C

Code Review API - AI Pull Request and Diff Reviewer

Published byRicky Orndorff
9/2/2026
Agent payments

Endpoints

4

v1
3

health
1

What is the Code Review API - AI Pull Request and Diff Reviewer?

Send a diff, get structured bug/security findings: file:line, severity, fixes. Tuned code-review model. Cheaper than GPT-4 / Claude.

Code Review API - AI Pull Request and Diff Reviewer is available on the JoJ API marketplace. Subscribe with a single JoJ API key, call it through one gateway, and pay from one wallet — no separate account or contract with the provider.

Pricing & plans About this API FAQ Discussions More APIs by @ricky-orndorff OpenAPI spec MCP server

Code Review API - AI Pull Request and Diff Reviewer endpoints

  • GET/v1/models

    List available models

    Returns available models (OpenAI-compatible).

  • POST/v1/chat/completions

    Create chat completion

    Generate a response from Llama 3 70B. Fully OpenAI-compatible — use the same SDK and parameters you'd use with GPT-4o. Your data never leaves RO2 Labs infrastructure. No third-party routing. No telemetry.

  • POST/v1/review

    Review code, return structured findings

    Send a unified diff (or whole files) and get structured review findings — each with `file`, `line`, `severity`, `issue`, and `suggestion` — plus a one-line `summary`. Provide either `diff` or `files` (if both are sent, `diff` wins). Every plan is reviewed by the same review-tuned model. Your code never leaves RO2 Labs infrastructure — no third-party routing, no telemetry.

  • GET/health

    Health check

    Returns API status and uptime.

Frequently asked questions about Code Review API - AI Pull Request and Diff Reviewer

Is my code or data sent to any third party?

No. All requests are processed on dedicated Apple Silicon hardware we own and operate in Austin, TX — there's no routing through OpenAI, Anthropic, or any other third-party inference provider, and no telemetry collection. Every response includes two headers you can verify directly: - x-ro2-data-residency: on-prem-austin-tx - x-ro2-third-party-routing: none If you're sending proprietary code for review, it never leaves hardware we control.

What's the difference between /v1/review and /v1/chat/completions?

`/v1/review` is the primary endpoint — send a unified diff (or raw files) and get back **structured, machine-readable findings** (`file`, `line`, `severity`, `issue`, `suggestion`) instead of prose, built for CI pipelines and PR bots that need to parse output programmatically. `/v1/chat/completions` is a general-purpose, OpenAI-compatible inference endpoint for anything beyond code review — same request/response shape as GPT-4o, drop-in with existing OpenAI SDKs. Model access scales with plan: | Plan | Model | |---|---| | Free | `qwen2.5-coder:32b` (base) | | Basic | `crank-reviewer v5` (tuned for code review) | | Pro | `crank-reviewer v5` (tuned, priority throughput) | | Mega | `crank-reviewer v5` (tuned, dedicated B2B) |