Claude Code is Anthropic's agentic coding tool: it runs in your terminal (plus IDE, desktop and web surfaces), reads your codebase, edits files, runs commands and iterates until a task is done. It is included in paid Claude plans starting with Pro at $20/month.
What is Claude Code?
Claude Code takes a task in plain language, explores the repository, proposes a plan, edits multiple files and runs your tests or build, then loops on failures. Because it lives in the terminal it works next to any editor and fits naturally with git, scripts and CI.
It is powered only by Anthropic's Claude models. Usage on Pro, Max and Team plans shares one pool with Claude chat; heavy users can switch to pay-as-you-go API billing through the Claude Console. It supports MCP servers, custom slash commands, hooks and subagents for extending its toolset.
Claude Code pricing
Plans as publicly listed on the official pricing page, verified 2026-10-10.
| Plan | Price | Notes |
|---|---|---|
| Pro | $20/mo ($17/mo billed annually) | Includes Claude Code |
| Max | From $100/mo | 5x or 20x Pro usage |
| Team | Per seat | For teams of 2–150 |
| Enterprise | $20/seat/mo + usage at API rates | Billed annually |
| API (pay-as-you-go) | Per token | Via a Claude Console account |
Source: https://claude.com/pricing. Prices in USD, excluding tax.
Supported models
Anthropic Claude models (Opus, Sonnet, Haiku families). Bring-your-own-key: supported.
Claude
Features at a glance
- ✓ Agent mode
- — Autocomplete
- ✓ Cloud / background agents
- ✓ PR code review
- ✓ MCP support
- — Self-host option
Interfaces: Terminal · VS Code / JetBrains · Desktop app · Web.
Strengths and weaknesses
＋ Strengths
- Top-tier results on agentic terminal benchmarks (see our benchmarks page)
- Works alongside any editor; terminal-native workflow
- Strong at multi-file changes in large, unfamiliar codebases
- Extensible with MCP servers, hooks and subagents
－ Weaknesses
- Claude models only — no OpenAI/Gemini option
- No free tier for Claude Code itself
- Usage limits on subscription plans can bite during long sessions
Who is Claude Code best for?
Developers who are comfortable in the terminal and want an agent that can own multi-step tasks end to end.
Claude Code benchmark results
Independent agent-level results we track. Scores depend on the model and harness — see how to read benchmarks.
| Benchmark | Score | Setup | Date |
|---|---|---|---|
| Terminal-Bench 4.0 | 64.8% | with Claude Opus 5.5 (max effort) | Oct 2026 · source |
| Terminal-Bench 2.1 | 89.1% | agent-level, Artificial Analysis harness | Aug 2026 · source |
Claude Code alternatives
ChatGPT subscribers who want to delegate well-scoped tasks to background agents and review PRs.
Free tier · from $20/mo · Compare →
Developers who want a Claude-Code-style terminal agent without vendor lock-in.
Free · Compare →
Git-centric developers who want precise, reviewable AI edits with any model.
Free · Compare →
Agent power users who want flexibility over models and where agents run.
Free tier · from $20/mo · Compare →
Head-to-head: Claude Code vs Codex (in-depth) · Claude Code vs Cursor (in-depth) · Claude Code vs OpenAI Codex · Claude Code vs OpenCode · Claude Code vs Aider · Claude Code vs Amp