Portkey 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.
| Reading | Aug 2026 | Nov 2026 | Change | Rank Aug 2026 → Nov 2026 |
|---|---|---|---|---|
| Added latency p50 (µs) | 1,177 µs | 1,196 µs | — +1.6% | 10 of 14 → 11 of 15 |
| Added latency p99 (µs) | 3,720 µs | 3,902 µs | — +4.9% | 10 of 14 → 11 of 15 |
| Throughput, p99 ≤ 5 ms (req/s) | 855 req/s | 831 req/s | — -2.8% | 2 of 2 → 1 of 1 |
| Throughput, p99 ≤ 10 ms (req/s) | 855 req/s | 835 req/s | — -2.3% | 1 of 1 → 1 of 1 |
| Throughput, p99 unbounded (req/s) | 855 req/s | 836 req/s | — -2.2% | 1 of 1 → 1 of 2 |
| CPU per request (µs) | 1,486.1 | 1,528.4 | — +2.8% | 11 of 14 → 12 of 14 |
| Idle RSS (MiB) | 123.8 MiB | 125.1 MiB | — +1.0% | — → — |
| Peak RSS (MiB) | 248.8 MiB | 250 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.
| Measured | Build | Engine | Result | Trend | Field placement | Evidence |
|---|---|---|---|---|---|---|
| portkeyai/gateway:1.15.2 | d240bad | 3,902 µs | Engine changed | 11 of 15 Current field | Run evidence | |
| portkeyai/gateway:1.15.2 | f3adbb1 | 3,720 µs | First run | 10 of 14 Aug 2026 field | Run evidence |