuration (its settings on your machine) has nothing to do with your usage limit — clearing local config doesn't refresh or extend a usage window, and nothing in the official config documentation links the config file to usage limits (see /config-toml/ for a sourced map of the file, and /usage-check/ for where limits are shown). Usage limits are tracked by OpenAI server-side and shown via /status or your usage page, independent of any local settings.