AI
aixjo

Claude Code

ActivePaid onlyLast updated 5 October 2026 · Robert Levandovsky

Verdict

Evidence: Editorial assessment

Claude Code is Anthropic's coding agent for developers who are comfortable in a terminal. It reads a codebase, edits files, runs commands and handles git, and it is included in every paid Claude plan rather than sold separately. The trade-off is cost predictability: it draws on the same usage limits as chat, so sustained agent work usually needs Max.

Quick facts

Claude Code
MakerAnthropic
CategoryAI Coding Assistants
Pricing modelPaid only
StatusActive
Official siteclaude.com
Data last checked5 October 2026

Key facts and sources

Verified = read on the provider's own page. Reported = third-party source, not yet confirmed. Claimed by provider = vendor claim, not tested by aixjo.
ClaimDetailEvidenceSource
What it is and where it runsAnthropic describes Claude Code as an agentic coding tool that lives in your terminal, understands your codebase and handles routine tasks and git workflows through natural-language commands. It runs in the terminal, in IDEs and on GitHub (by tagging @claude). Installed via a native installer, Homebrew or WinGet; npm installation is deprecated.Verifiedanthropics/claude-code on GitHub, 5 October 2026
Plan accessClaude Code is included in all paid Claude plans and shares usage limits with the plan.VerifiedClaude pricing, 5 October 2026
Consumer and team plansFree $0; Pro $20/month or $200/year ($17/month); Max from $100/month (5x or 20x Pro usage); Team Standard seat $25/month or $20/month billed annually; Team Premium seat $125/month or $100/month billed annually; Enterprise $20/seat/month plus usage at API rates.VerifiedClaude pricing, 5 October 2026
API prices per 1M tokens (input / output)Fable 5.1 $10 / $50; Opus 5.5 $4 / $20; Sonnet 5.5 $2 / $10; Haiku 4.5 $1 / $5.VerifiedClaude pricing, 5 October 2026
Vendor benchmark and speed claimsAnthropic says Sonnet 5.5 generates output 30%+ faster than Sonnet 5, costs up to 30% less per task and scores nearly level with Opus 5.5 on GDPval-AA v2.1. Reported scores: Terminal-Bench 4.0 70.6%; OSWorld 2.1 80.1% (partial); CursorBench 4.0 55.5%.Claimed by providerAnthropic: Introducing Claude Sonnet 5.5, 5 October 2026

Pricing

No prices are shown because we have not confirmed them on Claude Code's own pricing page. Go to Claude Code

Who should use it

  • Developers who prefer terminal and git-centred workflows
  • Multi-step refactors and repository-wide changes
  • Teams already paying for Claude seats

Who should skip it

  • You want a full graphical editor with inline autocomplete (compare Cursor or Copilot)
  • You need a fixed, published number of agent runs per month

Limitations and risks

  • Usage is shared with your Claude plan, so long agent sessions can hit plan limits.
  • An agent that runs commands needs review: check diffs and test results before merging.
  • Benchmark scores in Anthropic announcements are vendor-reported.

How it compares: Claude Code alternatives

Cursor

An AI code editor built on VS Code, with in-editor chat, multi-file agent edits and background agents.

Free plan availableChecked Oct 2026

OpenAI Codex

OpenAI's coding agent; the open-source Codex CLI runs in the terminal and is included with paid ChatGPT plans or usable with an API key.

Paid onlyChecked Oct 2026

GitHub Copilot

GitHub's AI coding assistant for code completion, chat, code review and agent tasks in major editors and on GitHub.

Free plan availableChecked Oct 2026

Gemini CLI

Google's open-source AI agent that brings Gemini models into the terminal for coding, file and shell tasks.

Open sourceChecked Oct 2026

Shipable AI

Listed as a tool that automates parts of building and shipping code.

Free trialChecked Jun 2026

Rating

Not yet rated. We show a rating only when at least four of six criteria have documented evidence. How we rate AI tools

Common questions

Is Claude Code free?

No. Claude Code is included in all paid Claude plans (Pro from $20 a month, Max from $100 a month, Team and Enterprise seats), or it can be used with API billing. It is not part of the Free plan.

Where does Claude Code run?

In your terminal, inside IDEs, and on GitHub, where you can tag @claude on issues and pull requests. Anthropic recommends its native installer, Homebrew or WinGet; npm installation is deprecated.

Claude Code or Cursor?

Choose Claude Code if you work from the terminal and want an agent that runs commands and git operations. Choose Cursor if you want an AI-first editor with autocomplete and visual diffs. Many developers use both; see our three-way comparison with OpenAI Codex.

Sources