Anthropic's managed pull request reviewer for GitHub that uses multiple agents and posts severity-tagged inline comments. It is a research preview for Team and Enterprise plans, billed by token usage.
Claude Code Review is a managed service from Anthropic that reviews GitHub pull requests. Once an Owner enables it for an organization, reviews run when a pull request opens, on every push, or when someone comments a review request. Several agents examine the diff and the surrounding code in parallel on Anthropic infrastructure, a verification step checks each candidate against actual code behavior to filter false positives, and the results are ranked by severity.
Findings appear as inline comments on the affected lines, with a summary in the review body and a check run listing every finding. Each is tagged as Important, Nit or Pre-existing, and they do not approve or block the pull request. Teams can steer the reviewer by adding a CLAUDE.md or REVIEW.md file to the repository. Reviews average about 20 minutes, and users can react to comments to rate them.
The service is in research preview and is available for Team and Enterprise subscriptions. It is not available for organizations with Zero Data Retention enabled or with the HIPAA configuration applied, and it is not covered under Anthropic's business associate agreement. Users on other plans can run a diff review locally with a command. For running in your own CI, Anthropic points to separate GitHub Actions and GitLab CI/CD options, and a self-hosted GitHub Enterprise Server page exists.
Billing is by token usage, separate from plan limits, through usage credits. The documentation says a review averages $15 to $25, scaling with pull request size, codebase complexity and the number of issues that need verification. Choosing a review on every push multiplies cost by the number of pushes, and Owners can set a monthly spend cap.
No. It is billed by token usage through usage credits, averaging $15 to $25 per review, and requires a Team or Enterprise subscription. A local diff review command exists on other plans.
It is a research preview available for Team and Enterprise subscriptions. It is unavailable with Zero Data Retention or the HIPAA configuration.
No. Findings are tagged by severity but do not approve or block a pull request, and a failed run never blocks it either.
Website: https://code.claude.com/docs/en/code-review
Company: Anthropic
Anthropic's managed PR reviewer: multi-agent, verification step, severity-tagged comments. Usage-billed at roughly $15-25 per review on top of a Team or Enterprise plan; GitHub only, research preview, not for ZDR or HIPAA orgs.
| Pricing model | Usage-based |
|---|---|
| Free tier | No free plan |
| Starting price | Not verified |
| Data residency | Not verified |
| Compliance (as stated by vendor) | Not verified |
| Integrations | GitHub |
| Public API | Not verified |
| Self-hostable | Not verified |
| Official site | Online (auto-checked 2026-10-12) |
| Can a general AI assistant replace it? | A general LLM can review code you paste, but this runs on GitHub automatically with repo context. A local /code-review command offers a lighter option on other plans. |
| Last verified | 2026-10-10 by editor |
Open Interpreter is an open-source terminal agent, forked from Codex, that reads and edits files and runs commands inside an OS-level sandbox with approvals. It is free under Apache 2.0 and works with local models through Ollama or LM Studio.
Together AI is a cloud platform for running open models through a per-token serverless API, plus dedicated endpoints, GPU clusters and fine-tuning. Hosted GLM-5.3-Flash, for example, is listed at $0.15 input and $0.50 output per million tokens.
Kimi is Moonshot AI's assistant and model family, offered as the kimi.com agent workspace and as a pay-as-you-go API. The Kimi K2.7 Code model is listed at $0.95 input and $4.00 output per million tokens.
Z.ai offers the GLM model family through a chat app and a developer API billed per million tokens. GLM-5.3-Flash is listed at $0.15 input and $0.50 output, and the API is compatible with the OpenAI SDK.
The Gemini API and Google AI Studio let developers build with Google's Gemini models for text, code, images, video and speech. A free tier covers some models; paid use is billed per million tokens, such as $0.30 in and $2.50 out on Gemini 3.5 Flash-Lite.
The Claude API is Anthropic's developer platform for building apps and agents on Claude models, billed per million tokens. Rates run from Claude Haiku 5.5 at $0.10 input and $0.50 output up to Claude Fable 5.1 at $10 and $50.
Need the outcome rather than the software?