# aisix vs bifrost

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) .

Requested cell: openai → openai. Metric: added_latency_p99_us.

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 (B ÷ A): 6.074712643678161. No statistical significance is asserted.

[Comparison JSON](https://onthebench.ai/api/v1/compare?a=aisix&b=bifrost&ingress=openai&egress=openai&metric=added_latency_p99_us)  ·  [All AISIX (api7) evidence](https://onthebench.ai/gateways/aisix)  ·  [All Bifrost evidence](https://onthebench.ai/gateways/bifrost)

## aisix

Build ghcr.io/api7/aisix:1.9.0@sha256:dbe230bdaa4f353f7bf99d5437ab11f8b67435afabb217cf371c441ede43270a. Measured 2026-11-10T17:39:23Z.  [Run evidence](https://onthebench.ai/gateways/runs/run-aisix-ef0cff28391e0017f17c4b7c01e0171c62359468b787de48402bc3408df76915)

| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
| --- | --- | --- | --- | --- |
| openai → openai | added_latency_p50_us | 146 | valid; gateway_c1_samples=35048; direct_c1_samples=262627 | — |
| openai → openai | added_latency_p99_us | 174 | valid; gateway_c1_samples=35048; direct_c1_samples=262627 | — |
| openai → openai | gateway_c1_p99_us | 202 | valid; gateway_c1_samples=35048 | — |
| openai → openai | direct_c1_p99_us | 28 | valid; direct_c1_samples=262627 | — |
| openai → openai | cpu_us_per_request | 152.64101169979259 | valid | — |
| openai → openai | rps_per_cpu_second | 6551.319261213721 | valid | — |
| openai → openai | cost_window_conc | 8 | valid | — |
| openai → openai | cost_core_utilisation | 0.9445269209542334 | valid | — |
| openai → openai | cost_window_ok | 148977 | valid | — |
| openai → openai | cost_window_rps | 24826 | valid | — |
| openai → openai | cost_threads | 16 | valid | — |
| openai → openai | cost_nonvol_ctxt_per_request | 0 | valid | — |
| openai → openai | cost_majflt | 0 | valid | — |
| openai → openai | added_ttft_p50_us | 277 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_ttft_p99_us | 366 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_gap_p50_us | 2 | valid; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | added_gap_p99_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | streams_sustained_fps | 30259.205544499786 | valid | — |
| openai → openai | streams_sustained | 645 | valid | — |
| openai → openai | idle_rss_mib | 34.2890625 | valid | — |
| openai → openai | steady_state_rss_mib | 68.62890625 | valid | — |
| openai → openai | recovered_rss_mib | 52.296875 | valid | — |
| openai → openai | peak_rss_mib | 70.42578125 | valid | — |
| openai → openai | peak_rss_hwm_mib | 70.28515625 | valid | — |
| openai → openai | time_to_plateau_s | not_measured | not_measured | — |
| openai → openai | growth_rate_mib_per_min | 0.37583951307297037 | valid | — |
| openai → openai | load_s | 300 | valid | — |
| openai → openai | shape | 0 | valid | — |
| openai → openai | idle_shape | -1 | valid | — |
| openai → openai | idle_static | 0 | valid | — |
| openai → openai | idle_growth_rate_mib_per_min | -0.8534572049737088 | valid | — |
| openai → openai | throughput_rps | 28888 req/s | concurrency 16; samples 173346 | 1 |
| openai → openai | throughput_rps | 31374 req/s | concurrency 64; samples 188254 | 5 |
| openai → openai | throughput_rps | 32092 req/s | concurrency 128; samples 192583 | 10 |
| openai → openai | throughput_rps | 32092 req/s | concurrency 128; samples 192583 | 50 |
| openai → openai | throughput_rps | 32092 req/s | concurrency 128; samples 192583 | 100 |
| openai → openai | throughput_rps | 32092 req/s | concurrency 128; samples 192583 | unbounded |

## bifrost

Build maximhq/bifrost:v2.5.0@sha256:445bc49544bc64971b63581a93c6ca5716a03ccf27a58ced4c285cbafc133e78. Measured 2026-11-11T03:17:59Z.  [Run evidence](https://onthebench.ai/gateways/runs/run-bifrost-c253d4668350f1793f587661b425702d5448ca78d04ec9144589514b6064ebd7)

| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
| --- | --- | --- | --- | --- |
| openai → openai | added_latency_p50_us | 658 | valid; gateway_c1_samples=8543; direct_c1_samples=269310 | — |
| openai → openai | added_latency_p99_us | 1057 | valid; gateway_c1_samples=8543; direct_c1_samples=269310 | — |
| openai → openai | gateway_c1_p99_us | 1084 | valid; gateway_c1_samples=8543 | — |
| openai → openai | direct_c1_p99_us | 27 | valid; direct_c1_samples=269310 | — |
| openai → openai | cpu_us_per_request | 865.1196519216824 | valid | — |
| openai → openai | rps_per_cpu_second | 1155.9094719195307 | valid | — |
| openai → openai | cost_window_conc | 8 | valid | — |
| openai → openai | cost_core_utilisation | 0.9909277682234482 | valid | — |
| openai → openai | cost_window_ok | 27580 | valid | — |
| openai → openai | cost_window_rps | 4595 | valid | — |
| openai → openai | cost_threads | 13 | valid | — |
| openai → openai | cost_nonvol_ctxt_per_request | 0.02708484408992023 | valid | — |
| openai → openai | cost_majflt | 0 | valid | — |
| openai → openai | added_ttft_p50_us | 932 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_ttft_p99_us | 1417 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_gap_p50_us | 3 | valid; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | added_gap_p99_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | streams_sustained_fps | 25840.89500725109 | valid | — |
| openai → openai | streams_sustained | 580 | valid | — |
| openai → openai | idle_rss_mib | 160.2734375 | valid | — |
| openai → openai | steady_state_rss_mib | 1049.515625 | valid | — |
| openai → openai | recovered_rss_mib | 1256.6328125 | valid | — |
| openai → openai | peak_rss_mib | 1257.0390625 | valid | — |
| openai → openai | peak_rss_hwm_mib | 1137.43359375 | valid | — |
| openai → openai | time_to_plateau_s | not_measured | not_measured | — |
| openai → openai | growth_rate_mib_per_min | 56.82213581346736 | valid | — |
| openai → openai | load_s | 300 | valid | — |
| openai → openai | shape | 1 | valid | — |
| openai → openai | idle_shape | not_measured | not_measured | — |
| openai → openai | idle_static | 1 | valid | — |
| openai → openai | idle_growth_rate_mib_per_min | 0.4802766176196459 | valid | — |
| openai → openai | throughput_rps | bound_not_met req/s | 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 |
| openai → openai | throughput_rps | 4346 req/s | concurrency 4; samples 26081 | 5 |
| openai → openai | throughput_rps | 4555 req/s | concurrency 8; samples 27340 | 10 |
| openai → openai | throughput_rps | 4624 req/s | concurrency 16; samples 27748 | 50 |
| openai → openai | throughput_rps | 4624 req/s | concurrency 16; samples 27748 | 100 |
| openai → openai | throughput_rps | 4624 req/s | concurrency 16; samples 27748 | unbounded |
