Claude Code or Codex: which coding agent to choose in 2026?

Comparison published on October 10, 2026, established from the official documentation of Anthropic and OpenAI consulted that day, and the interfaces of Claude Code and Codex opened on the same day in our accounts (Claude Max subscription, professional ChatGPT workspace).

Short answer: if your team already has a ChatGPT subscription, start with Codex, included in the Plus plan at $20 per month and sandboxed without network access by default; if you want to fine-tune the agent to your team (hooks, MCP connectors, skills), choose Claude Code, included in the Pro plan at $20 per month. As a team, both cost $25 per seat per month ($20 annually).

Claude Code and Codex are currently the two leading code agents: you describe a task to them in plain language, they read the project, modify the files, run commands and tests, and then provide the result. Both work in the terminal, code editor, desktop application, browser, and mobile. Claude Code stands out for its deep customization options and automatic authorization; Codex for its integration with the ChatGPT subscription, its strict default partitioning, and its speed on the higher-priced plans. The choice depends primarily on your existing subscription and the level of autonomy you want to grant the agent. To install Claude Code and configure its rules within an organization, see our guide. Claude Code in business.

The verdict in five lines

  • You already have a ChatGPT subscription: Codex is included in Plus, and is available in a limited version for free.
  • You want to fine-tune the agent to your team: Claude Code, with its hooks, MCP connectors, skills and agent development kit.
  • Default security: Codex works in a sandbox without network access; Claude Code relies on a classifier that blocks risky actions without interrupting you.
  • Background and planned tasks: They both know how to work in the cloud, in parallel and at fixed times.
  • Speed: Codex offers an Ultrafast mode up to 8 times faster, reserved for high-end offers; Claude Code offers a fast mode up to 2,5 times faster on Opus 5.5.

The comparative table

CriterionClaude Code (Anthropic)Codex (OpenAI)
Where to use itTerminal, VS Code, JetBrains, desktop app (macOS, Windows, Linux beta), browser (claude.ai/code), mobile, Slack, ChromeTerminal, editor extension, desktop application (macOS, Windows), cloud in ChatGPT, mobile, GitHub, Slack
ModelsOpus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.1 (1 million context tokens), with effort adjustmentGPT-6.1 Sol, GPT-6 Sol, GPT-6 Astra, GPT-6 Luna, with effort adjustment
Project instruction fileCLAUDE.md, and reading of an existing AGENTS.md; automatic memory management between sessionsAGENTS.md
PermissionsAuto mode (a classifier blocks risky actions), Manual mode, Change acceptance mode, Plan modeRead-only sandbox, write-in-workspace, or full access; approval policies; automatic agent review
Default network accessAccording to the authorizations grantedOff by default, must be explicitly enabled
Go backAutomatic checkpoints before each file modificationReview of changes by discussion thread, isolated worktrees
ExtensionsMCP, skills, hooks, plugins, sub-agents, Agent SDKPlugins (GitHub, Slack, Gmail, Google Drive, Notion, Figma…), skills
parallel workSub-agents, background agents, worktrees, workflows orchestrating dozens of sub-agentsParallel agents grouped by project, worktrees integrated into the application
Scheduled TasksRoutines in the cloud (schedule, GitHub event, API call) and tasks scheduled on the computerAutomations within the application, results in a review queue
Code reviewAutomatic review of pull requests on GitHub, GitHub Actions, and GitLab CI/CDAutomatic review of pull requests on GitHub
Quick modeFast mode on Opus 5.5, up to 2,5 times fasterUltrafast, up to 8x faster, on Pro at $500 and select Enterprise offerings
Free offerNo: paid subscription requiredYes, limited (GPT-6 Luna in the desktop application)
Individual offerPro: $20 per month ($17 annually); Max: $100 or $200Plus: $20 per month; Pro: $100, $200, or $500
Team offerTeam: $25 per seat per month ($20 annually), premium seat $125 ($100)Business: $25 per seat per month ($20 annually)
Other access pointsAPI key, Amazon Bedrock, Google Cloud, Microsoft FoundryAPI key (without cloud functions)

The prices shown are those in dollars displayed by the publishers and may vary in euros depending on VAT. In both cases, the use of the code agent is counted towards the same limits as the chatbot.

What we saw in both interfaces

  • Claude Code in the browser (claude.ai/code): We choose a repository and an environment, then we describe the task. The selector offers the model (Opus 5.5 by default on our account), the effort level (medium by default), the authorization mode (Auto) and the fast mode, disabled by default.
  • Codex in ChatGPT You choose where to work (in the cloud or remotely on your own machine) and an environment, then you describe the task. The selector offers GPT-6.1 Sol with a medium effort by default, and the "Ask for approval" mode, which requests your agreement before sensitive actions.

The two interfaces are very similar: an input field, a repository, a template, a level of autonomy. The difference lies less in the screen than in the default settings and what can be connected to it.

Two philosophies of security

Codex starts from a closed framework. The agent operates in a sandbox where you choose the level of access: read-only, write access limited to the workspace (the "Auto" preset), or full access, which the documentation advises against. Network access is disabled by default and must be explicitly enabled. Approval requests may be reviewed first by a review agent.

Claude Code starts with fluidity. Its Auto mode, now the default for interactive sessions, delegates authorization requests to a classifier: safe actions execute without interruption, while risky ones are blocked. The Plan mode allows a plan to be proposed without modifying the files, and each file change is preceded by a checkpoint that allows for reverting. Actions on remote systems (databases, deployments) cannot be undone in this way: they are governed by authorization rules.

In a company where the IT department wants to maintain control, Codex's default partitioning provides reassurance. For a developer who wants to delegate lengthy tasks without validating each command, Claude Code's Auto mode saves time.

Customize the agent

Both agents read an instruction file located at the project's root: AGENTS.md for Codex, and CLAUDE.md for Claude Code, which can also read an existing AGENTS.md file. A team can therefore share the same instructions between the two tools.

Beyond that, Claude Code offers more points of interest: hooks that run a command before or after an action (formatting the code after each modification, running tests before a commit), MCP connectors to Jira, Google Drive, or your internal tools, skills shareable, sub-agents specialized and a Agent SDK to build your own agents. Codex focuses on plugins ready to use (GitHub, Slack, Gmail, Google Drive, Notion, Figma, Supabase) and on skills manageable from its application.

Working in parallel and in the background

The two developers have made parallel work their priority for 2026. The Codex application presents itself as a "command center" for agents: each task runs in its own thread, on an isolated copy of the repository (worktree), and scheduled automations submit their results to a review queue. Claude Code offers a view of all ongoing sessions, background agents, workflows capable of orchestrating dozens of sub-agents, and cloud-based routines that are triggered by a schedule, a GitHub event, or an API call, even when the computer is turned off.

The models and the cost

On the subscription side, the two plans are identical: $20 per month for both Claude Pro and ChatGPT Plus, and $25 per seat per month ($20 annually) for both Claude Team and ChatGPT Business. Codex maintains an entry advantage: a limited version is available for free, while Claude Code requires a paid subscription.

In terms of modeling, OpenAI presents GPT-6.1 Sol, released in late September 2026, as being close to its most powerful model (GPT-6 Astra) at a fifth of the price. Anthropic presents Opus 5.5, released on September 22, 2026, as its reference model for agentic code, 40% less expensive than Opus 5 on typical tasks. These figures come from the vendors themselves: you should verify them on your own tasks.

Which one to choose depending on your situation

Your situationOur recommendation
Team already equipped with ChatGPT Business or EnterpriseCodex, already included
Team already equipped with Claude Team or EnterpriseClaude Code, already included
IT department demanding on compartmentalizationCodex, closed by default
Advanced automation (hooks, CI, custom agents)Claude Code
Model hosting on AWS, Google Cloud or MicrosoftClaude Code, available on these three platforms
Discovery without a budgetCodex, with its limited free access
Non-developer profiles who want to create toolsBoth, via their web interface or desktop application, rather than the terminal

For the conversational aspect of these two ecosystems, see our comparison. Claude or ChatGPTand to choose the right model depending on the task, The right AI model for each task.

F.A.Q

Claude Code or Codex: which is better for coding?

Neither excels in every area. Both developers publish test results that place them at the top in certain areas. In practice, Claude Code is more customizable and smoother to use independently, while Codex is more compartmentalized by default and included in the ChatGPT subscription.

Claude Code vs Codex: which is cheaper?

Subscriptions are the same price: $20 per month for individuals, $25 per seat per month for teams ($20 annually). Codex also offers limited free access. The actual cost depends primarily on usage, which is calculated based on limits that are renewed every five hours and weekly.

Do you need to know how to program to use them?

Not to start with: their web versions and desktop applications allow you to describe a task in French and review the result without opening a terminal. But reviewing and validating what the agent produces requires a foundation, especially before a production deployment. That's what our team is working on. Code Party, practical workshop on Claude Code and Codexopen to developers as well as business teams.

Can both be used on the same project?

Yes. Claude Code can read the AGENTS.md file used by Codex, which allows for the sharing of the same instructions. Some teams assign code review to one person and writing to the other.

Is my code being used to train the models?

On the team and enterprise plans from both publishers (Claude Team and Enterprise, ChatGPT Business and Enterprise), training is not enabled by default. On individual plans, training can be disabled in the settings.

Sources

Back to top
All NextStart.AI offersEight consulting missions, seven pillars, around twenty formats, eighteen professions, five tools
Around thirty major organizations were supported.Large groups, public agencies and networks: from acculturation to production

Insurance and social protection

Public sector and research

Consumption and retail

The NextStart.AI collectiveConsultants, trainers and industry experts: more than 5 350 trained professionals since 2023
All free resourcesDiagnostics, Finders, prompt library, kits by profession, by tool, and for managing an AI program
The NextStart.AI blogGuides, prices and comparisons of Copilot, Claude, ChatGPT, Gemini and Mistral, and field analyses
Let's talk about your AI projectResponse within 24 business hours
AI agents in businessUnderstanding, choosing the tool, training the teams, deploying
Delegate entire tasksClaude Cowork, Copilot Cowork, ChatGPT Work, Vibe Work