Bifrost vs Kong
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.
Requested cell: OpenAI → OpenAI. Metric: Added latency p99 (µs).
Comparability: Comparable. Ratios require an identical protocol pair, hardware, architecture, metric definition, clean harness commit, recorded mock digest, and metric-specific workload. Missing evidence never matches missing evidence. These are observed gateway measurements against a local mock, not a claim about model latency or statistical significance.
- Load-generator binary digests were not recorded; instrument equivalence is based on the identical clean harness source commit and mock digest.
- Measurements were made at different times on independently provisioned machines.
Ratio (Kong ÷ Bifrost): 0.388. No statistical significance is asserted.
Comparison JSON · All Bifrost evidence · All Kong evidence
Bifrost
Build maximhq/bifrost:v2.5.0. Measured . Run evidence
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → OpenAI | Added latency p50 (µs) | 658 | Valid · n=8,543 gateway / 269,310 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 1,057 | Valid · n=8,543 gateway / 269,310 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 1,084 | Valid · n=8,543 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 27 | Valid · n=269,310 | — |
| OpenAI → OpenAI | CPU per request (µs) | 865.1 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 1,155.9 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.991 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 27,580 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 4,595 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 13 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0.027 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 932 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 1,417 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | 3 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 25,840.9 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 580 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 160.3 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 1,049.5 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 1,256.6 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 1,257 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 1,137.4 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 56.82 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.48 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 4,346 | concurrency 4; n=26,081 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 4,555 | concurrency 8; n=27,340 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 4,624 | concurrency 16; n=27,748 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 4,624 | concurrency 16; n=27,748 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 4,624 | concurrency 16; n=27,748 | Unbounded |
Kong
Build kong:3.9.4. Measured . Run evidence
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → OpenAI | Added latency p50 (µs) | 213 | Valid · n=23,861 gateway / 246,038 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 410 | Valid · n=23,861 gateway / 246,038 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 440 | Valid · n=23,861 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=246,038 | — |
| OpenAI → OpenAI | CPU per request (µs) | 220.7 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 4,531.3 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.787 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 85,868 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 14,309 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 5 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0.000734 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 106,009 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 106,433 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | 168,648 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 3,731.9 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 78 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 406.2 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 617.4 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 617.5 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 617.7 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 618.6 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 66 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.105 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | — | Not measured | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.241 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 13,315 | concurrency 4; n=79,905 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 19,190 | concurrency 8; n=115,157 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 21,287 | concurrency 64; n=127,725 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,171 | concurrency 128; n=133,046 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,171 | concurrency 128; n=133,046 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,171 | concurrency 128; n=133,046 | Unbounded |