Open chatgpt.com/codex/settings/usage for your Codex limits and reset times, or run /status in the Codex CLI; /usage shows your token activity. For a team, Zest shows each engineer's Codex sessions, models and tokens next to the pull requests they merged.
Claude CodeFable 5.1 (max) (with fallback)70.4 · Coding Agent Index
CodexGPT-6 Astra (max)67.0 · Coding Agent Index
Muse CodeMuse Spark 1.3 (xhigh)64.2 · Coding Agent Index
Grok BuildGrok 4.5 (high)64.1 · Coding Agent Index
Kimi Code CLIKimi K362.6 · Coding Agent Index
OpencodeGemini 3.8 Flash (high)61.2 · Coding Agent Index
Cursor CLIComposer 2.5 Fast38.3 · Coding Agent Index
Demo setups use current model families. The pairings above are the combinations benchmarked by Artificial Analysis; rankings measure performance, not popularity.
Illustrative daily trends · Other totals: last 30 days. Build Hours: this week, model-estimated activity including overlap; not engineer hours.
↓ Scroll to explore
USED BY ENGINEERING TEAMS AT
How to check Codex usage
Codex usage is shown to each person, against their own limits. A team-wide, per-engineer view comes from workspace analytics, and the deepest one only on Enterprise:
The Codex usage dashboard (chatgpt.com/codex/settings/usage) shows your current usage limits and when they reset; Codex pricing lists what each plan allows.
In the Codex CLI, /status shows your remaining limits, and /usage daily, weekly or cumulative shows your token activity.
ChatGPT Business workspace analytics report messages, credits and active users.
On Enterprise, admins get a Codex analytics dashboard and an Analytics API.
How Zest tracks Codex usage across a team
Each engineer installs the Zest plugin for Codex from its marketplace (how it is built is on Codex plugins). It reads an allowlisted set of session files from ~/.codex, filters them for privacy on the engineer's machine, and syncs them on demand, or in the background once enabled, with the models and token counts of each session.
Per engineer: Codex sessions, the model behind each one, and its input and output tokens.
The Codex skills each session invoked with $skill-name or read from a SKILL.md, listed per engineer in the AI Stack view.
Next to Claude Code, Cursor, GitHub Copilot Chat, Grok Build and Hermes, on the same dashboard, so Claude Code vs Codex is measured on your own team's work.
No code diffs are uploaded.
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.
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.
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.
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, on ChatGPT Enterprise: OpenAI documents a Codex analytics dashboard and an Analytics API for Enterprise admins. Business workspaces get workspace analytics of messages, credits and active users.
Winding / Teams
