How to Check Your Codex Usage on ChatGPT (Plus and Pro)
TL;DR: ChatGPT’s Codex has its own usage analytics page at https://chatgpt.com/codex/cloud/settings/analytics, separate from the main ChatGPT settings. You need to be logged into your ChatGPT account first. The page splits your Codex usage into three meters: a 5-hour rolling limit, a weekly limit, and pay-as-you-go credits. Here is an example screenshot:
Where EXACTLY Do I Find My Codex Usage on ChatGPT?
You have to be logged into your ChatGPT account first. Then paste this URL into your browser:
https://chatgpt.com/codex/cloud/settings/analytics
Two things worth knowing before you go looking for it:
- This page does not live under the main ChatGPT Settings menu. It lives under the Codex side of ChatGPT, which is a separate area of the product.
- The fastest way to land here when you are locked out is to click the red “Usage limit reached” pill in the Codex header. ChatGPT routes you straight to the analytics page.
What Are the Three Meters?
Three independent budgets are tracked on this page:
5-hour usage limit. This is the one most people hit first. Rolling window. Local Codex messages and cloud tasks both draw from it. The page shows the reset timing for your current window.
Weekly usage limit. Separate cap on top of the 5-hour. You can hit your 5-hour wall and still have 80%+ of your weekly intact, which is exactly what my screenshot shows.
Credits. Top-up that kicks in after you hit included Codex usage limits. OpenAI is moving Codex credit pricing to token-based rates, but some plans may still show the previous message-based rate card until their account is migrated. Plus and Pro users can buy them and the balance feeds back into the same Codex pool.
The card right on the analytics page reads: “Codex usage draws from your shared agentic usage limit.” That means Codex, ChatGPT for Excel, and other agentic features all draw from the same bucket. Heavy Codex use eats into whatever else agentic ships on your plan.
How Many Codex Messages Does ChatGPT Plus Actually Give Me?
Per OpenAI’s official Codex pricing page, on the $20/month Plus tier, here is what you get per 5-hour window:
| Model | Local messages per 5-hour window |
|---|---|
| GPT-5.5 | 15 to 80 |
| GPT-5.4 | 20 to 100 |
| GPT-5.4-mini | 60 to 350 |
| GPT-5.3-Codex | 30 to 150 |
The range is wide because consumption varies by message size. A 50-line diff review costs more than a one-sentence question. Long prompts, attached files, and large code reviews burn faster than chat-style turns.
Is Upgrading to Pro Worth It?
For Plus users hitting the wall regularly, here is the math, again from OpenAI’s pricing page:
| Tier | Price | GPT-5.5 local messages per 5 hours |
|---|---|---|
| Plus | $20/mo | 15 to 80 |
| Pro 5x | $100/mo | 80 to 400 |
| Pro 20x | $200/mo | 300 to 1,600 |
OpenAI is also running two temporary promos through May 31, 2026. The $100 Pro tier is doubled, so it currently runs at roughly 10x the Plus quota instead of 5x. The $200 Pro tier is temporarily honored at 25x Plus on the 5-hour Codex limits instead of the standard 20x.
If you blow through Plus more than once a week, Pro 5x is the obvious step. If you hit the wall once a month and can wait 5 hours, stay on Plus and treat the lockouts as forced breaks.
If you also pay for Claude, the limit systems are not identical. Claude tracks a 5 hour session window and a weekly window too, but the math behaves differently and Anthropic recently tightened peak hour caps by design. I broke that down in what Claude’s usage limits actually look like and how to make them last. May be worth a read if you split work across both or want to compare.
What Do I Do When I Hit 0% on my 5 hour block?
Three options when the 5-hour allotment is used:
- ⏰ Wait it out. The 5-hour window rolls forward whether you are paying attention or not. For occasional Codex users this is fine.
- 💰 Buy credits. Pay-as-you-go top-up at token-based rates. Useful for “I just need to finish this one task” moments.
- 💰💰 Upgrade to Pro. 5x quota for $100/mo
If you are locked out and the task can wait, option one is the cheapest. Maybe just take a nice break and have a phone alarm for your reset time, come back when the meter ticks over.
The End
I hope this helps! I try to keep this info updated but OpenAI frequently changes things, so if something looks amiss just let me know. Also, if you have questions, tips or tricks to share, feel free to comment. Thanks for visiting! 👍👍