Claude Code
Visit Claude Code →About Claude Code
Claude Code is Anthropic's agentic coding tool. It reads your codebase, edits files, runs commands and can carry a task from a plain-language request through to a working change, rather than just suggesting completions in an editor.
The current release is CLI v2.1.x (v2.1.185-v2.1.193, late June 2026). Since May 28, 2026 the default model has been Claude Opus 4.8, Anthropic's strongest computer-use and browser-agent model, which runs at high effort by default (you can push it further with /effort xhigh). Fast mode now also runs on Opus 4.8 at $10/$50 per million tokens, roughly 3x cheaper than the models it replaced.
Beyond the terminal, Claude Code spans web and mobile. Recent additions include 'dynamic workflows' that orchestrate dozens to hundreds of subagents, expanded Auto mode (now on the Pro plan and on Bedrock, Google Cloud and Microsoft Foundry), computer use in the CLI, /ultrareview cloud bug-hunting, Artifacts (beta), scheduled cloud agents (Routines), native Windows support without Git Bash, /code-review and background subagents.
Pricing: the Free tier ($0) does not include Claude Code. It is bundled into Pro ($17/mo annual or $20/mo monthly), Max 5x (from $100/mo), Max 20x ($200/mo), Team Premium ($100/seat/mo annual, $125 monthly, 5-seat minimum) and Enterprise (seat plus API-rate usage from $20/seat). Team Standard is $20/seat/mo annual ($25 monthly). API access is priced separately at an intro $2/$10 per million tokens through Aug 31, 2026, then $3/$15; Opus 4.8 fast mode is $10/$50.
Limitations are worth knowing. There is no free way to use it, usage caps still apply even on paid plans (Anthropic doubled limits on May 6, 2026 and added pay-as-you-go overage with a spend cap), and API usage can get expensive on large agentic runs. High-effort agent runs can also be slow and consume tokens quickly.
It suits professional developers and teams who want an agent that actually edits and ships code, especially those already on a Claude Pro, Max or Team plan who want coding included without a separate API bill.
- Full agentic workflow: reads, edits and runs code, not just autocomplete
- Default Claude Opus 4.8 is a top-tier model for coding and computer use
- Now bundled into Pro at $17-20/mo, a much lower entry point than Max-only
- Runs across terminal, web and mobile with cloud agents and scheduled Routines
- Fast mode on Opus 4.8 is roughly 3x cheaper than the models it replaced
- Not available on the Free tier at all
- Usage caps apply even on paid plans; heavy use can hit limits
- API pricing rises to $3/$15 per MTok after the Aug 31, 2026 intro window
- High-effort agent runs can be slow and burn through tokens
- Deep feature set (subagents, workflows, computer use) has a learning curve
Choose Claude Code if…
- You want an agent that edits and ships real code, not just suggestions
- You already pay for Claude Pro, Max or Team and want coding included
- You need cloud agents, scheduled Routines or multi-subagent workflows
- You work across terminal, web and mobile and want one consistent tool
Leave a Review
Reviews are published after moderation. We don't share your email.