Kong 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)195 µs213 µs↓ +9.2%4 of 14 → 4 of 15
Added latency p99 (µs)389 µs410 µs↓ +5.4%7 of 14 → 7 of 15
Throughput, p99 ≤ 1 ms (req/s)14,060 req/s13,315 req/s↓ -5.3%1 of 2 → 1 of 3
Throughput, p99 ≤ 5 ms (req/s)21,520 req/s19,190 req/s↓ -10.8%1 of 1 → 1 of 3
Throughput, p99 ≤ 10 ms (req/s)21,520 req/s21,287 req/s— -1.1%1 of 1 → 2 of 3
Throughput, p99 unbounded (req/s)22,418 req/s22,171 req/s— -1.1%2 of 2 → 3 of 4
CPU per request (µs)209.9220.7↓ +5.1%6 of 14 → 5 of 14
Idle RSS (MiB)403.5 MiB406.2 MiB— +0.7%— → —
Peak RSS (MiB)620.7 MiB617.7 MiB— -0.5%— → —

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
kong:3.9.4d240bad410 µsEngine changed7 of 15 Current fieldRun evidence
kong:3.9.3f3adbb1389 µsFirst run7 of 14 Aug 2026 fieldRun evidence
Compare two runs across every recorded metric

History JSON · All gateways