APISIX 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)173 µs179 µs— +3.5%3 of 14 → 3 of 15
Added latency p99 (µs)343 µs340 µs— -0.9%6 of 14 → 6 of 15
Throughput, p99 ≤ 1 ms (req/s)12,490 req/s12,187 req/s— -2.4%2 of 2 → 2 of 3
Throughput, p99 ≤ 5 ms (req/s)26,260 req/s23,089 req/s↓ -12.1%1 of 2 → 1 of 2
Throughput, p99 ≤ 10 ms (req/s)29,172 req/s25,474 req/s↓ -12.7%3 of 5 → 1 of 3
Throughput, p99 unbounded (req/s)31,183 req/s26,590 req/s↓ -14.7%1 of 2 → 1 of 2
CPU per request (µs)185.1185.7— +0.3%4 of 14 → 3 of 14
Idle RSS (MiB)189.6 MiB191.2 MiB— +0.8%— → —
Peak RSS (MiB)227.1 MiB228.4 MiB— +0.6%— → —

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
apache/apisix:3.19.0-debiand240bad340 µsEngine changed6 of 15 Current fieldRun evidence
apache/apisix:3.18.0-debianf3adbb1343 µsFirst run6 of 14 Aug 2026 fieldRun evidence
Compare two runs across every recorded metric

History JSON · All gateways