Codex vs Cursor: what still separates them

The old answer to this comparison was that they are not substitutes: one is a terminal agent, the other is an editor. That answer expired. Cursor ships a headless CLI, Codex ships an extension that installs inside Cursor, and both run several agents at once in git worktrees. Two differences survived.

By the Continuum team. We build a workbench that runs Claude Code, Codex, and their peers, so the model rates quoted here are the ones our own cost analytics ship with.

The short version

Codex is included with ChatGPT plans from $20/mo and confines itself with an operating-system sandbox: Seatbelt on macOS, bubblewrap on Linux. Cursor Pro is $20/mo and owns predictive editing with Tab, plus an Agents Window that runs parallel agents in git worktrees. Both now have a headless CLI, so CI is no longer a Codex-only column. Pick Codex for enforced isolation and scripting, Cursor for editing and review, and note that Codex runs inside Cursor if you want both.

What you need to know
  • Codex comes with a ChatGPT plan you may already have, from $20/mo.
  • Cursor Pro is $20/mo, and Tab is still the only reason to pay for it.
  • Only Codex has an OS-enforced sandbox: Seatbelt, bubblewrap, Windows sandbox.
  • Both run headless now. "Cursor does not work in CI" is out of date.
  • At the limit they fail in opposite directions: Codex pauses, Cursor bills you.
  • The Codex IDE extension installs inside Cursor, so this is not either/or.

Side by side

From both vendors’ own pricing and documentation pages, checked August 2026.

CodexCursor
ShapeTerminal agent, plus a desktop app, an IDE extension and a cloud surfaceAI editor, plus a CLI and cloud agents
Entry priceIncluded with ChatGPT Plus, $20/mo$20/mo Pro
Free tierSmall amounts on ChatGPT Free and GoYes, Hobby
Middle tierNo separate published ChatGPT rungPro+, not published (3x Pro limits)
Top individual tier$200/mo ChatGPT Pro, maximum Codex tasksUltra, not published (20x Pro limits)
Predictive editingNoTab, multi-line and multi-location
Multi-file agent workYes, nativelyYes, Agent
OS-enforced sandboxYes: Seatbelt, bubblewrap, Windows sandboxNo
HeadlessYes, codex execYes, agent -p
Parallel sessionsOne git worktree or cloud task per laneAgents Window with /worktree
Runs inside the otherYes, the IDE extension installs in CursorNo
Diff review surfaceTerminal, or the IDE extensionNative editor diff
At the limitWindow resets, or you buy creditsOn-demand usage, billed in arrears
ModelsOpenAI modelsSeveral vendors

Both crossed into the other’s lane

Comparison articles for this pair are mostly a year out of date, and the two stalest claims are that Cursor cannot run without a GUI and that Codex cannot help you while you are reading code. Neither is true now.

  • Cursor has a command-line agent. The binary is agent, it takes a prompt with -p, and Cursor documents print mode explicitly for scripts and CI pipelines.
  • Codex has an IDE extension that runs beside your editor, including inside Cursor, Windsurf, VS Code, Xcode and JetBrains. It is the same agent with your open files and your selection.
  • Both have a cloud surface. Codex web runs a task in an OpenAI-managed container against a clone of your repository; Cursor runs cloud agents on paid plans.
  • Both parallelise with git worktrees. Cursor built it into the product; Codex expects you to create the worktree, or to hand the task to the cloud.
Installing both command-line agents, from each vendor’s own docs.
# Codex CLI. A Rust binary, so Node is not required.
curl -fsSL https://chatgpt.com/codex/install.sh | sh
codex          # then sign in with your ChatGPT account

# Cursor CLI. The binary is called agent, not cursor.
curl https://cursor.com/install -fsS | bash
agent -p "explain how sessions are authenticated" --output-format text

The sandbox is the difference that did not close

Codex confines itself with facilities provided by the operating system, outside the agent loop. That is a categorically different guarantee from a permission prompt: a read-only session cannot write, no matter what the model decides, what a file it reads tells it to do, or how tired you were when the dialog appeared.

What actually enforces the Codex sandbox, by platform.

PlatformMechanismCursor equivalent
macOSSeatbelt, the same facility macOS uses on its own appsNone. The agent asks you
Linux and WSL2bubblewrap, using unprivileged user namespacesNone
Windows, PowerShellNative Windows sandboxNone

Codex splits capability from interruption. -s sets what the agent can do at all, with three values: read-only, workspace-write, and danger-full-access. -a sets when it stops to ask, with untrusted, on-request, or never. They are independent, which is why the most useful configuration is one many people never try: a tight sandbox that never interrupts.

The two dials, set independently.
# exploration that genuinely cannot write, and never interrupts you
codex exec -s read-only -a never "map how sessions are authenticated"

# may write inside the repository, asks before it wants more
codex -s workspace-write -a on-request

# scriptable review with a machine-readable event stream
codex exec -s read-only -a never --json "review the diff on this branch"

Tab is the other one

Ordinary completion predicts the next tokens where your cursor is. Cursor Tab predicts your next edit, which is usually somewhere else in the file and is usually the mechanical consequence of the change you just made. Codex has no equivalent, and no plausible route to one, because it is not watching your keystrokes.

You add an argument to a signature. Then you press Tab, three times.
you edit:     function send(msg: string)
                                        ^ add a second argument, opts

Tab suggests: line 31   send(text)     -> send(text, {})
Tab suggests: line 88   send(body)     -> send(body, {})
Tab suggests: line 154  send(payload)  -> send(payload, { retry: true })

Parallel agents: two real answers now

Two agents editing the same working tree overwrite each other. Both products solve it the same way, with git worktrees, and the difference is how much of it you assemble yourself.

CodexCursor
How a lane is isolatedA worktree you create, or a cloud task/worktree, inside the Agents Window
Where lanes runTerminals on your machine, or Codex webLocal, worktrees, cloud, remote SSH
Setup for a fresh checkoutYour own script.cursor/worktrees.json
CeilingWhatever your machine toleratescursor.worktreeMaxCount, default 25 per machine
Same task, several modelsRun it twice and compare/best-of-n
Merging backgit merge from the worktree/apply-worktree, or commit in place

The setup row is the one that decides whether parallel agents work or fail identically. A fresh worktree is a clean checkout: no installed dependencies, no untracked environment file, no build cache. Without a setup step every agent you spawn spends its first three turns rediscovering that, badly, in parallel.

.cursor/worktrees.json, so a new lane starts installed rather than broken.
{
  "setup-worktree-unix": [
    "pnpm install --frozen-lockfile",
    "cp ../.env.local .env.local"
  ],
  "setup-worktree-windows": "scripts/setup-worktree.ps1"
}

The cost picture, and what happens at the limit

Both ladders, list monthly prices, August 2026.

TierCodex, via ChatGPTCursor
Free$0, small amounts on Free and Go$0 Hobby
Entry$20/mo Plus$20/mo Pro
MiddleNo separate published rungPro+, not published (3x Pro limits)
Top individual$200/mo Pro, maximum Codex tasksUltra, not published (20x Pro limits)
Team seat$20/user/mo Business, annual billing$40/user/mo Teams Standard

At the entry tier they cost the same, and the pairing is $40 a month. That is the number most heavy users land on, and it is worth noting that half of it is often already being paid: a great many people asking this question hold ChatGPT Plus and have never run codex.

CodexCursor
MeterA rolling five-hour window, with weekly limits on topIncluded model usage per plan, monthly
When it runs outWork pauses until the window resets, or you buy creditsOn-demand usage continues, billed in arrears
What you riskYour afternoon stopsYour invoice grows
Where to check/usage in the CLIThe Cursor dashboard

Which for which hour

TaskWinnerWhy
Editing code you are readingCursorTab, and the editor diff
"Fix this failing test"CodexRuns it, reads the failure, iterates
Exploring an unfamiliar repository safelyCodex-s read-only cannot write, and asks nothing
Six lanes on one repositoryCursorAgents Window plus /worktree
One lane inside a pipelineCodexcodex exec runs once and exits
Reviewing a large agent-written diffCursorThe editor diff is easier to read
Output a script has to parseCodex--json and --output-schema
A ticket to run with the laptop shutEitherCodex web, or a Cursor cloud agent
Running something you half trustCodexcodex sandbox confines any command

Running both, which is what most people do

Because the Codex extension installs inside Cursor, this is one of the few comparisons where the answer can genuinely be "both, in the same window". A setup that takes ten minutes:

01

Start with the one you already pay for

If you hold ChatGPT Plus, the marginal cost of trying Codex this afternoon is zero. Install the CLI, run codex in a repository, and sign in with the ChatGPT account rather than an API key.

02

Put Codex inside Cursor

Install the Codex IDE extension from the marketplace in Cursor. You get the agent with your open files and selection as context, without leaving the editor you are reading in.

03

Give every parallel lane its own checkout

Use /worktree in Cursor, and commit a .cursor/worktrees.json so a new lane installs dependencies instead of failing on them. For Codex, create the worktree yourself or send the task to Codex web.

04

Keep pipelines on codex exec

Both CLIs run headless, but codex exec -s read-only -a never is the combination worth standardising on for CI: the sandbox is enforced by the kernel rather than promised, and it cannot hang waiting for an approval nobody will give.

05

Watch two meters, not one

You now have a five-hour ChatGPT window with weekly limits, and a Cursor allowance that silently becomes on-demand spend. They live in different dashboards and neither knows about the other.

Questions people ask

For work you hand over, for anything that runs unattended, and for scripting, yes. Codex confines itself with an operating-system sandbox and codex exec runs once and exits. For editing code you are actively reading, Cursor is better, and Tab is the reason.

Yes, and more directly than most pairings. The Codex IDE extension installs inside Cursor, so the agent and the editor share one window. At entry tiers the pairing is about $40 a month, and half of it is often already on your card as ChatGPT Plus.

Both are $20 a month at the entry tier as of August 2026. Codex comes with ChatGPT Plus, so if you already pay for that the marginal cost is zero. Higher up they diverge: Cursor does not publicly publish Pro+ or Ultra prices, while ChatGPT publishes Pro at $200 a month.

Not in the same sense. Codex is confined by Seatbelt on macOS, bubblewrap on Linux and WSL2, and the native Windows sandbox in PowerShell. Those are kernel-level, so a read-only session cannot write regardless of what it is told. Cursor relies on you approving actions, which is a weaker guarantee exactly when you stop reading the prompts.

Yes. Cursor installs a CLI whose binary is agent, and Cursor documents print mode with -p for scripts, CI pipelines and automation. The claim that only Codex works headless is out of date, though codex exec is still the better default for a pipeline because of the enforced sandbox.

Cursor, if you want it built in. The Agents Window runs many agents in parallel and /worktree isolates each one, with setup commands in .cursor/worktrees.json and a default ceiling of 25 worktrees per machine. Codex parallelises just as well, but you create the worktrees yourself or delegate to Codex web.

They fail in opposite directions. Codex pauses until the rolling five-hour window resets, or you buy credits. Cursor keeps working on on-demand usage and bills it in arrears. One costs you an afternoon, the other costs you money, and which is worse depends entirely on your week.

If you already pay for ChatGPT, start with Codex, because it costs nothing extra and you can decide with real evidence in a fortnight. If you spend most of your day inside existing code and want the typing itself to be faster, Cursor, and Tab is the whole argument.

Sources

Every figure above was read from these pages on August 2026. Vendors reprice without notice; if you find a stale number, tell us.

  1. ChatGPT plans and pricing
  2. Cursor pricing
  3. OpenAI Codex documentation
  4. Codex sandboxing
  5. Cursor CLI overview
  6. Cursor worktrees configuration
Try it

Editor and agent,
one gauge.

Continuum runs Codex and Cursor agent side by side, each in its own worktree, with live quota per subscription and one spend view.

free app · your subscriptions · local-first