Explainer · updated Oct 10, 2026
Claude Code is Anthropic's agentic coding tool. It reads your codebase, edits files across a project and runs commands from the terminal, IDEs, a desktop app or the browser. It is included in paid Claude plans and can also be billed per token through an Anthropic Console account.
Claude Code is an agentic coding assistant from Anthropic. According to its documentation, it reads a codebase, edits files, runs commands and integrates with development tools, working across multiple files instead of one snippet at a time. You describe a task in plain language or paste an error message. Claude Code works in your local project directory and returns multi-file edits and diffs, shell command results such as test and lint runs, and written explanations of the codebase.
The terminal version is a command-line agent. After installing it, you change into a project folder and run claude to start a session, or run claude with a task in quotes to execute a single prompt. It runs on macOS, Linux, WSL and Windows. Other surfaces use the same agent: extensions for VS Code (including Cursor) and JetBrains IDEs, a desktop app with visual diff review and scheduled tasks, a browser version at claude.ai/code, and iOS and Android apps. Tasks can also start from Slack and GitHub. The web version can work on repositories you do not have locally. Repeatable steps go into Claude Code skills, shared setups ship as plugins, external tools arrive through MCP servers, and project conventions live in AGENTS.md.
There is no free tier. Claude Code is included in paid Claude subscriptions or billed per token through the API. Pro is $17 per month with the annual discount ($200 billed up front) or $20 billed monthly. Max 5x is $100 per month and Max 20x is $200 per month, with 5x and 20x the usage of Pro. Prices exclude tax. The plan table is on the Claude Code pricing page.
Team standard seats are $25 per seat per month billed monthly, or $20 billed annually; premium seats are $100 annual or $125 monthly. Enterprise has no single published price: the pricing page states US$20 per seat per month billed annually plus usage at API rates. Console use is billed by API token consumption, so costs scale with usage. Subscription plans carry usage limits.
The vendor lists building features across multiple files, fixing bugs, automating development tasks, exploring an unfamiliar codebase and running commands and tests from the terminal. In the vendor demos, a request such as adding a dark mode toggle to settings produces edits across several files. Result quality depends on how clearly the task is described, so review every diff before merging. Long jobs consume plan usage limits, and real bugs may need your confirmation along the way. The listed audience is developers and small teams for feature work, developers debugging production issues for bug fixes, and engineers with repetitive chores for automation such as writing tests, fixing lint errors and handling dependency updates. Direct comparisons: Claude Code vs Cursor, Codex vs Claude Code, Gemini CLI vs Claude Code, GitHub Copilot vs Claude Code and Windsurf vs Claude Code; the Claude Code alternatives page and the AI coding tools guide list the rest.
Claude Code fits developers who work in the terminal and teams that already use Claude subscriptions or Console. If you want an agent that edits several files and runs commands, and you have or will buy a Pro, Max, Team or Enterprise plan, it is a direct match. It is a poor fit if you need a free tool, since Free Claude users cannot use it. It also adds account management for teams, and heavy sessions can hit subscription limits. Console billing by token is harder to predict. Cursor, GitHub Copilot, Windsurf and Replit are the alternatives our profile lists.
On macOS, Linux or WSL, run curl -fsSL https://claude.ai/install.sh | bash, or install with Homebrew or WinGet. Open a new terminal and run claude --version to confirm. Then cd into your project, run claude, and log in with a Claude subscription or Console account on first use. Start with a bounded task such as a bug fix. Describe it with the error message, let Claude read files and reproduce the problem, review the proposed diff, then ask it to run the tests. Afterward, run the test suite yourself and read the full diff before committing.
Anthropic's agentic coding tool that reads your codebase, edits files and runs commands from the terminal, IDEs, desktop app or browser.
Watch out: Not included in the Free Claude plan, and usage on subscriptions is capped by plan limits.
Verified code.claude.com (opens Claude Code website in a new tab)
From $20/mo US · checked Sep 29
No. The pricing page lists Claude Code as not included on Free and included on Pro, Max 5x and Max 20x.
Pro is $17 per month with the annual discount ($200 billed up front) or $20 billed monthly, and includes Claude Code. Max starts at $100 per month for 5x the usage of Pro. Prices exclude tax.
Yes, with an Anthropic Console account, billed by API token consumption. Most surfaces need either a subscription or a Console account.
In the terminal on macOS, Linux, WSL and Windows, in VS Code, Cursor and JetBrains IDEs, in the desktop app, on the web, and on iOS and Android. Tasks can also start from Slack and GitHub.
Per the pricing page, training is opt-out on Free, Pro and Max, and off by default on Team and Enterprise. Check Anthropic's policy for current detail.
Subscription plans carry usage limits that reset on a schedule, and long jobs consume them. Max 5x and Max 20x give 5x and 20x the usage of Pro, and Console billing removes the plan cap but charges per API token.
They are different products. Claude Code is an agent that works directly in your codebase; ChatGPT is a general assistant whose coding agent is Codex. Compare the two agents side by side in our Codex vs Claude Code page.
compare>
