Codex usage limits by plan
| Plan | 5-hour window | Weekly cap | Shared with ChatGPT from December | How to get more |
|---|---|---|---|---|
| Free | Limited Codex usage; OpenAI doesn't publish numbers | Not stated | Not announced | Upgrade your plan. Codex Cloud isn't included with Free |
| Go | Limited Codex usage; OpenAI doesn't publish numbers | Not stated | Not announced | Upgrade your plan. Codex Cloud isn't included with Go |
| Plus | Yes; OpenAI publishes ranges per model | May apply; no number published | Yes | Buy credits without changing plan, upgrade, or wait for the reset |
| Pro | None currently | May apply; no number published | Yes | Buy credits without changing plan, or wait for the reset |
| Business | Yes on Standard seats; OpenAI publishes ranges per model | May apply; no number published | Yes | Buy credits, or wait for the reset |
| Enterprise | With flexible pricing, no fixed rate limits; otherwise the same per-seat limits as Plus | With flexible pricing, none fixed; otherwise as Plus | Not announced | Flexible pricing scales with credits; on token-based billing, ask your workspace admin |
OpenAI publishes ranges, not fixed numbers: its estimates of local messages per five-hour period for Plus and Standard Business are 15-160 with GPT-6.1 Sol, 35-285 with GPT-6.1 Terra, 5-45 with GPT-6 Astra and 350-3,000 with GPT-6 Luna, depending on the task. Local messages and cloud chats share your plan's allowance. Plus and the $20 Business plan include limited GPT-6 Astra usage, with credits for more.
Starting in December, OpenAI says Plus, Pro and Business usage will be shared across ChatGPT and Codex and measured in tokens, and Instant chat won't draw from it. It hasn't announced the change for Free, Go or Enterprise.
When does the Codex usage limit reset?
Codex has two limits that reset separately. The five-hour limit covers usage per five-hour period on Plus and Standard Business (Pro plans currently have none), and a weekly limit may also apply on top of it. OpenAI doesn't publish a fixed reset day or say whether the five-hour window rolls, so go by the reset time it shows you.
To see your reset times, open your Codex usage dashboard, or check the limit notice in Codex. From December, ChatGPT Settings → Usage shows your combined remaining usage and reset times for ChatGPT and Codex. If you can't wait, you may be able to add credits, use an available reset or upgrade.
Hit your limit? Reason keeps going on your other connected accounts or Reason credits.
Keep working when Codex hits its limit
Check your limits and reset times
Run /status in the Codex CLI, or open the usage dashboard in ChatGPT, to see your current limits. /usage shows your account's token usage, and is also where you use a rate-limit reset if you have one.
Choose an OpenAI option
ChatGPT Plus and Pro users can buy more credits without changing plan; Business, Edu and Enterprise plans with flexible pricing can buy workspace credits. Anyone can run extra local chats with an API key, billed at standard API rates.
Save where the task stands
Commit your work in progress on a branch and push it, and note the goal, what is done, what is next and how to check it. Reason can't see your previous agent's conversation, so the branch and your notes carry the task.
Open Reason on the web or the Mac app
Sign in at reasonmachines.com, or download the Reason Mac app for macOS from reasonmachines.com/download and sign in there. Both open the same Sessions.
Give Reason the task in the composer
Tell Reason which repository and branch to work on, or in the Mac app which folder on your computer, then paste your notes. Pick a Claude model or another connected model in the composer, so the task keeps moving while your Codex limit resets.
How Codex limits work
OpenAI publishes estimates of local messages per five-hour period for Plus and Standard Business, which vary widely by model, and says they are not fixed message limits. Local messages and cloud tasks share your plan's allowance, cloud tasks may use more of it, and weekly limits may also apply. Pro plans currently have no five-hour limit. On October 29, 2026, OpenAI doubled the Work and Codex allowance of Pro 100 and Pro 500, canceled a planned Pro 200 reduction, and said Plus usage is unchanged.
OpenAI says that starting in December, Plus, Pro and Business usage will be shared across ChatGPT and Codex and measured in tokens, with combined remaining usage and reset times in Settings → Usage.
Carrying the task on in Reason
Reason starts from your branch and notes, in the web app on the repository you name or in the Mac app in a folder on your computer. Pick a model that isn't on the plan that ran out, such as a Claude model on Reason credits. Note that a GPT model on the same ChatGPT plan shares the limit Codex hit.
Questions
When does Codex usage limit reset?
OpenAI doesn't publish a fixed reset schedule. Plus and Standard Business usage is measured per five-hour period (Pro plans currently have no five-hour limit), and a weekly limit may also apply. Your Codex usage dashboard and the limit notice show your exact reset time; from December, ChatGPT Settings → Usage shows combined ChatGPT and Codex reset times.
What are Codex Plus usage limits?
OpenAI publishes ranges, not a fixed number: an estimated 15-160 local messages per five-hour period with GPT-6.1 Sol, 35-285 with GPT-6.1 Terra, 5-45 with GPT-6 Astra and 350-3,000 with GPT-6 Luna, depending on the task, and weekly limits may also apply. Plus users can buy credits without changing plan, and from December Plus usage is shared across ChatGPT and Codex.
Does every Codex plan have usage limits?
Yes. Every ChatGPT plan with Codex has usage limits that vary by plan; Pro plans currently have no five-hour limit but weekly limits may apply, and Enterprise and Edu plans with flexible pricing have no fixed rate limits because usage is paid for with credits.
What is the weekly usage limit for Codex?
OpenAI doesn't publish a fixed weekly number: it says weekly limits may apply on top of the five-hour window, and how much you get depends on your plan, the model and the task. Settings > Usage or your usage dashboard shows your current limits and reset times.
Why does Codex have a 5 hour usage limit?
OpenAI doesn't say why. Its docs measure Codex allowances per five-hour period, with weekly limits that may also apply, and say how fast you use them depends on the model, context, reasoning, tools and whether a task runs locally or in the cloud; Pro plans currently have no five-hour limit.
How to bypass Codex usage limits?
You can't bypass them, but you can keep working legitimately: upgrade your plan, buy credits on Plus or Pro (or workspace credits on Business, Edu and Enterprise plans with flexible pricing), use a one-time or banked reset if OpenAI gives you one, or run extra local chats with an API key at standard API rates. Hit your limit? Reason keeps going on your other connected accounts or Reason credits.
How do I check my Codex usage?
Open Settings > Usage in ChatGPT or your usage dashboard for your current limits and reset times, or enter /status during an active Codex CLI session.
Does Codex stop in the middle of a task at the limit?
OpenAI says that if you reach your limit during an active turn, the agent can continue working on that turn, subject to fair-use limits. New turns wait for the reset, credits or an API key.
Can I use an API key when Codex hits its limit?
Yes. OpenAI says all users may run extra local chats with an API key, charged at standard API rates. Cloud features are not available with an API key.
Can Reason continue a Codex task?
Yes, if you hand it the state: commit and push the work in progress, then tell Reason the branch and what's next in the web or Mac app.