Last verified

What is Codex in ChatGPT?

Codex

Codex is the software-development half of ChatGPT — a separate experience alongside Chat and Work, dedicated to writing and debugging code, running tests and commands, reviewing changes and working with repositories. It lives in the ChatGPT desktop app and is not selectable on web or mobile. Its history is kept separate from your ChatGPT chat history, and its usage is metered in credits rather than messages.

What it is
Coding agent code, tests, repos, terminals
Where
Desktop app macOS and Windows
On web / mobile
No remote access from mobile only
History
Separate not in ChatGPT chat history
Metering
Credits shared pool with Work
Extra usage
Purchasable credits beyond plan limits
Our coverage
Full section /agents/codex/
Verified
2026-08-21 OpenAI help centre
§ 01 / SOURCE

Where this answer comes from.

Methodology →
PER VENDOR DOCS · AUG 21, 2026

It is a different product sharing a login with the one you know.

OpenAI's current documentation puts Codex alongside Chat and Work as one of three experiences, and describes its job precisely: "Write or debug code, run tests and commands, review changes, or work with a repository." Unlike the other two, it is a separate view in the ChatGPT desktop app, reached from the top-left menu, and its workflows and history stay separate from ChatGPT's.

The platform constraint is the thing most people discover the hard way: Codex is not selectable on web or mobile. You can reach supported desktop Codex chats from the Remote tab in the ChatGPT mobile app — approving actions and checking progress from a phone — but those chats never become part of your web or mobile chat history. If you have been looking for Codex on chatgpt.com, it is not hiding; it is not there.

It works where code lives: local folders, repositories, terminals and developer tools, with inline editing within diffs and pull-request review in a side panel. Recent additions include a plugin directory for packaged workflows, computer use, and remote control for Windows hosts. Voice works with Codex on desktop, drawing on the same tools and permissions the experience already has.

Billing is where Codex stops behaving like ChatGPT. Work and Codex share an agentic usage and credit pool, and additional credits can be bought beyond plan limits. That is a genuinely different model from the unlimited-chat-plus-metered-tools structure of the rest of the product — and OpenAI does not publish a dollar price for a credit anywhere, which is why we took its rate card apart separately.

Experience: Third, beside Chat and WorkPlatforms: Desktop appWeb / mobile: Not selectableMobile remote: Remote tabWorks with: Repos, terminals, local foldersCredit dollar price: Not published by OpenAI
!
Per vendor docs — we did not run this test. The answer above rests on the source below, read on . Where we run a capability ourselves, this section carries the terminal transcript instead.
Source OpenAI Help Center — ChatGPT Work and Codex (updated 4 days before we read it) https://help.openai.com/en/articles/20001275
§ 02 / WHY

What we know that OpenAI doesn't print.

2.1
The credit problem, and what we did about it

Codex meters usage in credits. OpenAI publishes what a plan includes and what more credits cost to buy, but not what a credit is worth in dollars of model usage — which makes comparing Codex against any per-token alternative impossible on the vendor's own numbers.

So we did the arithmetic ourselves: divide the published rate card by the per-token prices in our pricing snapshot, and show every line of the working. That is on our Codex pricing page, along with the access routes and what each one actually includes. It is the single most useful thing on this site about Codex, and it is not something you will find in the help centre.

2.2
Where this page stops and the section starts

This page answers what is it. The section that answers should you use it, what does it cost, and what does it fail at is /agents/codex/, which covers Codex the way we cover any tool we take seriously: every route in priced from the vendor's own page and stamped with a date, and the honest cases where something else is the better choice on the alternatives page.

One thing we will say plainly here, because it is the kind of claim that is usually fudged: we have not run Codex ourselves. Doing so would require signing into somebody else's ChatGPT account, which we do not do. Where our Codex pages rest on documentation rather than our own runs, they say so on the page.

2.3
Codex versus the other coding agents

The comparison people actually want is against Anthropic's Claude Code, and we have it written out at Codex vs Claude Code — plus Codex vs Cursor for the editor-shaped alternative.

The structural differences that matter before any benchmark: Codex lives in a desktop app and bills in credits from a pool shared with Work; Claude Code is a terminal tool covered by a Claude subscription or API credits; Cursor is an editor. Those shapes decide more about whether a tool fits your day than any leaderboard does, which is why our ranking is built from our own comparison pages rather than from a score we invented.

Frequently asked.

Quick follow-ups people search after this question.

Q · 01 Where do I find Codex in ChatGPT? +
In the ChatGPT desktop app, from the top-left menu. It is a separate view from Chat and Work, with its own history. Codex is not selectable on the web or in the mobile app — mobile offers a Remote tab for reaching supported desktop Codex sessions.
Q · 02 Is Codex included in my ChatGPT plan? +
Access and included usage depend on your plan, and it is metered in credits from a pool shared with ChatGPT Work rather than counted as messages. Extra credits can be purchased beyond plan limits. Our Codex pricing page sets out each route and what it includes.
Q · 03 What is the difference between Codex and ChatGPT? +
Codex is one of ChatGPT's three experiences, dedicated to software development — repositories, terminals, tests, diffs and pull-request review. Chat is conversational, Work produces documents and reports, and Codex writes and runs code.
Q · 04 How much does a Codex credit cost? +
OpenAI publishes what plans include and what more credits cost to buy, but not what a credit is worth in model usage. We estimated it by dividing the published rate card by per-token prices from our pricing snapshot, and show the working on our Codex pricing page.
Q · 05 Have you tested Codex yourselves? +
No. Running it would require signing into a ChatGPT account we do not have, and we do not use other people's accounts. Our Codex coverage is documentation-based and says so on each page, which is a different claim from the capability tests we publish transcripts for.