# Kong benchmark summary

Overview ·  [History](https://onthebench.ai/gateways/kong/history)  ·  [Evidence](https://onthebench.ai/gateways/kong/evidence)

Operated by the Busbar team; Busbar is also an entrant. Gateway overhead against a local mock is not end-to-end model latency.  [Methodology and limitations](https://onthebench.ai/gateways/method) .

Selected pair: OpenAI → OpenAI. Other protocol pairs are available through paginated measurements. This summary is not a universal product ranking.

[Compact JSON](https://onthebench.ai/api/v1/summary?gateway=kong)  ·  [Paginated measurements](https://onthebench.ai/api/v1/measurements?gateway=kong&limit=10)  ·  [Markdown](https://onthebench.ai/gateways/kong.md)  ·  [Gateway CSV](https://onthebench.ai/gateways/data.csv?gateway=kong)

| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
| --- | --- | --- | --- | --- |
| openai → openai | added_latency_p50_us | 213 | valid; gateway_c1_samples=23861; direct_c1_samples=246038 | — |
| openai → openai | added_latency_p99_us | 410 | valid; gateway_c1_samples=23861; direct_c1_samples=246038 | — |
| openai → openai | added_ttft_p99_us | 106433 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |

**Build**: kong:3.9.4@sha256:2d572848be6fc58b73ba75edc84f028837bb7be998b3a8b8117fdb44a6892220

**Measured**: 2026-11-10T17:39:46Z

**Published**: 2026-11-14T11:09:23.855Z

**Age**: 3 days old at collection generation

[Immutable run and definitions](https://onthebench.ai/gateways/runs/run-kong-d4b6d413ea59fd281dacf70be5988600ace51a15e8665c6c7dedcc87dd2cd2fb)  ·  [Raw evidence (large download)](https://onthebench.ai/api/v1/runs/run-kong-d4b6d413ea59fd281dacf70be5988600ace51a15e8665c6c7dedcc87dd2cd2fb/raw.json)

[Complete evidence: all protocol pairs, configuration and history (large page)](https://onthebench.ai/gateways/kong/evidence)  ·  [Paginated historical runs](https://onthebench.ai/api/v1/runs?family=kong)  ·  [Data & API guidance](https://onthebench.ai/gateways/data)
