From ChatGPT to Codex, guide in 10 steps
You're already paying for Codex through your ChatGPT plan. Here's how to actually open it in ten steps.
If you have ChatGPT Plus or Pro, you've been paying for Codex for months but probably never opened it. Codex isn't ChatGPT with another name, it's a different tool that actually executes tasks instead of just answering. Here's how to get to actually using it in ten steps.
1. Find Codex
Open chatgpt.com on desktop and look at the top bar or left menu. There's a "Codex" button. If you don't see it, type chatgpt.com/codex directly into the address bar.
A tip: bookmark chatgpt.com/codex. The UI will keep shifting, but the path stays. Then you don't have to relearn navigation each time OpenAI rebuilds the interface.
As of 31 July 2026: Codex now runs on OpenAI's 5.6 generation, where Terra covers balanced everyday work and Luna the fast, cheap runs. Nothing changes for you at the start, but if you push tasks through all day, the smaller tier is worth a look because you hit the limit later with it. Which model for what is in Model landscape 2026.
2. What Codex does differently from ChatGPT
ChatGPT answers you. Codex executes. You give it a real task, Codex spins up an isolated container in the cloud, does the work, returns the result. It's like ChatGPT with hands.
A tip: the first task should be boring and concrete. Summarize a PDF, rewrite a long email, sort an Excel list. Anything you'd otherwise hand to an intern.
3. The first run in under five minutes
On the Codex page you see two buttons: "Code" and "Ask". Ask behaves like ChatGPT. Code actually executes the task. Take a real thing you did by hand this week, paste it in, click Code, wait.
A tip: be concrete about output format. "Bullet list" is weaker than "table with three columns: task, owner, due by". The more precise you specify how you want it, the more usable the result.
4. Where Codex lives
Codex is in five places. Web at chatgpt.com/codex, the iOS app with a Codex tab, a desktop app for Mac and Windows, a VS Code extension for developers, and a CLI for the terminal. For the first week the web version is enough. Don't install anything.
A tip: the desktop app is worth it only if you want to run multiple tasks in parallel or keep files local instead of in the cloud. One version on day one is enough.
5. Use Codex for non-code things
This is the step most skip. The name sounds like "for programmers only", but in practice I use Codex more for Excel cleanup, PDF summaries, research reports with sources, translations with consistency checks, Notion reorganizations, and bug-report sorting than for actual code.
A tip: write down three tasks you do by hand every week and don't want to anymore. Hand them to Codex for two weeks. One never lands on your desk again.
6. Understand the limits and expand them
Codex is in your ChatGPT plan, no extra charge. Plus gives you a few sessions per week, the Pro tiers give roughly ten to twenty times that plus access to the research-preview model. Exact quotas and prices change every few months, check OpenAI's pricing page when deciding. If you hit the limit on Plus mid-task, switch in chat to the current mini model, that gives 2 to 4 times more runtime depending on the moment with little quality loss.
A tip: start with Plus. Run it for three weeks, see how often you really hit the cap. Only then decide on Pro. Don't preemptively upgrade.
7. Connect GitHub only if you really have code tasks
Non-code tasks don't need GitHub. The connector exists so Codex can read, review and change repositories, but that's not needed in the first month. Stick with single file uploads, that's enough for 90% of all uses.
A tip: if you want to test code tasks for real, attach a small private test repo first. Have Codex review a tiny change, see how it feels before letting it loose on something important.
8. Solve the memory problem
This is the biggest trap when switching from ChatGPT. ChatGPT remembers you, Codex doesn't. Each session starts empty. Two honest solutions. The simple: place a Markdown file agent.md in your work folder, write your project facts there, tell Codex at session start to read it. The complete: attach external storage via MCP. MCP is a protocol Codex understands natively, so your facts and decisions are simultaneously available in Claude, Codex, and your other tools.
A tip: start this week with the Markdown file. That catches 80% of the pain. Get into MCP only once you really feel the gap.
New since Codex CLI version 0.145.0: there is an /import command that pulls in existing memories from Cursor and Claude Code. So if you are coming from either of those, you do not have to retype your project facts. You still need the rest of this step, because imported is not the same as maintained.
9. Accept the cloud execution model
Each time you click "Code", your task runs in an isolated cloud container that's discarded after completion. That's why tasks take one to two minutes, and why you don't have to worry about Codex touching your local machine when you use it in the browser. The result stays, the container doesn't.
A tip: don't stare at the spinner. Start the task, open another tab, switch to your phone, come back when done. Codex is built async, use it that way.
10. Build a small habit, not a giant project
The fastest way to get Codex into your daily life: replace one recurring manual task with it. Not ten, not a whole workflow, just one. Monday morning inbox to action list. Friday weekly report. Wednesday KPI cleanup. Take the smallest recurring thing you really do and hand it to Codex for two weeks.
A tip: when the first habit sits, add the next. Stacking is what turns a tool you opened once into one you rely on.
What's next
If you've done these ten steps, you know Codex well enough to decide if it stays in your setup permanently. The honest weakness is the missing memory between sessions. The honest fix, without you having to buy something new, is the MCP path.
If you want to go further there, see the playbook "Use memory portably" or directly Level 4 of the Academy. There we show how external storage works simultaneously in Codex, Claude, and Cursor. One source of truth, many clients. That's what Codex alone doesn't offer.
For now: open it, throw in a task, two weeks straight. The rest comes by itself.