Claude Code
Anthropic's coding agent, running in the terminal, IDEs, Slack, the web and mobile, with parallel subagents and scheduled routines.
Updated 2026-08-27
Yes, within limits. Claude Code runs a free tier with paid plans above it.
Listed pricing: Included with Claude Pro $17/mo, Max 5x $100/mo, Max 20x $200/mo, Team and Enterprise plans.
Overview
Claude Code is Anthropic's coding agent. The pitch on its product page is short: "Build, debug, and ship from your terminal, IDE, Slack, web, and more." Install is a single shell line, curl -fsSL https://claude.ai/install.sh | bash, and from there it works against the repo already on disk. There is also a desktop build for macOS, Linux and Windows, a browser version at claude.ai/code, iOS and Android apps, extensions for VS Code, JetBrains, Cursor and Devin Desktop, a Slack integration, and a GitHub Actions path.
Two architectural choices set the shape of the thing. It runs locally and talks straight to the model APIs, with no backend server and no remote code index, so there is no third-party copy of the codebase to reason about during a security review. And it asks before it acts, requesting permission ahead of file edits and command execution. The features layered on top are about scale rather than autocomplete: what Anthropic calls Dynamic workflows spreads a job across "10s to 100s of parallel subagents", Agent view collects every running session in one place, Routines runs a configured job on a schedule or from an API call or an event, and Computer use lets it open apps, drive a browser and run dev tools.
My read: the interesting bet here is distribution, not capability. Every Claude plan down to the $0 tier lists Claude Code as included, which means the cost question for most developers is not "is this worth $20" but "how far does my existing subscription stretch". That is also where the documentation goes quiet. Anthropic's pricing page carries the line "Usage limits apply" and publishes no Claude Code specific quota, and it prints the same "From $100 per month" against both Max 5x and Max 20x without separating them. Budget for the plan, then find out empirically where the ceiling sits.
Is Claude Code free?
Yes, within limits. Claude Code runs a free tier with paid plans above it.
What the free tier covers: Not established for Claude Code. The $0 Free plan exists ("Free for everyone"), but its listed features do not include Claude Code; Pro is listed as "Everything in Free, plus: ... Includes Claude Code", and the Claude Code page's individual options start at Pro.
Listed pricing: Included with Claude Pro $17/mo, Max 5x $100/mo, Max 20x $200/mo, Team and Enterprise plans.
Pricing verified . That is the date the plans were last re-checked against the vendor's own pages, not today's date. Confirm on the official site before you pay.
What the free tier leaves out
Read straight off the plan list below. Vendors move features between tiers, so check the current split before you pay.
- Pro $17/mo with annual subscription discount ($200 billed up front), $20/mo billed monthly Claude Code included. The Claude Code page positions the Pro tier for short coding sprints in small codebases.
- Max 5x $100/mo Claude Code included. Listed as 5x more usage than Pro, with higher output limits, early access to advanced features and priority access at high traffic times.
- Max 20x $200/mo Claude Code included. Listed as 20x more usage than Pro; the Claude Code page positions it for power users with the most access to Claude models.
- Team $20/seat/mo billed annually ($25 monthly) standard seat, $100/seat/mo billed annually ($125 monthly) premium seat Includes Claude Code and Claude Cowork. Premium seats are listed as 5x more usage than standard seats, and seat types can be mixed. For teams of 2 to 150.
- Enterprise $20/seat plus usage at API rates Seat price plus usage at API rates, with usage cost scaling with model and task. Available self-serve or sales-assisted, with spend limits, role-based access, SCIM, audit logs and a HIPAA-ready offering.
Claude Code pricing
| Plan | Price | What's included |
|---|---|---|
| Free | $0 | Listed on claude.com/pricing as "Free for everyone". The Free feature list does not name Claude Code, and Pro is described as "Everything in Free, plus: ... Includes Claude Code". |
| Pro | $17/mo with annual subscription discount ($200 billed up front), $20/mo billed monthly | Claude Code included. The Claude Code page positions the Pro tier for short coding sprints in small codebases. |
| Max 5x | $100/mo | Claude Code included. Listed as 5x more usage than Pro, with higher output limits, early access to advanced features and priority access at high traffic times. |
| Max 20x | $200/mo | Claude Code included. Listed as 20x more usage than Pro; the Claude Code page positions it for power users with the most access to Claude models. |
| Team | $20/seat/mo billed annually ($25 monthly) standard seat, $100/seat/mo billed annually ($125 monthly) premium seat | Includes Claude Code and Claude Cowork. Premium seats are listed as 5x more usage than standard seats, and seat types can be mixed. For teams of 2 to 150. |
| Enterprise | $20/seat plus usage at API rates | Seat price plus usage at API rates, with usage cost scaling with model and task. Available self-serve or sales-assisted, with spend limits, role-based access, SCIM, audit logs and a HIPAA-ready offering. |
Listed on claude.com/pricing as "Free for everyone". The Free feature list does not name Claude Code, and Pro is described as "Everything in Free, plus: ... Includes Claude Code".
Claude Code included. The Claude Code page positions the Pro tier for short coding sprints in small codebases.
Claude Code included. Listed as 5x more usage than Pro, with higher output limits, early access to advanced features and priority access at high traffic times.
Claude Code included. Listed as 20x more usage than Pro; the Claude Code page positions it for power users with the most access to Claude models.
Includes Claude Code and Claude Cowork. Premium seats are listed as 5x more usage than standard seats, and seat types can be mixed. For teams of 2 to 150.
Seat price plus usage at API rates, with usage cost scaling with model and task. Available self-serve or sales-assisted, with spend limits, role-based access, SCIM, audit logs and a HIPAA-ready offering.
Pricing verified . That is the date the plans were last re-checked against the vendor's own pages, not today's date. Confirm on the official site before you pay.
Is Claude Code worth it?
Worth it for Developers who want an agent that works inside an existing repo and toolchain rather than in a hosted editor, and who already pay for a Claude plan.
You can test that on the free tier before paying anything. The recorded trade-offs are listed below, and any one of them can settle the question on its own.
The 9.3/10 AI Score is an editorial read of published capability, price and shipping pace. Nobody here has hands-on hours with Claude Code. How we verify.
Worth it if
The strengths recorded against this entry.
- Included on every Claude plan including the free one, so trying it costs nothing beyond an account
- No backend server and no remote code index, which removes a whole category of question from a security review
- Permission prompts before file edits and command execution keep the agent's blast radius under the developer's control
- Same entitlement covers terminal, IDE, Slack, web and mobile rather than charging per surface
- Routines turn the agent into a scheduled or event-driven job, not just an interactive session
Not worth it if
Any one of these blocks your use case.
- Anthropic publishes no Claude Code specific usage limit, only the line "Usage limits apply", so the practical ceiling is unknown until you hit it
- The pricing page shows "From $100 per month" for both Max 5x and Max 20x, which makes the step between them impossible to read from the page
- Terminal-first workflow assumes comfort with a shell and with reviewing diffs, which is a real barrier for people used to a graphical editor
- Parallel subagent fan-out consumes usage quickly, and the cost of a large run is not visible before you start it
What sets Claude Code apart
- Runs locally and talks directly to model APIs, with no backend server and no remote code index
- Asks permission before editing files or running commands, so the blast radius stays under the developer's control
- Fans work out across what Anthropic describes as 10s to 100s of parallel subagents
- Routines run the same configured job on a schedule, from an API call, or in response to an event
- One entitlement covers terminal, IDE, Slack, web and mobile instead of a per-surface licence
Key features
Runs where the code already is
Terminal install via a one-line script, plus desktop builds for macOS, Linux and Windows, a web version at claude.ai/code, iOS and Android apps, and extensions for VS Code, JetBrains, Cursor and Devin Desktop. Slack and GitHub Actions are supported surfaces too.
Dynamic workflows with parallel subagents
Anthropic describes execution "across 10s to 100s of parallel subagents", which is the difference between one assistant working a file and a fan-out across a codebase. Agent view is the companion surface: one place to manage every running Claude Code session.
Routines
Configure a job once and it can run on a schedule, from an API call, or in response to an event. This is what turns the agent from something you invoke into something that runs unattended against a repo.
Computer use
Opens applications, navigates a browser and runs local dev tools, so tasks that end outside the editor (checking a rendered page, driving a CLI that has no API) stay inside the same session.
Local execution, permission gates
Runs in the terminal and talks directly to model APIs without a backend server or a remote code index, and asks for permission before making changes to files or running commands. Both facts matter more to a security reviewer than any benchmark.
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| Claude Code | Developers who want an agent that works inside an existing repo and toolchain rather than in a hosted editor, and who already pay for a Claude plan. | Included with Claude Pro $17/mo, Max 5x $100/mo, Max 20x $200/mo, Team and Enterprise plans | 9.3/10 |
| Cursor vs Cursor → | Professional developers handling complex, multi-file refactors who want AI built into a familiar VS Code-based editor. | Free Hobby + Individual $20/mo + Teams $40/user/mo + Enterprise Custom | 9.5/10 |
| GitHub Copilot vs GitHub Copilot → | Developers who want an AI coding assistant built into their existing editor, from free-tier autocomplete to autonomous PR workflows. | Free tier + Pro $10/mo | 8.8/10 |
| Aider vs Aider → | Terminal-based developers who want an AI pair programmer that edits their local git repo directly, without adopting a new IDE. | Free (BYOK — pay your LLM provider) | 8.6/10 |
| OpenAI Codex vs OpenAI Codex → | Teams already standardised on ChatGPT who want the coding agent bundled with the seats they pay for, and who want the same agent in a terminal, an editor and a pull request. | Included with ChatGPT Free, Go, Plus, Pro, Business, Edu and Enterprise plans | 8.8/10 |
Compare head-to-head
Related reading
DeepSeek Harness: Open Agent Runtime, How to Run It
DeepSeek open-sourced an MIT-licensed agent runtime on August 13. Plugin architecture, Trajectory replay, and the npx command to run it locally.
Alibaba Bans Claude Code Over Security Concerns
Alibaba told staff to remove Anthropic's Claude Code by July 10 over security concerns. Here's what triggered the ban and what it signals.
Anthropic's SpaceX Deal: 220K GPUs for Claude
Anthropic leased SpaceX's entire Colossus 1 cluster — 220K GPUs, 300MW. Here's what changes for Claude users.
Ready to try Claude Code?
Head to the official site to start with Claude Code — pricing and plans are listed above.
Visit Claude Code