Engineering teams on Claude Team or Enterprise get thorough PR reviews, but at $15 to $25 a review it isn't cheap.

Kenning's take

What it does

Code Review analyses GitHub pull requests with several specialised agents that look for logic errors, security holes, broken edge cases and regressions in the context of the whole codebase. Findings are checked, ranked by severity and posted as inline comments. It is a research preview for Claude Team and Enterprise, billed by token usage at about $15 to $25 per review on average.

  • Multi-agent review of each pull request
  • Verification step to filter false positives
  • Inline comments ranked by severity
  • REVIEW.md and CLAUDE.md to tune reviews
  • Analytics on reviews and costs

Who it suits. Engineering teams on Claude Team or Enterprise who use GitHub.

Key facts

Part of
Claude
Made by
Anthropic
Based in
United States
Released
9 March 2026
How to get it
research preview for Claude Team and Enterprise; not available with Zero Data Retention or HIPAA configurations
Works on
GitHub
In the UK
Yes
API price
token-based, average $15-25 per review, billed through usage credits

Pricing

PlanPriceBilled
Team standard seat$25seat per month ($20 billed yearly)
Team premium seat$125seat per month ($100 billed yearly)
Enterprise$20 per seat plus usage at API ratesseat per month, billed yearly

source

FAQ

How much does Claude Code Review cost?

It is billed by token usage. Anthropic says a review averages $15 to $25.

Who can use Claude Code Review?

Claude Team and Enterprise customers, as a research preview. Other plans can review a diff locally with /code-review.

When did Code Review launch?

Anthropic announced it on 9 March 2026.

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.