Codex alternatives in 2026: 7 coding agents and apps to use instead

Disclosure: Enjoy is our product, and it runs Codex. We checked every option below against its maker’s own pages on October 28, 2026, and we say where another option is the better pick, Codex included.

Codex alternatives compared

OpenAI’s Codex is a coding agent: you describe a change, and it reads your project, edits files and runs commands until it’s done. It runs in the ChatGPT desktop app, which OpenAI sums up as “Run projects in parallel, work with files, use your computer, and keep long-running work moving from one desktop workspace,” and in a terminal, your editor and the browser, on a ChatGPT plan. The options below do the same job with other labs’ models, on other plans, or with code you can read and change. Two of them, GitHub Copilot and Enjoy, can run Codex itself.

Option	Best for	Price, checked October 28, 2026	Runs on	Models
Codex	OpenAI’s models, at a low cost per task	Free and Go ($8) in the desktop app; Plus $20; Pro $100, $200 or $500	Mac, Windows, Linux	GPT-6 Luna on Free and Go; GPT-6.1 Sol from Plus
Claude Code	The nearest match, with Claude	Claude Pro $20 a month, or $17 billed yearly; Max from $100	Mac, Windows, Linux	Anthropic’s Claude models
GitHub Copilot	OpenAI’s models, and Codex itself, on GitHub’s plan	Free; Pro $10 a month; Pro+ $39; Max $100	VS Code, Visual Studio, JetBrains IDEs, Eclipse, Xcode; CLI on Mac, Windows, Linux	GPT, Claude and Gemini; GPT-6.1 Sol from Pro+
Cursor	An AI editor with Grok included	Free; Plus $8 a month, Grok and Composer only; Premium $30, other labs’ models at API prices	Mac, Windows, Linux	Grok and Composer; GPT-5.6, Claude and Gemini billed separately
OpenCode	Free and open source, with your ChatGPT plan or any provider	Free; other providers at their own prices	Mac, Windows, Linux	75+ providers, free models and local ones
Antigravity CLI	Gemini for free	Free; Google AI Pro $19.99 a month; Ultra from $99.99	Mac, Windows, Linux	Gemini; Claude Sonnet and Opus 5.5 on paid Pro and Ultra
Cline	An open-source agent in your editor, with your own keys	Free; ClinePass $9.99 a month	VS Code, JetBrains IDEs, Cursor, Zed and other editors, and a CLI	Any provider’s key
Enjoy	Keeping Codex, with other labs’ agents beside it	A monthly subscription, free for 7 days, with your phone and other computers (pricing)	Mac, Windows, Linux	Codex, Claude Code, Grok Build, Antigravity, Muse Code, OpenCode

Prices are per month as each maker lists them in the US, before tax. Codex, Claude Code, Copilot, Cursor and Antigravity CLI come with their makers’ own plans; OpenCode, Cline and Enjoy run on the plans, keys and free models you choose.

Why people look for a Codex alternative

Three things on OpenAI’s own pages send people looking:

• Pro 200 is shrinking. OpenAI’s help center says eligible Pro 200 subscribers keep the previous allowance “through October 29, 2026 while their Pro 200 subscription is active,” and “After that date, your subscription will move to the lower included usage allowance.” The price stays $200 a month. Our memo on the change has the numbers.
• The limits aren’t fixed, and ChatGPT shares them. Codex’s pricing estimates 15 to 160 local messages every five hours with GPT-6.1 Sol on Plus, then says “These estimates are not fixed message limits” and “Weekly limits may also apply.” “ChatGPT Work and Codex share usage,” and OpenAI’s usage guide adds: “Where both apply, you need allowance remaining in both to continue.”
• The free plans get the least. Free, and Go at $8 a month, get “GPT-6 Luna at Standard speed in the desktop app, subject to rollout.” The CLI, the IDE extension and GPT-6.1 Sol start with Plus, at $20. On Artificial Analysis’s Coding Agent Index, Codex with GPT-6 Luna scores 31.1 at max effort, against 54.1 with GPT-6.1 Sol.

Claude Code

Best for: the nearest match to Codex, with Claude’s models.

Claude Code is Anthropic’s coding agent, and it works much as Codex does: in a terminal on macOS, Windows and Linux, and as the Code tab of the Claude desktop app, on Mac and Windows with Linux in beta, where, its docs say, “The sidebar lists your sessions and lets you run several in parallel.” Your project’s instructions come with you: Claude Code “can read AGENTS.md as your project instructions, so a repository already set up for other coding agents works without adding a CLAUDE.md,” per its docs.

On the Coding Agent Index, Claude Code with Opus 5.5 at max effort scores 61.7, the highest on the index, against 54.1 for Codex with GPT-6.1 Sol.

Price: “Claude Code is included in all paid plans,” says Claude’s pricing: Pro at $20 a month, or $17 a month billed yearly, and Max from $100. Its setup guide says “The free claude.ai plan does not include Claude Code access.”

Watch for: Anthropic’s limits replace OpenAI’s. “Both Pro and Max plans have a five-hour session limit and a weekly limit,” says its help center, and “These limits are shared across Claude and Claude Code.” The top score costs more: $11.42 a task in API prices with Opus 5.5, against $1.50 for Codex with Sol. Claude Code isn’t open source: its license reads “© Anthropic PBC. All rights reserved.” And on native Windows, its setup guide lists sandboxing as “Not supported”; that takes WSL 2. Our Claude Code vs Codex guide compares the two in detail.

GitHub Copilot

Best for: keeping OpenAI’s models, and even Codex itself, on GitHub’s plan, beside Claude and Gemini.

GitHub Copilot works in VS Code, Visual Studio, JetBrains IDEs, Eclipse and Xcode, per its feature matrix, and its plans page says “All plans include Copilot CLI and the Copilot app.” Copilot CLI runs on Linux, macOS, and “Windows from within Powershell and Windows Subsystem for Linux (WSL).” Its model list puts OpenAI’s models in the plans: Pro includes GPT-6.1 Terra and GPT-6 Luna, with Claude Sonnet 5.5 and Gemini 3.8 Flash, and Pro+ adds GPT-6.1 Sol, GPT-6 Astra, Claude Opus 5.5 and Gemini 4 Argon.

It runs Codex too. GitHub’s docs say “The OpenAI Codex coding agent and the VS Code OpenAI Codex integration use the Codex SDK and can be powered by your existing Copilot subscription.”

Price: Copilot Free costs nothing. Pro is “$10 USD per month (free for some users),” with 1,500 GitHub AI Credits a month; Pro+ is $39, with 7,000; and Max is $100, with 20,000. Past that, “additional usage is billed in GitHub AI Credits at the per-token rates” on its pricing page, where a credit is a cent and GPT-6.1 Sol costs $2 per million input tokens and $10 per million output.

Watch for: “Copilot Student and Copilot Free users have access to models through auto model selection only,” so you can’t pick GPT there. The Codex integration “is currently in public preview,” GitHub’s Codex agent offers GPT-5.3-Codex and GPT-5.4 nano rather than the GPT-6 models, and signing in to OpenAI’s Codex extension for VS Code with Copilot “is only available to GitHub Copilot Pro+ and Copilot Max subscribers.”

Cursor

Best for: an AI code editor with Grok’s models included, if you don’t need GPT.

Cursor is an AI code editor for macOS, Windows and Linux, with a CLI, run as agent, that installs on “macOS, Linux and Windows (WSL)” and “Windows (native).” “Cursor is sold as part of The X Subscription, one subscription for Grok, Cursor, and X,” says its models page, and its paid plans “include a weekly pool of usage for Cursor models, shared across Grok and Cursor.”

Price: its pricing has Free, with “Limited agent requests”; Plus at $8 a month, where “Only Grok models are available on this plan”; Premium at $30; Super at $100; and Ultra at $200.

Watch for: GPT is on its way out. Cursor’s models page lists GPT-5.6, not OpenAI’s GPT-6 models, and OpenAI’s help center says “We have proposed a transition period of November 12, 2026,” adding that “Cursor may choose to end access sooner.” Until then, “Plus and Free don’t include third-party models,” and on Premium and above they’re paid “at the model’s API list price from the first request.” Our memo on the cutoff has the details, and our Cursor alternatives guide covers its plans.

OpenCode

Best for: a free, open-source agent that can keep your ChatGPT plan, or use any other provider.

OpenCode is “The open source AI coding agent,” under the MIT license on GitHub, where it has more than 220,000 stars. It’s “Available as a terminal interface, desktop app, and IDE extension” for macOS, Windows and Linux, and the desktop app is in beta. Its homepage lists “75+ LLM providers through Models.dev, including local models,” and you can “Log in with OpenAI to use your ChatGPT Plus or Pro account,” so you keep GPT and change only the agent around it.

Price: “OpenCode is 100% free to use,” and “OpenCode comes with a set of free models that you can use without creating an account.” Other providers bill you at their own prices.

Watch for: your Claude plan doesn’t come along. Its providers page says “There are plugins that allow you to use your Claude Pro/Max models with OpenCode. Anthropic explicitly prohibits this.” Its free models are free “for a limited time,” and for several of them, “The team is using this time to collect feedback and improve the model.” Its homepage says “Your data and information is only stored when you use our free models.”

Antigravity CLI

Best for: Gemini for free, and Claude on Google’s plan.

Antigravity CLI, run as agy, is Google’s coding agent for the terminal, with installers for macOS, Linux and Windows, beside its Antigravity desktop app. Google’s plans page gives every plan “Access to all product features, such as scheduled tasks and the CLI.” On the Coding Agent Index, Antigravity CLI with Gemini 4 Argon at high effort scores 53.2.

Price: free. Google AI Pro is $19.99 a month, and Ultra starts at $99.99. Its models page gives a free account Gemini 3.8 Flash, while a paid Pro plan adds Gemini 4 Argon and Claude Sonnet 5.5 and Opus 5.5, “Available on Google AI Pro for non-trial subscriptions only.”

Watch for: there’s no GPT. The only OpenAI model on its models page is GPT-OSS-120b, which “Will be removed on November 2, 2026,” along with the Claude models on free accounts, as our memo on the change explains. Without Pro or Ultra, you get “A meaningful quota, refreshed weekly,” and there’s no support for “Bring-your-own-key (BYOK) or bring-your-own-endpoint for additional rate limits.”

Cline

Best for: an open-source agent inside the editor you already use, with your own OpenAI or other keys.

Cline is an “Autonomous coding agent as an SDK, IDE extension, or CLI assistant,” under Apache 2.0 on GitHub. Its docs say it “works across all major editors”: VS Code, Cursor, Windsurf, JetBrains IDEs, Antigravity, Zed and Neovim. The CLI installs with npm i -g cline.

Price: “The Cline open source extension is completely free for individual developers,” says its pricing, and you can bring your own API keys “from providers like OpenAI, Anthropic, Google, and others,” or use Cline’s own provider. ClinePass is a “Flat $9.99/month subscription that offers 2-5x the usage on popular open coding models compared to standard API rate.”

Watch for: you pay for the models separately: “You only pay for AI inference on a usage basis.” An OpenAI key bills at OpenAI’s API rates, apart from any ChatGPT plan you pay for.

Enjoy

Best for: keeping Codex, with Claude Code and other labs’ agents ready when it runs out.

Enjoy is a desktop app for Mac, Windows and Linux that runs Codex itself, signed in to your ChatGPT plan, along with Claude Code, Grok Build, Antigravity, Muse Code, and local models through OpenCode. What it adds:

• Hand the conversation on. Switch agents at any point: “The new agent gets the conversation so far, including replies from other agents, before it works on your message.” Build with Codex, then have Claude Code review it.
• Keep going through limits. When Codex runs out, Enjoy offers your free resets, switches to another ChatGPT account with usage left, or waits for the reset and carries on, a weekly one included. Select Stop waiting to hand the conversation to Claude Code instead.
• Your history, brought in. Enjoy imports a project’s past Codex conversations, so you pick up where you left off.
• Every project at once. Each conversation runs its own agent, and JOY keeps an eye on all your projects: ask it what needs you, or start work in any of them.

Price: Enjoy is one monthly subscription, and the first seven days are free, with a card to start. It includes your phone and any browser and your other computers, and each teammate you invite needs a subscription of their own. See pricing.

Watch for: Enjoy doesn’t change OpenAI’s limits or add GPT to another lab’s plan, and each account is a plan you pay for. It runs the Codex CLI, which OpenAI includes from Plus, so Codex in Enjoy starts at $20 a month. Waiting for a reset needs “Your computer must be on, with Enjoy open, when the usage resets.” Enjoy isn’t open source, it’s a monthly subscription on top of your AI plans once the free week ends, and scheduled workflows run only while your computer is awake with Enjoy open.

When to stay with Codex

If Codex does your work and you rarely run out, none of this is a reason to move. It gets a lot done for the money: on the Coding Agent Index, Codex with GPT-6.1 Sol scores 54.1 at $1.50 a task, under a seventh of the $11.42 that Claude Code with Opus 5.5 costs for its 61.7, and the index says those costs are “pay-per-token API cost, not consumer plan pricing.” Its CLI is open source under Apache 2.0, and on Windows its desktop app “runs natively on Windows using PowerShell and the Windows sandbox,” which Claude Code needs WSL 2 for.

A limit needn’t end your week either. “Pro plans currently have no five-hour limit,” and “ChatGPT Plus and Pro users who reach their usage limit can purchase additional credits.” Our Codex usage limit guide compares the ways to keep going, from free resets to a local model, and if the Pro 200 change sent you here, compare Pro 100 before you leave.

Move when you want Claude’s models, several labs’ models in one plan, an editor of your choice, or a free start with more than GPT-6 Luna. You don’t have to choose only one: ChatGPT Plus and Claude Pro together cost $40 a month, and Enjoy hands a conversation from Codex to Claude Code and back.

How we compared

We read OpenAI’s Codex pricing, docs and help center, Anthropic’s pricing, help center, Claude Code docs and license, each other maker’s homepage, pricing, plans, docs and GitHub repository, and Artificial Analysis’s Coding Agent Index on October 28, 2026, and every one is linked below. Licenses and star counts come from GitHub that day, and index scores and costs are as the index showed them that day. We quote each maker’s own words for its limits and leave out what it hasn’t documented. Plans and models in this category change often, so we recheck this guide against its sources at least once a month, and the date at the foot of the page says when we last did.