Your Codex usage dashboard is at chatgpt.com/codex/settings/usage: your current limits and when they reset, also shown by /status in the CLI. It covers your own account; Zest shows each engineer's Codex sessions, models and tokens next to their other agents and merged pull requests.
Free for 3 seats · No credit card · One command signs in every agent on your machine
Sample data
Stack in the Zest app: how well your setup is wired, and what raises the score
USED BY ENGINEERING TEAMS AT
How to check your Codex usage
Two commands in the Codex CLI answer it for your own account. To keep your limits in view, add them to the footer with /statusline.
Outside the CLI, OpenAI's Codex usage dashboard in ChatGPT, at chatgpt.com/codex/settings/usage, shows your current limits and when they reset. Once you reach them, available credits let you keep working. How big each plan's limits are and what resets them is on Codex usage limits, and what each plan costs on Codex pricing.
/status: the session's model, approval policy, token usage and context left, plus your remaining usage limits.
/usage: your ChatGPT token activity, or a rate-limit reset if you have one to use. /usage daily, /usage weekly and /usage cumulative open the activity view directly. Since Codex CLI 0.156.0 it also has an analytics dashboard of account usage, token totals, and plugin and skill activity.
Every place to see Codex usage
Each view answers a different question, so start with whose usage you need: yours, one machine's or the whole team's.
OpenAI's Codex docs read November 8, 2026; the desktop app and API key rows read November 10, 2026; ccusage from its README, read October 5, 2026.
Where
What it shows
Who it covers
chatgpt.com/codex/settings/usage
Current limits and reset times
Your account
Usage & billing in the ChatGPT desktop app
Credits over 7 or 30 days and your top consuming chats
Your account
platform.openai.com/usage
API usage from sessions signed in with an API key
An API organization
/status in the CLI
Session tokens, context left, remaining limits
Your account
/usage in the CLI
Daily, weekly or cumulative token activity
Your account
codex exec --json
Input, cached, output and reasoning tokens per turn
One scripted run
ccusage
Token usage stats by day, week, month and session
One laptop
OpenTelemetry export
API requests, prompts and tool events, in your own dashboards
Whoever turns it on
Admin Console
Usage, Insights and Code review
A workspace
Daily Usage Analytics API
Daily ChatGPT, Codex and Work usage
An Enterprise workspace
Zest
Sessions, models, tokens and skills, next to merged pull requests
Each engineer, across agents
Codex analytics in ChatGPT, the desktop app and the API
ChatGPT labels the usage page Codex Analytics. Its Usage tab also has a Personal usage chart you can set to 7 days, a month or a custom range, though some accounts have reported it empty with usage on record.
In the ChatGPT desktop app, open Settings and then Usage & billing (Usage on eligible Enterprise accounts). It shows your Work and Codex credits over 7 or 30 days, grouped by surface, model, reasoning or speed, and ranks your top consuming chats. OpenAI calls the per-chat totals estimates, because subagent work, image generation and some background activity may be left out.
Sign in to Codex with an API key and OpenAI bills that usage through your OpenAI Platform account at API rates, so it shows on the OpenAI usage dashboard at platform.openai.com/usage and not against your plan. If the Codex dashboard you're after is the one where cloud tasks run, that's Codex in ChatGPT on the web or in the desktop app, and the usage page is in its settings.
Codex usage from scripts, logs and OpenTelemetry
codex exec --json prints one JSON event per line, and each turn ends with a turn.completed event whose usage holds input, cached input, output and reasoning tokens. For past sessions on one laptop, ccusage reads Codex's local logs into daily, weekly, monthly and session reports; for the same on Claude, see Claude usage tracker.
For your own dashboards, Codex exports OpenTelemetry log events: each API request, prompt, tool decision and tool result, with token counts on each completed response. It's off by default. Turn it on with an [otel] table in ~/.codex/config.toml; Codex ignores otel in a project's .codex/config.toml.
That table can send Codex metrics too. With the OTel metrics pipeline on, Codex emits counters and duration histograms for API, stream and tool activity, and codex.turn.token_usage by token type, each tagged with the model. Grafana's dashboard library has a ready token usage dashboard for Codex (ID 25338) with sessions, turns, tokens and tool calls, and it expects the data in Application Insights.
If you want a Codex usage tracker instead of commands, two community projects do that for one person. CodexBar is a menu bar app for macOS 14 or later, with a Linux version, that shows each limit and when it resets. tokscale reads Codex's files under ~/.codex/sessions/ and reports token use across coding agents from your terminal; its submit command publishes your numbers to a public leaderboard, so leave that out if they're private. Neither comes from OpenAI.
codex exec --json "summarize the repo structure" | jq 'select(.type == "turn.completed") | .usage'
bunx ccusage codex daily # this machine's Codex tokens by day
Workspace admins get two views, and which parts they see depends on role and plan. Workspace analytics (chatgpt.com/admin/usage) covers adoption across ChatGPT. The Admin Console (admin.openai.com) has Codex analytics: Usage for activity and consumption, Insights for what the work was, as use cases and tasks with their messages, credits and active users, and Code review for Codex's reviews.
For automated reports, Enterprise workspaces use the Daily Usage Analytics API, which returns daily ChatGPT, Codex and Work usage for a workspace Admin key scoped to enterprise.analytics.usage.read. Its routes and fields are in OpenAI's Admin API reference.
Eligible Enterprise and Edu workspaces can also turn on Personal Analytics, a plugin for the ChatGPT desktop app that answers plain-language questions about your own Work and Codex activity. An admin has to enable it first, and it never shows another person's individual activity.
How Zest tracks Codex usage across a team
OpenAI's views stop at Codex: they don't show the Claude Code or Cursor sessions the same engineer runs, or which sessions ended in a merged pull request. Each engineer installs the Zest plugin for Codex from its marketplace (setup; how plugins work is on Codex plugins). It reads an allowlisted set of session files from ~/.codex, the folder the Codex CLI, IDE extension and ChatGPT desktop app all write to, filters them for privacy on the engineer's machine, and syncs them on demand, or in the background once enabled.
Per engineer: Codex sessions, the model behind each one, and its input, cached and output tokens.
The Codex skills and MCP tools each session used, listed per engineer next to their Claude Code skills.
Next to Claude Code, Cursor, GitHub Copilot Chat, Grok Build and Hermes on the same dashboard, so Claude Code vs Codex or Codex vs GitHub Copilot is measured on your own team's work.
No code diffs are uploaded.
Stack in the Zest app: how well your setup is wired, and what raises the scoreSample data
What Codex usage looks like on our own team
Of the 2,620 pull requests merged in our two repos from July 5 to October 3, 2026, 133 (5%) came from Codex, from 4 engineers. In the 30 days to October 3 the Codex share rose to 9.9%.
866 pull requests merged in our two repos from August 12 to October 4, 2026 carry a session-analytics block, written by the agent that opened them. Codex wrote 31 of them, all in September, which fits the rise above, with a median 576 lines changed against Claude Code's 691.
Counting every agent rather than Codex alone: of the 2,620 pull requests merged in our two repos from July 5 to October 3, 2026, 95% carry an AI agent's signature and about 90% carry Claude Code's. How much code is written by AI explains why counting lines, commits or survey answers gives a different share.
From Codex sessions to merged pull requests
With the Zest GitHub App connected, each engineer's Codex sessions sit next to the pull requests they merged, with their PR throughput: merged pull requests per week, averaged over four weeks.
Team in the Zest app: your teams, who's on them and the agent work they ranSample data
TRY IT ON YOUR TEAM
See what your team ships with AI.
Starter is free (3 seats, no credit card). Pro is $49 a month with 5 seats and Max is $149 a month with 10 seats — priced per workspace, not per engineer, with extra seats at $19 a month. See pricing
Run /status in the Codex CLI, or open the usage dashboard at chatgpt.com/codex/settings/usage for your limits and reset times. Once you reach them, available credits let you keep working.
How do I see Codex usage across my team?+
Each engineer installs the Zest plugin for Codex and an admin connects your GitHub org. Zest then shows each engineer's Codex sessions, with models and tokens, next to the pull requests they opened and merged and the rest of your team's AI tools.
Does Codex have an analytics API?+
Yes. Enterprise workspaces pull daily ChatGPT, Codex and Work usage from the Daily Usage Analytics API with an Admin key scoped to enterprise.analytics.usage.read, and the Admin Console shows Codex analytics interactively.
Can I get Codex token usage from the command line?+
Yes. codex exec --json ends each turn with a turn.completed event whose usage field holds input, cached input, output and reasoning tokens.
Which analytics tools work with Codex?+
OpenAI's usage dashboard and the desktop app's Usage & billing cover your own account, and the Admin Console covers a workspace, with the Daily Usage Analytics API on Enterprise. OpenTelemetry export feeds your own dashboards, and ccusage reads one laptop. Zest's Codex plugin shows each engineer's Codex sessions next to their Claude Code and Cursor sessions and the pull requests they merged.