Claude Code is Anthropic’s agentic coding tool. It reads your codebase, edits files, runs commands and works through multi-step tasks, and it runs in the terminal, in VS Code and JetBrains IDEs, in a desktop app, on the web and in Slack.
It comes with every paid Claude plan rather than being sold separately, so your coding and your chats draw from the same allowance. For heavy sessions you can switch to pay-as-you-go API usage instead.
Who it’s for
Developers who want a capable agent that works across a whole codebase, from the terminal or their IDE, and who are happy to use Claude models only. It’s especially good value if you already pay for a Claude plan, since coding is included.
What stands out
- Hooks. Run your own shell commands before or after Claude Code acts, for example formatting after every edit.
- Subagents and background agents. Several agents can work in parallel under a lead agent.
- Skills and CLAUDE.md. Package reusable workflows and project instructions; it also reads an existing
AGENTS.md. - Cloud scheduled tasks. Jobs run on Anthropic’s cloud even when your computer is off, triggered by schedules, API calls or GitHub events.
- Code review and CI. Automatic GitHub pull request review, plus GitHub Actions and GitLab CI/CD integrations.
- Work from anywhere. Continue a session from your phone with Remote Control, or tag
@Claudein Slack to turn a bug report into a pull request.
Drawbacks and things to watch
- Claude models only. You can’t switch to GPT or Gemini models, unlike Cursor, Copilot or Cline.
- Shared limits. Heavy coding uses up the same allowance as your Claude chats, and Pro, Max and Team still have a five-hour window.
- No free tier. You need at least Pro or an API account.
- Sandbox prompts changed. Since version 2.1.325, sandboxed Bash commands ask for permission by default. Set
sandbox.autoAllowBashIfSandboxed: trueto restore the old behaviour.
Privacy and security
On consumer plans (Pro, Max and Ultra), Anthropic trains on your sessions only if you allow it in your privacy settings. Anthropic doesn’t train on Team, Enterprise or API data unless the customer opts in, and keeps it for 30 days as standard. Zero data retention is available to qualified Enterprise accounts. Anthropic holds SOC 2 Type II, ISO 27001 and ISO 42001 for its commercial products, and offers a HIPAA-ready setup.
Getting started
On macOS, Linux or WSL, run curl -fsSL https://claude.ai/install.sh | bash; on Windows PowerShell, irm https://claude.ai/install.ps1 | iex. Homebrew, WinGet and npm also work. Then run claude in your project and sign in with your Claude account or an API key.
Plans and prices
| Plan | Price | What you get |
|---|---|---|
| Pro | $20/mo ($17/mo billed annually) | Claude Code included. Fable through usage credits. |
| Max | $100/mo | 5x Pro usage every 5 hours and every week. Fable up to half the weekly limit. $100/month in API credits. |
| Ultra | $200/mo | 10x Pro usage each week, no five-hour limit for verified accounts. $200/month in API credits. |
| Team | $20/seat/mo annual ($25 monthly); Premium $100 ($125) | 2 to 150 seats, Claude Code included. Premium seats get 5x standard usage and Fable. |
| Enterprise | $20/seat/mo + usage | Usage billed at API rates. SCIM, audit logs, custom retention. |
Claude Code FAQ
Is Claude Code free?
No. The free Claude plan doesn't include it. You need a paid Claude plan (Pro from $20 a month, Max, Ultra, Team or Enterprise) or an Anthropic Console account billed at API rates.
How much does Claude Code cost?
It's included in Claude plans: Pro is $20 a month ($17 billed annually), Max $100 with 5x Pro usage, and Ultra $200 with 10x Pro usage each week and no five-hour limit for verified accounts. Team seats start at $20 a month billed annually. You can also pay per use with an API key.
What are Claude Code's usage limits?
Your coding shares one allowance with Claude chat, with a five-hour limit and a weekly limit. When you hit it, you can wait for the reset, upgrade, or turn on usage credits at standard API rates.
Which model does Claude Code use?
Opus 5.5 by default on every paid plan. You can switch to Sonnet 5.5, Haiku 5.5 or Fable 5.2. Fable is included on Max and Ultra up to half the weekly limit, and on Pro through usage credits.
Does Anthropic train on my Claude Code sessions?
On Pro, Max and Ultra, only if you allow it in your privacy settings; data is kept for 5 years if you allow training and 30 days if not. Anthropic doesn't train on Team, Enterprise or API data unless the customer opts in.
Latest changes
Sources
- Claude plans & pricing
- Claude Code docs: overview
- Claude Help Center: the Ultra plan
- Claude Code changelog
- Claude Code docs: model configuration
- Claude Code docs: setup
- Claude Code docs: data usage
- Anthropic certifications
Facts last checked November 14, 2026.