AI agent profile
Claude Code: facts from dated sources
Source dated
- Maker
- Not reported
- Launched
- Not reported
- Access
- Not recorded
- Our coverage
- Reported only (no first-hand tests in the MVP) — Reported only at launch.
Facts from dated sources
Each fact links to the page it comes from, with the date it applies to. Official source = a first-party page; Reported by <site> = a third-party page.
Pricing(20)
-
Free tier: $0
-
Claude Code is NOT included on Free
-
Pro: $20/month billed monthly
-
Pro: $17/month effective, $200 billed up front annually
-
Pro includes Claude Code
-
Max: from $100/month (Max 5x and Max 20x tiers)
-
Max: 5x or 20x more usage than Pro
-
Max includes $100/month (5x) to $200/month (20x) in API credits
-
Max: monthly billing only (no annual option listed)
-
Team Standard seat: $20/seat/month annual, $25/seat/month monthly
-
Team Premium seat: $100/seat/month annual, $125/seat/month monthly
-
Team includes Claude Code
-
Team: up to $500/month in pooled API credits
-
Enterprise: US$20/seat/month billed annually, 20 seat minimum, plus usage at API rates
-
Enterprise includes Claude Code
-
Annual plans available for Pro and Team; Enterprise annual only; annual designed to cost less
-
Claude Code charges by API token consumption; for subscription plans (Pro, Max, Team, Enterprise) the docs point to claude.com/pricing, whose FAQ says Claude Code is included in all paid plans.
-
Claude Max and Pro subscribers have usage included in their subscription, so the session cost figure isn’t relevant for billing purposes.
-
Usage credits let subscribers exceed plan limits
-
Anthropic-reported average enterprise Claude Code cost ~$13/developer/active day, $150-250/developer/month
Regions(11)
-
Claude Code is covered by Anthropic's supported-countries policy; only listed countries/regions are served (list runs from Albania to Zimbabwe, ~170 entries incl. US, UK, Canada, Japan, India, Brazil, Australia, and EU member states such as Germany, France, Italy, Spain, Netherlands, Poland, Ireland) (Effective Nov 12, 2026; not yet in effect.)
-
Under Anthropic's Supported Regions Policy effective 2026-11-12 (published; not yet in effect as of 2026-10-20): any country or region not listed is unsupported, including use by persons while physically located in an unsupported region, and use by entities incorporated/headquartered there or majority-owned from there. (Effective Nov 12, 2026; not yet in effect.)
-
United Arab Emirates - United Kingdom - United States of America - Uruguay - Uzbekistan (Effective Nov 12, 2026; not yet in effect.)
-
Territories and dependencies of a listed country are supported (example: Puerto Rico as a US territory) (Effective Nov 12, 2026; not yet in effect.)
-
Per the Supported Regions Policy effective 2026-11-12 (not yet in effect as of 2026-10-20): Ukraine supported except Crimea, Donetsk, Kherson, Luhansk, Zaporizhzhia. (Effective Nov 12, 2026; not yet in effect.)
-
macOS 13.0+, Windows 10 1809+ or Windows Server 2019+, Ubuntu 20.04+, Debian 10+, Alpine Linux 3.19+; 4 GB+ RAM; x64 or ARM64
-
Bash, Zsh, PowerShell, CMD (native Windows or WSL 1/2; Linux package installs via apt, dnf, apk)
-
Install location must be in an Anthropic supported country
-
Graphical Desktop app available (terminal-free use), distributed for macOS, Windows, and Linux
-
VS Code extension and JetBrains plugin exist alongside CLI and Desktop app
-
Requires a paid/login account tier: Pro, Max, Team, Enterprise, or Console
Actions(11)
-
Claude Code has access to a set of built-in tools that help it understand and modify your codebase.
-
Can execute shell commands in the user's environment (approval required in Manual mode).
-
Custom/external tools are added by connecting MCP servers (no first-party named site integrations stated on this page).
-
Web fetch WebFetch Yes, except a built-in set of preapproved documentation domains Permanently per repository and domain
-
Fetching a URL requires approval unless the domain is on a built-in preapproved documentation list; a saved approval is permanent per repository and domain.
-
Web search requires approval; 'don't ask again' saves a permanent per-repository rule.
-
File modification requires approval; that approval lasts only until session end.
-
Deny rules prevent Claude Code from using the specified tool. Rules are evaluated in order: deny, then ask, then allow.
-
Permission rules are enforced by Claude Code, not by the model. Instructions in your prompt or `CLAUDE.md` shape what Claude tries to do, but they don’t change what Claude Code allows.
-
On Claude Code v2.1.290 or later (a minimum version, not the current build), an interactive terminal session's web-search limit refills at about 100 calls per hour.
-
Can publish an HTML/Markdown file as a private interactive page on claude.ai (requires Pro, Max, Team or Enterprise plan and /login).
Terms changes(9)
-
The Usage Policy explicitly covers Claude Code users
-
Agent builders/deployers are responsible for actions their agents take through tools, browsers or connected systems
-
Prohibits bypassing authentication systems, endpoint protection or monitoring tools without authorization
-
Prohibits creating automated tools designed to compromise multiple systems at scale without authorization
-
Consumer-facing chatbots/agents must disclose they are AI, at minimum at the start of each chat session or in the product interface
-
v2.1.304 (October 19, 2026) adds /auto-mode-setup, a guided setup that teaches auto mode about the user's environment; also /claude-api managed-agents-secure
-
Changelog entry: Removed the “(research preview)” label from the `/fast` dialog title on Opus 5.5
-
Changelog entry: Added `CLAUDE_CODE_AUTO_MODE_MODEL` to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode
-
v2.1.302 warns standalone Claude Design (claude.ai/design) closes December 14, 2026
Compare Claude Code
Frequently asked
What do the pricing pages say about Claude Code? (1)
Free tier: $0
What do the pricing pages say about Claude Code? (2)
Claude Code is NOT included on Free
What do the pricing pages say about Claude Code? (3)
Pro: $20/month billed monthly
Has Claude Code been tested first-hand by aiagentcomparisons.com?
Reported only (no first-hand tests in the MVP). Reported only at launch.