AI reviewer that comments on pull requests in GitHub, GitLab, Bitbucket and Azure DevOps and from the CLI. Reviews of public repositories are free; paid plans start at $24 per developer a month on annual billing.
CodeRabbit is a service that reviews pull requests automatically. After it is installed on a repository, it posts comments on each pull request, summarises the change and can suggest one-click fixes. It supports GitHub, GitLab, Azure DevOps and Bitbucket, and the same review agent is also available from a command line tool and from the IDE. The company says more than 17,000 customers and 6 million repositories use it.
Beyond the review itself, the product adds several workflow features. Learnings let the reviewer adapt to team preferences over time, linters and static security scanners feed into the review, and Jira and Linear integrations connect issues to changes. Higher plans add Triage, custom pre-merge checks, multi-repo analysis, unit test generation, merge conflict resolution, and blast radius and architectural impact analysis. Separate usage-based products include a security scan and a cloud agent charged at $0.40 per agent minute.
Every plan includes a 14-day free trial with no credit card required. The pricing page lists Essentials at $24 per developer per month billed annually, Team at $48 and Advanced at $72, with annual billing saving 20 percent against monthly payment. Enterprise is custom and adds SSO, audit logging, a self-hosting option, an EU SaaS deployment and marketplace payment through Claude, AWS or Google Cloud. A free plan for public repositories is described in the FAQ. Review rates are capped per developer per hour, from 5 on Essentials to 12 on Enterprise.
CodeRabbit states that code is encrypted during review, that nothing is stored after the review, and that it is SOC 2 Type II audited each year, with details in a public trust center.
Reviews of public repositories are free, according to the pricing FAQ. Every paid plan also includes a 14-day free trial with no credit card required.
Essentials is $24 per developer per month billed annually, Team is $48 and Advanced is $72. Annual billing saves 20 percent, so month-to-month rates are higher.
CodeRabbit says code is encrypted during review and nothing is stored afterward. It states annual SOC 2 Type II audits, with details in its trust center.
Website: https://www.coderabbit.ai/
Company: CodeRabbit Inc.
Dedicated PR reviewer across the four main Git hosts, free for public repos. Paid plans from $24 per developer a month billed annually; per-hour review caps apply and the monthly rate was not shown.
| Pricing model | Freemium |
|---|---|
| Free tier | Yes · Free reviews for public repositories; 14-day trial of paid plans, no card. · no credit card required · 14-day trial |
| Starting price | Not verified |
| Data residency | Not verified |
| Compliance (as stated by vendor) | SOC 2 (certified) |
| Integrations | GitHub, GitLab, Bitbucket, Azure DevOps, Jira, Linear, Slack, Discord |
| Public API | Yes |
| Self-hostable | Yes |
| Official site | Online (auto-checked 2026-10-12) |
| Can a general AI assistant replace it? | A general LLM can review a pasted diff but cannot comment in the pull request or see the whole repo. CodeRabbit is needed for automatic, in-context reviews on every PR. |
| 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?