P1Cleanup ticker 10x frequency increase · API Performance Review
When cleanup runs every minute, all eight DB/file jobs run 10x more often and can overlap the 9m timeout, raising DB load.
LowKnown issue in the API Performance Review benchmark · caught by Muse Spark 1.3See the graded case
Muse Spark 1.3 is its best model on this benchmark; API Performance Review runs DeepSeek V4.1 Flash unless you pick another.
API Performance 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 API Performance 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). Rows not graded on every PR come last. Review times come from runs on Sep 19–24, 2026 (models) and Jan 23–Apr 7, 2026 (apps). Click a column heading to sort.
On this benchmark Muse Spark 1.3 scored higher than DeepSeek V4.1 Flash (56.0% F1 against 53.3%). Why IonWarp runs DeepSeek V4.1 Flash: in a blind-graded replay of 50 recent production reviews on 19 October 2026, run twice, it found significant issues in 3 of them, 2 of them on both runs, where GLM 5.3 Flash found none, and 4% of its findings were false to GLM's 9%. It costs more: $0.033 a review against $0.006.
Pricing
Simple pricing for your whole team.
One workspace price with seats included. Credits pool across your team. Unlimited repos on every plan.
API Performance Review is on Max: $149 a month with 10 seats and a 7-day trial.
P1Cleanup ticker 10x frequency increase · API Performance Review
When cleanup runs every minute, all eight DB/file jobs run 10x more often and can overlap the 9m timeout, raising DB load.