Orkas Orkas
Home Compare Claude Code vs Codex
Honest comparison

Claude Code vs Codex:
they now do most of the same things, so pick by plan, model and sandbox, or run both.

Claude Code is Anthropic's coding agent and runs only Claude models. Codex is OpenAI's, runs OpenAI's GPT-6 models, and its CLI is open source. Both now work in the terminal, your editor, a desktop app, the web and your phone, and both have plan mode, skills, plugins, hooks, subagents, MCP and memory. What still separates them is whose plan you pay for, how each one fences in commands (the Codex sandbox is on by default, Claude Code's is off) and how each runs on Windows. They also work together: OpenAI ships a Codex plugin for Claude Code, and Codex can import your Claude Code setup.

Side by side

Claude Code vs Codex, capability by capability

Checked against Claude Code 2.1.322 and Codex CLI 0.167.1, both released on November 10, 2026, using each vendor's own docs and pricing pages.

CapabilityClaude CodeAnthropic · proprietaryCodexOpenAI · CLI under Apache-2.0
What it isAnthropic's coding agent; the source is closedOpenAI's coding agent; the CLI is open source (Apache-2.0)
Where you use itTerminal, VS Code and JetBrains, the Claude desktop app (macOS, Windows, Linux in beta), the web and the Claude mobile appTerminal, VS Code, Cursor and Windsurf (Xcode and JetBrains have their own Codex integrations), the ChatGPT desktop app (macOS, Windows, Linux in preview), the web and the ChatGPT iOS app
ModelsClaude models only, through Anthropic, Amazon Bedrock, Google Cloud or Microsoft FoundryOpenAI's GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Luna, depending on your plan; with an API key, the models your API account has
Plans that include itClaude Pro ($20 a month), Max ($100), Ultra ($200), Team or Enterprise, or an API key; the Free plan does not include itChatGPT Plus ($20 a month) for the CLI, editor, web and iOS; Pro at $100, $200 or $500; Business or Enterprise; or an API key. OpenAI lists Free and Go for the desktop app with GPT-6 Luna, still rolling out
ApprovalsPermission modes from Manual to auto, which runs background safety checks and is the starting mode in the terminal and VS Code; deny rules hold in every modeAsk for approval (recommended), Approve for me (automatic review) or Full access; in a git folder the CLI starts with workspace writes and on-request approvals
SandboxOff by default; /sandbox turns on an OS sandbox for shell commands on macOS, Linux and WSL2On by default for every command it spawns, on macOS, Linux, WSL2 and native Windows; .git and .codex stay read-only
WindowsRuns natively; shell commands run unsandboxed unless you use WSL2Runs natively in PowerShell with its own Windows sandbox, or in WSL2
Instructions and memoryCLAUDE.md, or a repository's AGENTS.md, plus auto memory notes it writes itself, on by defaultAGENTS.md, plus local Codex memories you can switch on or off per machine
Extending itSkills, plugins and marketplaces, subagents, agent teams (experimental), hooks and MCP serversSkills, plugins that bundle skills, MCP servers and hooks, custom subagents, and the Codex SDK
Planning and undoPlan mode, and checkpoints you can roll back with /rewindPlan mode with /plan; for rollback, OpenAI suggests git checkpoints before and after a task
Working while you are awayCloud sessions on the web, cloud scheduled tasks (research preview), desktop scheduled tasks and Remote Control from your phoneCodex Cloud tasks that keep running while your computer sleeps, scheduled tasks, and the ChatGPT iOS app to follow and approve work
Code review and team toolsCode Review, GitHub Actions, GitLab CI/CD and SlackAutomatic GitHub code review (GitLab in preview), a GitHub Action and @ChatGPT in Slack

Neither is a complete security boundary: Claude Code's sandbox covers shell commands only, and Full access in Codex removes its sandbox. Many comparisons online are out of date: they cite GPT-5-era Codex models (GPT-5.5 left Codex for ChatGPT sign-in on October 14, 2026), count hooks as a Claude Code advantage although Codex has them too, or treat Claude Code as a terminal tool only.

This comparison was last updated on November 12, 2026; check each vendor's site for current terms.

Using them together

How Claude Code and Codex work together

Many people who search this end up running both. OpenAI supports that directly: it ships a plugin that calls Codex from Claude Code, and Codex can import your Claude Code setup.

Call Codex from inside Claude Code

OpenAI's Codex plugin for Claude Code adds /codex:review for a read-only review, /codex:adversarial-review to challenge a design decision and /codex:rescue to hand Codex a task. It runs the Codex CLI on your machine, needs a ChatGPT plan or an OpenAI API key, and counts against your Codex usage limits.

/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins
/codex:setup

Move a session, or your whole setup, to Codex

/codex:transfer hands the current Claude Code conversation to Codex; then run the codex resume command it prints. To bring everything, /import in the Codex CLI turns CLAUDE.md into AGENTS.md and settings.json into config.toml, and copies skills, plugins, MCP servers, hooks, subagents and up to 50 chats from the last 30 days. Your Claude Code setup stays as it was.

# in Claude Code
/codex:transfer
# then, in your terminal
codex resume <session-id>

# or bring your whole setup (in an idle Codex CLI session)
/import

One AGENTS.md for both

Codex reads AGENTS.md before it starts work, and Claude Code can read a repository's AGENTS.md in place of CLAUDE.md, so one file of project rules can serve both. Older guides that add Codex to Claude Code as an MCP server with codex mcp-server no longer work: OpenAI removed that command, and the plugin is the supported route.

Both in one desktop window

Orkas runs Claude Code and Codex as two local agents in the same chat, next to OpenCode, OpenClaw and Hermes. The next table lists what Orkas can and cannot hand each of them.

Step-by-step guide: how to run Claude Code and Codex together →

What a host gets

Driving both from Orkas: what each one accepts

These rows come from Orkas's adapter code for each CLI, which is the same in Orkas 2.0 and the next release. They describe what a host can do with each agent, not how well either one works.

In OrkasClaude CodeCodex
How Orkas starts itclaude -p, with streaming JSON in and outcodex app-server, over JSON-RPC
Project folderBound to the project folder you chooseBound to the project folder you choose
The next turnContinues the same sessionContinues the same Codex thread
Standing instructionsSent again with every runSaved in the Codex thread and sent again only when they change
Permission levelUse CLI default, Ask for permission (you approve in Orkas) or Full accessUse CLI default, Ask for permission (you approve in Orkas) or Full access
While it runsShows progress as it works, and you can send a message mid-runShows progress as it works; a message you send mid-run joins the current turn

Orkas checks for Claude Code 2.0.0 or later and Codex 0.145.0 or later, finds both on your PATH, can update either one, and installs neither. Each agent keeps its own sign-in, plan and usage limits. Orkas skills, the services you connected and each agent's Orkas memory reach both in every run.

When to choose which

Pick by the plan you have and the machine you work on

Pick Claude Code if…

  • You already pay for a Claude plan, or you want Claude models
  • You want checkpoints you can roll back with /rewind
  • You want to check on sessions from an Android phone as well as an iPhone

Pick Codex if…

  • You already pay for ChatGPT, or you want OpenAI's models
  • You work on native Windows and want commands sandboxed without WSL
  • You want to read, fork or build on the CLI's open source code
Running both from one place

Claude Code and Codex side by side in Orkas

Orkas is a free, MIT-licensed desktop app for macOS and Windows. It runs the Claude Code and Codex you already have, plus OpenCode, OpenClaw and Hermes, as agents in one chat.

1

Install Claude Code and Codex first and sign each one in with its own plan or API key. Orkas finds them on your PATH and needs Codex 0.145.0 or later.

2

Open Connect agents and add both.

3

Set approvals in AI Team > Claude Code > Runtime settings > Permission level, and the same for Codex. Then, in the same chat, @-mention one to plan or review and the other to build.

What Orkas does not do here: it does not install either CLI, sign you in or add usage to either plan. Cloud tasks, Remote Control and the ChatGPT apps stay with each vendor.

FAQ

Claude Code and Codex — your questions

Which is better, Claude Code or Codex?

Neither wins outright, and most head-to-head tests online predate the current models. The two run in the same places and share most features, so decide on three things: which plan you already pay for, whether you want Claude or OpenAI models, and how much sandboxing you need, especially on native Windows. Many developers use both, one to plan or review and the other to build.

Is Codex cheaper than Claude Code?

Both start at $20 a month: Claude Pro for Claude Code, ChatGPT Plus for Codex. Above that, Claude has Max at $100 and Ultra at $200, and ChatGPT Pro costs $100, $200 or $500. Claude's Free plan does not include Claude Code, while OpenAI lists ChatGPT Free and Go for Codex in the desktop app with GPT-6 Luna, still rolling out. How far each plan goes depends on the model and the task, so compare them on your own work.

Can Claude Code use OpenAI models, or Codex use Claude?

Not officially. Claude Code runs Claude models only, and Anthropic does not support routing it to other models through a gateway. Codex runs OpenAI models; a custom provider has to offer a Responses API endpoint, and Chat Completions-only endpoints are not supported. To use both model families, run both agents.

Can I move from Claude Code to Codex?

Yes. Type /import in an idle Codex CLI session and choose Claude Code. It turns CLAUDE.md into AGENTS.md and settings.json into config.toml, copies skills, plugins, MCP servers, hooks, subagents and up to 50 chats from the last 30 days, and makes your slash commands into skills. The ChatGPT desktop app can also import from Claude Cowork. Your Claude Code setup is not changed, but check imported permissions and hooks before you rely on them.

Can I use Claude Code and Codex together?

Yes. OpenAI's Codex plugin for Claude Code lets you run /codex:review or hand over a task with /codex:rescue without leaving Claude Code. Orkas runs both as local agents in one desktop window, each in the project folder you choose, with its own session, progress and approvals, so you can @-mention one to plan or review and the other to build.

More comparisons

More comparisons of coding agents

Anthropic's coding agent and OpenAI's, in one window

Orkas is free and MIT licensed. It drives Claude Code, Codex, OpenCode, OpenClaw and Hermes as local sessions on your own machine.