Codex how to see usage: dashboard, /status and /usage

To see your Codex usage, open the usage dashboard at chatgpt.com/codex/settings/usage, or type /status inside a Codex CLI session. OpenAI's Codex pricing page names both. This guide covers the CLI, the app and the web, and how limits are counted on each plan, as read in the docs on November 5, 2026.

See your Codex usage on the web

Open chatgpt.com/codex/settings/usage while signed in to ChatGPT, in any browser. The pricing page says "you can find your current limits in the usage dashboard", and the dashboard also shows reset times. The docs suggest checking it every week or two.

The pricing page gives no separate steps for the web and the app, so this is the one place the docs send everyone.

See your Codex usage in the CLI

Two slash commands matter. Type either one inside a running session. Per the developer commands reference:

1. /status displays session configuration and token usage. OpenAI says to use it to confirm the active model, approval policy, writable roots and remaining context capacity. The pricing page adds that it shows your remaining limits during an active session.
2. /usage lets you view account token usage or use a rate-limit reset. OpenAI says to use it to inspect daily, weekly or cumulative ChatGPT token activity from inside the terminal interface.

If you have not installed the CLI yet, start with the Codex install guide.

See your Codex usage in the app

The docs do not describe a usage screen in the Codex app. What they do say is that /status is among the commands available from the app composer, the box where you type a prompt. The developer commands page lists it without a description, so what it shows there is not documented. For a figure you can rely on, use the web dashboard above.

How Codex limits are counted per plan

Everything here is from the pricing page, as of November 5, 2026.

Local messages and cloud chats draw on the same allowance, and cloud tasks may use more of it than local messages. What a message costs depends on the model, the size of the task, the context, reasoning, tool use and caching, so the estimates are ranges.

For Plus and Standard Business, OpenAI estimates these local messages per five-hour period:

Fast and Ultrafast modes burn allowance faster than Standard. Included usage is multiplied by 2.5 for Fast, and by 8 for GPT-6 Astra Ultrafast and GPT-6.1 Sol Ultrafast. Image generation counts toward the same limits.

What happens when you hit the limit

Credits pay for eligible usage once your included limits run out. Plus and Pro users can buy extra credits without upgrading, and Business, Edu and Enterprise plans with flexible pricing can buy workspace credits. If you hit the limit in the middle of a turn, the agent can finish that turn, within fair use limits.

To decide between the plans, see ChatGPT Plus vs Pro for Codex after the $500 Pro tier. Prices and limits change, so check the pricing page before you rely on a number.

Check the dashboard before a long task, since it is the only place the docs say shows reset times. Check /status mid-session when you want to know how much context is left in the current chat.