Skip to content
Menu

Guides

How to check your Codex usage

Checked on 5 November 2026 against the sources below. Updated on 12 November 2026.

Just ran out? What you can do now covers when your window comes back, how to keep working until it does, and how to make the next one last, for Claude Code and Codex.

If Codex has just stopped, type /status in the Codex CLI now. It shows a row for each window, the 5-hour one and the weekly one, with the share left and when it resets, and a credits row if you have credits. That tells you whether you can carry on after the next reset or are waiting for the week to roll over, and whether credits will keep you going in the meantime. The rest of this page is about the other place to look, and how to keep a record over time.

Two places, both OpenAI's. In the Codex CLI, type /status: it shows your context usage and your rate limits, one row per window, with the share left and when it resets. Outside a session, the usage dashboard at chatgpt.com/codex/settings/usage shows your current limits for the account. OpenAI's Codex pricing page puts it this way: "You can find your current limits in the usage dashboard. If you want to see your remaining limits during an active Codex CLI session, you can use /status." Both show where you are now. To see your Codex usage over time, you need something that records it: Codex writes each limits snapshot to its session file on your machine, and OpenReason Intel, a dashboard for Claude Code and Codex usage, reads that file after every turn and keeps the history of your 5-hour and weekly windows, from every machine you use, with the turns that used each one up.

Each option below says what it shows and where that was checked.

Run /status in the Codex CLI

OpenAI's slash command reference describes /status as "Show the chat ID, context usage, and rate limits." What the rate-limit part prints is set in the CLI's source rather than on a page: each window is a row labelled by its length, "5h limit" or "Weekly limit", with a bar, the percentage left and the reset time, and a "Credits" row when the account has them (codex-rs/tui/src/status/rate_limits.rs). A user on OpenAI's forum in July 2026 pasted a real one from a plan with no 5-hour window: a single "Weekly limit: 0% left" line and "Credits: 341".

So on Plus or a Business Standard seat you see two rows, and on Pro you see one, because Pro plans currently have no 5-hour limit. The figures come from OpenAI with each response, so they are current as of your last turn.

/usage is a different command: the reference says it will "Open usage and billing settings, when available with ChatGPT sign-in", which is the dashboard below in a browser.

Open the usage dashboard

The Codex pricing page links the usage dashboard at chatgpt.com/codex/settings/usage and says "You can find your current limits in the usage dashboard", suggesting you check "every week or two to understand your pace and remaining capacity". It is the account-wide view, and the place credits are bought and seen. On a Business or Enterprise workspace, the admin's usage limits and spend controls are set separately and cover "some Codex activity", not all of it.

No OpenAI page read for this guide describes a usage display inside the IDE extension, so this page does not claim one. In the extension, the dashboard is the place to look.

From December 2026 the place to look moves. OpenAI says Plus, Pro and Business plans will share one allowance across ChatGPT and Codex, and "You will be able to see your combined remaining usage and reset times in Settings → Usage" (Understanding ChatGPT and Codex usage limits). On credit-based plans, OpenAI also says "ChatGPT Desktop shows credit usage for individual Work and Codex chats", and members of eligible Enterprise workspaces can open Settings > Usage & billing in ChatGPT Desktop for their monthly Work and Codex allowance and recent credit history (Using Codex with your ChatGPT plan).

Seeing it over time

Neither /status nor the dashboard keeps a history. The raw material for one exists on your machine: Codex records the rate-limit snapshot it receives with each response into the session's log under ~/.codex/sessions, and each snapshot carries each window's used_percent, window_minutes and resets_at (codex-rs/protocol/src/protocol.rs). A script that reads those files can rebuild your windows over time. OpenAI publishes no usage API for this; the endpoint the CLI calls is internal and needs your ChatGPT sign-in.

ccusage, the local tool most often cited for Claude Code, reads Codex too: its guide lists Codex among its sources, reading ~/.codex by default, and ccusage codex daily gives a Codex-only report by day, week, month or session. It reports tokens used and an estimated cost; it does not know your plan's limit, so it shows how much you used rather than how close to the window you were. tokscale, another free local tool, reads the same files and can also show your current Codex windows by asking OpenAI with your ChatGPT sign-in; it shows where you stand now rather than keeping a history.

Session Forensics, a free page from OpenReason, does that rebuilding for you. It reads your ~/.codex/sessions folder in your browser, with no sign-up, and your files are never uploaded. Because Codex records its own meter in those files, the page shows your 5-hour windows over the last seven days with Codex's own figures, lists the times you hit a limit, and names the turns that used each window up. On Codex's free plan there is little to show, because that plan records one 30-day window and no 5-hour window.

If you are on a team

Each seat has its own windows and its own /status. A Business admin sets workspace limits and spend controls but does not get a per-person window view from these pages. Enterprise workspaces with Codex can read usage through the Codex Enterprise Analytics API, using a workspace Admin key with the codex.enterprise.analytics.read permission, according to OpenAI's Using Codex with your ChatGPT plan. For who keeps running out and what Codex credits are costing beside Claude Code's usage credits, see what your team spends and who went past their plan.

See your Codex windows over time in OpenReason Intel

OpenReason's reporter, or-otel, does the reading above for you. One install command registers a Codex hook that runs after each turn, reads the newest limits snapshot from the session file, and sends only those fields: the 5-hour and weekly used percentage and reset times, credits, and the reason when a limit was hit. Every snapshot since the last one sent goes, each with its own time, so a limit hit is dated to the response that crossed it. A seat with no 5-hour window is reported as weekly only. In the dashboard you can see your Codex windows over time, when each filled, and the sessions and turns that were running, beside the same view for Claude Code.

For one person, that adds a record across days and weeks and across every machine you use, the turns running when a window filled with each one's estimated share, your Claude Code windows beside your Codex ones, and a record you can show your lead if your company pays. It does not warn you or stop anything; it is a record you look at. What you can do instead is check /status during long sessions and look afterwards at which turns filled the window. The hook also sends Codex's reply text by default, which your team lead chooses whether to keep; installing with --no-log-prompts stops text leaving your machine. Sign-up takes a Google account or an email address, no card. Run the command from the or-otel quickstart, quit and reopen Codex, send a prompt, and the first snapshot arrives; or-otel uninstall removes it all.

What to do next

  1. Read next

  2. See what used up your limit

    Session Forensics is a free page that reads the Claude Code and Codex session files already on your computer, in your browser. It lists the limits you hit and the turns that used each one up. There is nothing to install and no sign-up, and your files are never uploaded. For Claude Code its 5-hour figure is an estimate, because Claude Code's files do not record the meter.

    Would you rather have your own agent do it? Paste this prompt into Claude Code or Codex.

    Open Session Forensics (opens in a new tab)

  3. Get an email when the limits change

    Get an email when Claude Code or Codex limits change. One email per change, at most one a week, from OpenReason. Unsubscribe from any email in one click.

  4. Track it over time

    Sign up with your Google account, no card, and run one install command. OpenReason Intel then records your Codex 5-hour and weekly windows from every machine you use, with the turns that used each one up, and your Claude Code windows beside them. It is free for one person.

    It shows you what happened; it does not stop a session as you work, and it cannot change your vendor's limits.

    Sign up free with Google

Questions people ask

How do I check my Codex usage?
Type /status in the Codex CLI for your context usage and rate limits, one row per window with the share left and the reset time, or open the usage dashboard at chatgpt.com/codex/settings/usage for the account view. OpenReason Intel keeps the history of both windows, across your machines, if you want to see them over time.
How do Codex's 5-hour and weekly limits work?
On Plus and Business Standard seats there is a 5-hour window and a weekly limit on top; Pro plans currently have no 5-hour limit. OpenAI lifted the 5-hour limit for all paid plans on 12 July 2026 and brought it back for Plus on 25 August. The guide on Codex's limits has OpenAI's wording and the dates.
How do I check how close I am to my Claude Code limit?
The equivalent in Claude Code is /usage, which shows your 5-hour and weekly bars and a breakdown of what used them, with the same bars under Settings > Usage on claude.ai. The guide on checking your Claude Code usage covers it and the status line.

Sources

Every figure on this page was read from these pages on 5 November 2026. Limits and prices change; if a vendor page now says something different, the vendor page is right and this one is out of date.