AISIX (api7) history

Aug 2026 → Nov 2026

openai → openai cell. The engine changed between these runs (f3adbb1 → d240bad), so differences can include instrument changes, not only gateway changes. Changes within ±5% show as roughly unchanged (—); this is a display tolerance, not a statistical margin.

ReadingAug 2026Nov 2026ChangeRank Aug 2026 → Nov 2026
Added latency p50 (µs)153 µs146 µs— -4.6%2 of 14 → 2 of 15
Added latency p99 (µs)170 µs174 µs— +2.4%2 of 14 → 2 of 15
Throughput, p99 ≤ 1 ms (req/s)30,821 req/s28,888 req/s↓ -6.3%1 of 1 → 1 of 1
Throughput, p99 ≤ 5 ms (req/s)34,945 req/s31,374 req/s↓ -10.2%2 of 4 → 1 of 2
Throughput, p99 ≤ 10 ms (req/s)34,945 req/s32,092 req/s↓ -8.2%2 of 5 → 2 of 3
Throughput, p99 unbounded (req/s)34,945 req/s32,092 req/s↓ -8.2%2 of 5 → 2 of 4
CPU per request (µs)140152.6↓ +9.0%2 of 14 → 2 of 14
Idle RSS (MiB)99.97 MiB34.29 MiB↑ -65.7%— → —
Peak RSS (MiB)133.4 MiB70.43 MiB↑ -47.2%— → —

Runs

2 published runs · Added latency p99 (µs), openai → openai · values describe the recorded local-mock configuration; a missing reading is never zero. Hover a trend for its comparability details.

Added latency p99 (µs), openai → openai
MeasuredBuildEngineResultTrendField placementEvidence
ghcr.io/api7/aisix:1.9.0d240bad174 µsEngine changed2 of 15 Current fieldRun evidence
target/release/aisixf3adbb1170 µsFirst run2 of 14 Aug 2026 fieldRun evidence
Compare two runs across every recorded metric

History JSON · All gateways