OpenAI Codex Cloud

OpenAIDeveloper toolReleased 29 SeptOfficial site for OpenAI Codex Cloud no referral link

Codex tasks that keep running in OpenAI's cloud, on Plus and up; no independent test of the cloud side yet.

Our callFirst look: Worth tryingChecked 11 Oct

ScoreNot scored yetOnce an independent agent benchmark or a credible independent write-up covers Codex running in the cloud.

Cost$20 a monthNo free plan

Cheaper optionOpenCodeScores 80 for coding, free

Should you use it?

Pick it if

ChatGPT Plus or Business users who want coding tasks to run unattended in the cloud.

Best for: ChatGPT Plus or Business users who want coding tasks to run unattended (Coding agents Top 20)

Skip it if

You don't pay for ChatGPT; GitHub Copilot Pro includes a cloud agent that opens pull requests at $10/month s4.

You give up: Not on Free, Go or an API key alone; cloud tasks use more of your plan allowance

The short version

What this is: Runs Codex coding tasks in reusable cloud environments, so work continues while your laptop is closed. Announced at OpenAI DevDay on 29 Sep 2026.
Why it matters: Handy if you already pay for Plus, but how well the cloud agent works hasn't been tested independently.

Included with ChatGPT Plus at $20/month and higher plans s1 s2.
Cloud tasks draw more from your usage limits than local ones s2.
Personal plans train on Codex tasks unless you opt out s3.

Good at

Reusable cloud environments so tasks start quickly and keep going while your computer is off, with shared team settings s1.
Comes with the $20 Plus plan rather than a separate fee s1 s2.

Weak at

Cloud tasks can use more of your plan's allowance than local messages, and OpenAI gives no task count s2.
Not on Free or Go, and not with an API key alone s1 s2.

Our take

This was a headline item at OpenAI's DevDay on 29 Sep 2026 s1: Codex can now work in reusable cloud environments, so a task keeps going while your computer is off. It comes with Plus at $20/month and higher plans s1 s2. We haven't scored it because no independent test of the cloud agent has been published; the one public comparison of Codex as a tool, from May 2026, doesn't say which surface it measured. The OpenAI Codex CLI review covers that evidence.

Two practical points from OpenAI's pages: cloud tasks use more of your allowance than local work, with no stated number s2, and on personal plans training on environments has its own setting, separate from the usual ChatGPT one s3.

Not scored yet

This is a First look: the call above comes from the maker's own pages, so there is no score yet. Once an independent agent benchmark or a credible independent write-up covers Codex running in the cloud.

CodingAgents

New to this? What the scores and labels mean

0 to 100: Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
Our verdict: Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
First look: Just released. We say what it is and whether to bother, and give it a score once public results exist.
No score yet: None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
Best buy: Nothing cheaper scores as well for that job.
Best free: The best score for that job that costs nothing, through a free plan or by running on your own computer.
Pay as you go: No monthly plan: you pay for each use, usually through a developer account.
Checked: The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
AI model: The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
Open source: Free to download and run on your own computer, so nothing leaves your machine.

How we score, in full

Alternatives

Better or cheaper for coding, from our scores, then the ones we'd also look at. The same kind of product comes first.

OpenCodeTop scoredCoding agent80FreeScores 80 in coding, first in our ranking; free. Side by side
GitHub Copilot (including Copilot CLI and cloud agent)Coding agentFirst look: Worth trying$10 a monthIts cloud agent turns an issue into a pull request, from $10/month. Side by side
OpenAI Codex CLICoding agent70$20 a monthThe same Codex agent on your own machine. Side by side
Claude CodeCoding agent70$20 a monthAlso runs cloud sessions in Anthropic-managed machines on paid Claude plans. Side by side

Compare side by side →

Evidence

Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.

How we scored this

Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.

No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score

Sources 4

s1OpenAI: DevDay 2026 recapchecked 11 Oct
s2Codex docs: Pricingchecked 11 Oct
s3OpenAI Help: How your data is used to improve model performancechecked 11 Oct
s4GitHub Copilot planschecked 11 Oct

Something here out of date or wrong? Report a mistake and we will check it against the source.

History 1 change

Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.

11 OctFirst look; no independent evidence for the cloud agent yet.

Use it well 3 guides on this site

Pages on this site that help with the jobs above.