Skip to content
IonWarpGet started
AI code review for GitHub teams

Add Code Review
to your pull requests.

Finds bugs in changed code by tracing each function to its callers.

discourse-graphite#10
FEATURE: Can edit category/host relationships for embedding
FEATURE: Can edit category/host relationships for embeddingdiscourse-graphite #10
IonWarp caught it Qodo, Greptile and CodeRabbit missed it
IonWarpbotcommented

Category and embeddable_host fabricator contents are swapped between files - category_fabricator.rb defines embeddable_host and embeddable_host_fabricator.rb defines category fabricators · Code Review

HighKnown issue in the Code Review benchmark · caught by DeepSeek V4.1 FlashSee the graded case

IonWarp caught 47 issues Qodo, Greptile, Cursor Bugbot or CodeRabbit missed

Real IonWarp comments on open-source pull requests, graded against the benchmark's answer key.

Missed byQodo 18Greptile 25Cursor Bugbot 21CodeRabbit 20

4 of 47 · See the benchmark

FEATURE: Can edit category/host relationships for embeddingdiscourse-graphite #10
IonWarp caught it Qodo, Greptile and CodeRabbit missed it
IonWarpbotcommented

Host lookup fails for uppercase hostnames because the input host is not lowercased before comparing with lower(host) in the query · Code Review

MediumKnown issue in the Code Review benchmark · caught by Muse Spark 1.3See the graded case

Muse Spark 1.3 is its best model on this benchmark; Code Review runs DeepSeek V4.1 Flash unless you pick another.

Code Review on the benchmark

IonWarp's models and the review apps, graded on the same open-source pull requests.

Blue: DeepSeek V4.1 Flash, the model IonWarp runs for Code Review. Yellow: Muse Spark 1.3, the model a failed review retries on. Sorted by Reviewer Score (F1 counts 3×, time and cost 1× each). Review times come from runs on Sep 8–Oct 6, 2026 (models) and Jan 23–Apr 7, 2026 (apps). Click a column heading to sort.
PRs
IonWarp Code · Muse Spark 1.3
Qodo v2
IonWarp Code · DeepSeek V4 Pro
IonWarp Code · DeepSeek V4.1 Flash
IonWarp Code · GLM 5.3 Flash
Greptile v4.1
Cursor Bugbot
IonWarp Code · GPT 5.6 Luna Pro
CodeRabbit

On this benchmark Muse Spark 1.3 scored higher than DeepSeek V4.1 Flash (56.6% F1 against 49.2%). Why IonWarp runs DeepSeek V4.1 Flash: on our own repositories from 1 to 21 September 2026 it filed slightly more P0 and P1 findings per 100 reviews than DeepSeek V4 Pro (14.8 on 549 reviews, against 13.5 on 104) for about a quarter of the cost ($0.034 a review against $0.140).

Pricing

Simple pricing for your whole team.

One workspace price with seats included. Credits pool across your team. Unlimited repos on every plan.

Code Review is on every plan, including Starter.

Starter

$0 /mo

Try AI PR review.

  • 2 reviewers
    • Code Review
    • Security Review
  • 3 seats included
  • 15,000 credits to start, then 5,000/mo
  • About 70 reviews to start, then about 25 a month
  • Unlimited repos
Get Started

Max

$149 /mo

Scale AI PR review.

  • +9 reviewers
    • UX Review
    • API Performance
    • Analytics Review
    • SEO Review
    • Changelog
    • CI/CD Performance
    • Plan Review
    • Repeat-Failure Learnings
    • SOC 2 Review
  • 10 seats included
  • +75,000 credits/mo
  • About 360 reviews a month
  • +$29/mo per added seat
  • Unlimited repos
  • Priority support
Choose Max
Enterprise

Custom reviewers + credits · GitHub Enterprise · SSO/SAML + audit logs · Custom security review + SLA

Contact us
About Code Review
FAQ

Frequently asked questions

What does IonWarp Code Review check?

It looks for bugs in the code a pull request changes: a swallowed write failure, a caller that no longer matches a changed signature, a race on money or quota, a value put into a URL or query without encoding. It traces each changed function to its callers and through its real scenarios. It does not comment on naming, dead imports or magic numbers.

Does Code Review run on every pull request?

Yes, once the GitHub App is on the repository, and again when a new push changes code. Drafts wait until they are ready for review, and Dependabot and Renovate pull requests are skipped, unless you change those settings. Specialist reviewers join when the diff calls for them.

What does a review look like on the pull request?

IonWarp posts one comment on the pull request. Each finding has a severity of P0, P1 or P2, the file and line it points to and a suggested fix, and by default a P0 sets the GitHub check to Action required. IonWarp never approves a pull request and never writes to your repository, so the merge stays with your team.

How accurate is Code Review?

On our code review benchmark, 50 open-source pull requests with 158 known issues, DeepSeek V4.1 Flash found 77 and posted 78 findings that matched none, an F1 of 49.2%. On the same pull requests the apps scored Qodo 58.5%, Cursor Bugbot 51.4%, Greptile 51.1% and CodeRabbit 42.2%. The table on this page lists every model and app we ran.