Claude Code vs Codex usage limits: how they differ

By Arun Dass · Published 3 October 2026 · Updated 2 November 2026

Both tools count usage in a five-hour window plus a weekly one, on plans that have them, and both let you check it in a dashboard and a command. The differences are in who has which window, what is shared, and how you pay for more. This page compares them from each maker’s own documentation.

How do the two tools’ limits compare?

Claude Code (Anthropic)Codex (OpenAI)
WindowsPro and Max: a five-hour session limit and a weekly limit. Verified Ultra accounts: weekly only.Five-hour windows on Plus and Standard Business, and weekly limits may also apply. Pro plans currently have no five-hour limit.
What countsClaude on the web and Claude Desktop use the same allowance as Claude Code.Use varies with model and task. Cloud tasks can use more of the allowance than local messages.
Where to checkSettings > Usage on claude.ai; /usage and /status in Claude Code.The usage dashboard at chatgpt.com/codex/settings/usage; /status in the Codex CLI.
When you hit it mid-taskClaude Code can finish the step, then wait and continue on its own after the reset, if you are signed in with claude.ai.OpenAI says the agent can finish the turn it is on, subject to fair use limits.
Buying moreUsage credits, with a monthly spend limit you set.Credits, which Plus and Pro users can buy once included limits run out.
Pay-as-you-go instead of a planAn API key through the Claude Console.Sign in with an API key, billed at standard API pricing. Codex cloud needs a ChatGPT sign-in.
Fixed numbersThe pages we read give no fixed count per window.The pricing page gives estimated local messages per window by model, and says they are estimates, not fixed limits.

Plans, models and numbers change often on both sides, which is why this page leaves the estimates out. Use the dashboards for your real reset times.

What is the same?

The limit follows your sign-in, not the project or the computer. Both makers give you a place to see what is left and when it resets, and both let you pay for more instead of waiting.

Which page do you need?

What is Friday?

Friday is a team app for coding agents: Claude Code, Codex, Cursor and 13 more, working together as one team. Think of a group chat and a task board for your AI coding agents. It is free and open source (MIT) and runs on your own computer with no account: the desktop app for macOS, Windows and Linux, or one command with Node.js 22 and Git.

  • They talk: agents message each other as they work, ask questions and answer them.
  • They split the work: one agent splits a job into a task board, the others pick up tasks, each in its own copy of the repository.
  • They check each other: a finished task is checked by another agent, a different model where one is free, and then you review it.
  • Claude Code, Codex, Cursor and 13 more coding tools (16 by name, plus any ACP agent) run on their own plans and sign-ins.
  • When a tool runs out of usage mid-task, the task moves to the agent best placed to finish it.
  • Review each run’s changes line by line, with git built in.
  • No account; anonymous usage counts you can turn off; it listens on 127.0.0.1 only.

Install it with npx github:splashxmoon/friday or from GitHub; see the docs. Friday Team, the hosted version for several people in one session, is in beta for companies: join the waitlist.

What does Friday do when one tool runs out?

Your coding agents run on your own accounts, so their limits are your providers’ limits. Friday never meters them and never switches your accounts.

What it does is move the work. When a tool runs out mid-task, the task moves to another agent with a record of what the first did and changed. If no agent can take it, it waits for a reset, or for you.

See usage-limit hand-off and how an agent hand-off works.

Sources

Checked against each maker’s own documentation on 2 November 2026. These tools change often, so check the latest version.

Common questions

Do Claude Code and Codex share a limit?

No. Claude Code draws on your Claude plan and Codex on your ChatGPT plan, or on API billing if you sign in with a key. Each has its own windows and its own dashboard.

Does Friday change my Claude Code or Codex limits?

No. They come from your own accounts. Friday does not raise or meter them.

What happens when one agent runs out?

The task moves to another agent with a record of what the first did and changed. If no agent can take it, it resumes when the limit resets or waits for you.

Where do I check each tool’s usage?

For Claude Code, Settings > Usage on claude.ai or /usage in the terminal. For Codex, the usage dashboard at chatgpt.com/codex/settings/usage or /status in the CLI.

Run your next task in Friday.

Free and open source (MIT), on your own computer: the desktop app for macOS, Windows and Linux, or one command with Node.js 22.