AISIX (api7) benchmark measurements
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.
Rust · recorded build: ghcr.io/api7/aisix:1.9.0. Measured: .
JSON · Markdown · CSV · Project source · Interactive dashboard
Each row below names its protocol pair. A representative dashboard cell may differ between gateways; compare an identical pair before interpreting a ranking. Unavailable metrics retain their reason; below-resolution readings are not exact zeroes.
Published measurements
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → Anthropic | Added latency p50 (µs) | 162 | Valid · n=32,039 gateway / 261,797 direct | — |
| OpenAI → Anthropic | Added latency p99 (µs) | 190 | Valid · n=32,039 gateway / 261,797 direct | — |
| OpenAI → Anthropic | Gateway p99 at concurrency 1 (µs) | 218 | Valid · n=32,039 | — |
| OpenAI → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=261,797 | — |
| OpenAI → Anthropic | CPU per request (µs) | 158.6 | Valid | — |
| OpenAI → Anthropic | Requests per CPU-second | 6,305.9 | Valid | — |
| OpenAI → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI → Anthropic | Cost window core utilisation | 0.786 | Valid | — |
| OpenAI → Anthropic | Cost window successful requests | 119,308 | Valid | — |
| OpenAI → Anthropic | Cost window throughput (req/s) | 19,882 | Valid | — |
| OpenAI → Anthropic | Cost window threads | 16 | Valid | — |
| OpenAI → Anthropic | Non-voluntary context switches per request | 0.00000838 | Valid | — |
| OpenAI → Anthropic | Cost window major page faults | 0 | Valid | — |
| OpenAI → Anthropic | Added time to first event p50 (µs) | 294 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added time to first event p99 (µs) | 500 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p50 (µs) | 9 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p99 (µs) | 19 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Streams sustained (frames/s) | 34,767.8 | Valid | — |
| OpenAI → Anthropic | Streams sustained | 775 | Valid | — |
| OpenAI → Anthropic | Idle RSS (MiB) | 34.36 | Valid | — |
| OpenAI → Anthropic | Steady-state RSS (MiB) | 67.63 | Valid | — |
| OpenAI → Anthropic | Recovered RSS (MiB) | 54.02 | Valid | — |
| OpenAI → Anthropic | Peak RSS (MiB) | 69.21 | Valid | — |
| OpenAI → Anthropic | Peak RSS high-water mark (MiB) | 68.88 | Valid | — |
| OpenAI → Anthropic | Time to plateau (s) | — | Not measured | — |
| OpenAI → Anthropic | Memory growth (MiB/min) | 0.108 | Valid | — |
| OpenAI → Anthropic | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Anthropic | Memory shape under load | 0 | Valid | — |
| OpenAI → Anthropic | Idle memory shape | — | Not measured | — |
| OpenAI → Anthropic | Idle memory static | 1 | Valid | — |
| OpenAI → Anthropic | Idle memory growth (MiB/min) | -0.687 | Valid | — |
| OpenAI → Anthropic | Throughput (req/s) | 26,114 | concurrency 16; n=156,705 | 1 ms |
| OpenAI → Anthropic | Throughput (req/s) | 28,484 | concurrency 64; n=170,915 | 5 ms |
| OpenAI → Anthropic | Throughput (req/s) | 29,206 | concurrency 128; n=175,266 | 10 ms |
| OpenAI → Anthropic | Throughput (req/s) | 29,206 | concurrency 128; n=175,266 | 50 ms |
| OpenAI → Anthropic | Throughput (req/s) | 29,206 | concurrency 128; n=175,266 | 100 ms |
| OpenAI → Anthropic | Throughput (req/s) | 29,206 | concurrency 128; n=175,266 | Unbounded |
| Bedrock → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → Anthropic | — | — | Not declared: recorded note 1 | — |
| Anthropic → Anthropic | Added latency p50 (µs) | 150 | Valid · n=34,173 gateway / 257,073 direct | — |
| Anthropic → Anthropic | Added latency p99 (µs) | 175 | Valid · n=34,173 gateway / 257,073 direct | — |
| Anthropic → Anthropic | Gateway p99 at concurrency 1 (µs) | 204 | Valid · n=34,173 | — |
| Anthropic → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=257,073 | — |
| Anthropic → Anthropic | CPU per request (µs) | 150.1 | Valid | — |
| Anthropic → Anthropic | Requests per CPU-second | 6,664.2 | Valid | — |
| Anthropic → Anthropic | Cost window concurrency | 8 | Valid | — |
| Anthropic → Anthropic | Cost window core utilisation | 0.993 | Valid | — |
| Anthropic → Anthropic | Cost window successful requests | 159,340 | Valid | — |
| Anthropic → Anthropic | Cost window throughput (req/s) | 26,553 | Valid | — |
| Anthropic → Anthropic | Cost window threads | 16 | Valid | — |
| Anthropic → Anthropic | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → Anthropic | Cost window major page faults | 0 | Valid | — |
| Anthropic → Anthropic | Added time to first event p50 (µs) | 271 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added time to first event p99 (µs) | 444 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p50 (µs) | 3 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p99 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Streams sustained (frames/s) | 32,295.2 | Valid | — |
| Anthropic → Anthropic | Streams sustained | 677 | Valid | — |
| Anthropic → Anthropic | Idle RSS (MiB) | 34.68 | Valid | — |
| Anthropic → Anthropic | Steady-state RSS (MiB) | 68.68 | Valid | — |
| Anthropic → Anthropic | Recovered RSS (MiB) | 52.76 | Valid | — |
| Anthropic → Anthropic | Peak RSS (MiB) | 70.72 | Valid | — |
| Anthropic → Anthropic | Peak RSS high-water mark (MiB) | 70.5 | Valid | — |
| Anthropic → Anthropic | Time to plateau (s) | — | Not measured | — |
| Anthropic → Anthropic | Memory growth (MiB/min) | 0.325 | Valid | — |
| Anthropic → Anthropic | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Anthropic | Memory shape under load | 0 | Valid | — |
| Anthropic → Anthropic | Idle memory shape | — | Not measured | — |
| Anthropic → Anthropic | Idle memory static | 1 | Valid | — |
| Anthropic → Anthropic | Idle memory growth (MiB/min) | -0.687 | Valid | — |
| Anthropic → Anthropic | Throughput (req/s) | 28,154 | concurrency 16; n=168,946 | 1 ms |
| Anthropic → Anthropic | Throughput (req/s) | 30,535 | concurrency 64; n=183,220 | 5 ms |
| Anthropic → Anthropic | Throughput (req/s) | 31,272 | concurrency 128; n=187,661 | 10 ms |
| Anthropic → Anthropic | Throughput (req/s) | 31,272 | concurrency 128; n=187,661 | 50 ms |
| Anthropic → Anthropic | Throughput (req/s) | 31,272 | concurrency 128; n=187,661 | 100 ms |
| Anthropic → Anthropic | Throughput (req/s) | 31,272 | concurrency 128; n=187,661 | Unbounded |
| OpenAI Responses → Anthropic | Added latency p50 (µs) | 182 | Valid · n=28,838 gateway / 259,566 direct | — |
| OpenAI Responses → Anthropic | Added latency p99 (µs) | 215 | Valid · n=28,838 gateway / 259,566 direct | — |
| OpenAI Responses → Anthropic | Gateway p99 at concurrency 1 (µs) | 244 | Valid · n=28,838 | — |
| OpenAI Responses → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=259,566 | — |
| OpenAI Responses → Anthropic | CPU per request (µs) | 181.1 | Valid | — |
| OpenAI Responses → Anthropic | Requests per CPU-second | 5,521.2 | Valid | — |
| OpenAI Responses → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Anthropic | Cost window core utilisation | 0.986 | Valid | — |
| OpenAI Responses → Anthropic | Cost window successful requests | 131,074 | Valid | — |
| OpenAI Responses → Anthropic | Cost window throughput (req/s) | 21,842 | Valid | — |
| OpenAI Responses → Anthropic | Cost window threads | 16 | Valid | — |
| OpenAI Responses → Anthropic | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → Anthropic | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → Anthropic | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → Anthropic | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → Anthropic | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → Anthropic | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → Anthropic | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → Anthropic | Streams sustained | — | Untestable | — |
| OpenAI Responses → Anthropic | Idle RSS (MiB) | 34.46 | Valid | — |
| OpenAI Responses → Anthropic | Steady-state RSS (MiB) | 65.39 | Valid | — |
| OpenAI Responses → Anthropic | Recovered RSS (MiB) | 52.29 | Valid | — |
| OpenAI Responses → Anthropic | Peak RSS (MiB) | 67.24 | Valid | — |
| OpenAI Responses → Anthropic | Peak RSS high-water mark (MiB) | 67.08 | Valid | — |
| OpenAI Responses → Anthropic | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Anthropic | Memory growth (MiB/min) | -0.113 | Valid | — |
| OpenAI Responses → Anthropic | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → Anthropic | Memory shape under load | 0 | Valid | — |
| OpenAI Responses → Anthropic | Idle memory shape | -1 | Valid | — |
| OpenAI Responses → Anthropic | Idle memory static | 0 | Valid | — |
| OpenAI Responses → Anthropic | Idle memory growth (MiB/min) | -0.832 | Valid | — |
| OpenAI Responses → Anthropic | Throughput (req/s) | 22,218 | concurrency 8; n=133,328 | 1 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 25,257 | concurrency 64; n=151,548 | 5 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 25,869 | concurrency 128; n=155,239 | 10 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 25,869 | concurrency 128; n=155,239 | 50 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 25,869 | concurrency 128; n=155,239 | 100 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 25,869 | concurrency 128; n=155,239 | Unbounded |
| Cohere → Anthropic | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI | — | — | Not declared: recorded note 1 | — |
| Bedrock → OpenAI | — | — | Not declared: recorded note 1 | — |
| Anthropic → OpenAI | Added latency p50 (µs) | 152 | Valid · n=34,038 gateway / 258,158 direct | — |
| Anthropic → OpenAI | Added latency p99 (µs) | 178 | Valid · n=34,038 gateway / 258,158 direct | — |
| Anthropic → OpenAI | Gateway p99 at concurrency 1 (µs) | 207 | Valid · n=34,038 | — |
| Anthropic → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=258,158 | — |
| Anthropic → OpenAI | CPU per request (µs) | 152.1 | Valid | — |
| Anthropic → OpenAI | Requests per CPU-second | 6,574.8 | Valid | — |
| Anthropic → OpenAI | Cost window concurrency | 8 | Valid | — |
| Anthropic → OpenAI | Cost window core utilisation | 0.756 | Valid | — |
| Anthropic → OpenAI | Cost window successful requests | 119,727 | Valid | — |
| Anthropic → OpenAI | Cost window throughput (req/s) | 19,952 | Valid | — |
| Anthropic → OpenAI | Cost window threads | 16 | Valid | — |
| Anthropic → OpenAI | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → OpenAI | Cost window major page faults | 0 | Valid | — |
| Anthropic → OpenAI | Added time to first event p50 (µs) | 275 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added time to first event p99 (µs) | 461 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p50 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p99 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Streams sustained (frames/s) | 31,294.4 | Valid | — |
| Anthropic → OpenAI | Streams sustained | 658 | Valid | — |
| Anthropic → OpenAI | Idle RSS (MiB) | 34.22 | Valid | — |
| Anthropic → OpenAI | Steady-state RSS (MiB) | 67.3 | Valid | — |
| Anthropic → OpenAI | Recovered RSS (MiB) | 51.81 | Valid | — |
| Anthropic → OpenAI | Peak RSS (MiB) | 68.92 | Valid | — |
| Anthropic → OpenAI | Peak RSS high-water mark (MiB) | 68.56 | Valid | — |
| Anthropic → OpenAI | Time to plateau (s) | — | Not measured | — |
| Anthropic → OpenAI | Memory growth (MiB/min) | -0.507 | Valid | — |
| Anthropic → OpenAI | Memory load duration (s) | 300 | Valid | — |
| Anthropic → OpenAI | Memory shape under load | 0 | Valid | — |
| Anthropic → OpenAI | Idle memory shape | -1 | Valid | — |
| Anthropic → OpenAI | Idle memory static | 0 | Valid | — |
| Anthropic → OpenAI | Idle memory growth (MiB/min) | -0.92 | Valid | — |
| Anthropic → OpenAI | Throughput (req/s) | 27,958 | concurrency 16; n=167,769 | 1 ms |
| Anthropic → OpenAI | Throughput (req/s) | 30,196 | concurrency 64; n=181,184 | 5 ms |
| Anthropic → OpenAI | Throughput (req/s) | 31,041 | concurrency 128; n=186,278 | 10 ms |
| Anthropic → OpenAI | Throughput (req/s) | 31,041 | concurrency 128; n=186,278 | 50 ms |
| Anthropic → OpenAI | Throughput (req/s) | 31,041 | concurrency 128; n=186,278 | 100 ms |
| Anthropic → OpenAI | Throughput (req/s) | 31,041 | concurrency 128; n=186,278 | Unbounded |
| Gemini → OpenAI | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI | Added latency p50 (µs) | 169 | Valid · n=30,866 gateway / 260,253 direct | — |
| OpenAI Responses → OpenAI | Added latency p99 (µs) | 199 | Valid · n=30,866 gateway / 260,253 direct | — |
| OpenAI Responses → OpenAI | Gateway p99 at concurrency 1 (µs) | 228 | Valid · n=30,866 | — |
| OpenAI Responses → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=260,253 | — |
| OpenAI Responses → OpenAI | CPU per request (µs) | 162.1 | Valid | — |
| OpenAI Responses → OpenAI | Requests per CPU-second | 6,168.3 | Valid | — |
| OpenAI Responses → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI | Cost window core utilisation | 0.785 | Valid | — |
| OpenAI Responses → OpenAI | Cost window successful requests | 116,520 | Valid | — |
| OpenAI Responses → OpenAI | Cost window throughput (req/s) | 19,417 | Valid | — |
| OpenAI Responses → OpenAI | Cost window threads | 16 | Valid | — |
| OpenAI Responses → OpenAI | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → OpenAI | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → OpenAI | Streams sustained | — | Untestable | — |
| OpenAI Responses → OpenAI | Idle RSS (MiB) | 34.47 | Valid | — |
| OpenAI Responses → OpenAI | Steady-state RSS (MiB) | 66.86 | Valid | — |
| OpenAI Responses → OpenAI | Recovered RSS (MiB) | 52.7 | Valid | — |
| OpenAI Responses → OpenAI | Peak RSS (MiB) | 68.23 | Valid | — |
| OpenAI Responses → OpenAI | Peak RSS high-water mark (MiB) | 68.01 | Valid | — |
| OpenAI Responses → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → OpenAI | Memory growth (MiB/min) | 1.24 | Valid | — |
| OpenAI Responses → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → OpenAI | Memory shape under load | 0 | Valid | — |
| OpenAI Responses → OpenAI | Idle memory shape | -1 | Valid | — |
| OpenAI Responses → OpenAI | Idle memory static | 0 | Valid | — |
| OpenAI Responses → OpenAI | Idle memory growth (MiB/min) | -0.817 | Valid | — |
| OpenAI Responses → OpenAI | Throughput (req/s) | 25,449 | concurrency 16; n=152,712 | 1 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 27,472 | concurrency 64; n=164,835 | 5 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 28,458 | concurrency 128; n=170,775 | 10 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 28,458 | concurrency 128; n=170,775 | 50 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 28,458 | concurrency 128; n=170,775 | 100 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 28,458 | concurrency 128; n=170,775 | Unbounded |
| OpenAI → OpenAI | Added latency p50 (µs) | 146 | Valid · n=35,048 gateway / 262,627 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 174 | Valid · n=35,048 gateway / 262,627 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 202 | Valid · n=35,048 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=262,627 | — |
| OpenAI → OpenAI | CPU per request (µs) | 152.6 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 6,551.3 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.945 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 148,977 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 24,826 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 16 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 277 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 366 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | 2 | 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) | 30,259.2 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 645 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 34.29 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 68.63 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 52.3 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 70.43 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 70.29 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.376 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory shape | -1 | Valid | — |
| OpenAI → OpenAI | Idle memory static | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | -0.853 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 28,888 | concurrency 16; n=173,346 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 31,374 | concurrency 64; n=188,254 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 32,092 | concurrency 128; n=192,583 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 32,092 | concurrency 128; n=192,583 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 32,092 | concurrency 128; n=192,583 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 32,092 | concurrency 128; n=192,583 | Unbounded |
| OpenAI Responses → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI → Cohere | — | — | Not declared: recorded note 1 | — |
| Bedrock → Cohere | — | — | Not declared: recorded note 1 | — |
| Gemini → Cohere | — | — | Not declared: recorded note 1 | — |
| Cohere → Cohere | — | — | Not declared: recorded note 1 | — |
| Anthropic → Cohere | — | — | Not declared: recorded note 1 | — |
| Anthropic → Gemini | Added latency p50 (µs) | 162 | Valid · n=32,091 gateway / 257,892 direct | — |
| Anthropic → Gemini | Added latency p99 (µs) | 187 | Valid · n=32,091 gateway / 257,892 direct | — |
| Anthropic → Gemini | Gateway p99 at concurrency 1 (µs) | 216 | Valid · n=32,091 | — |
| Anthropic → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=257,892 | — |
| Anthropic → Gemini | CPU per request (µs) | 163.1 | Valid | — |
| Anthropic → Gemini | Requests per CPU-second | 6,130.4 | Valid | — |
| Anthropic → Gemini | Cost window concurrency | 8 | Valid | — |
| Anthropic → Gemini | Cost window core utilisation | 0.984 | Valid | — |
| Anthropic → Gemini | Cost window successful requests | 145,168 | Valid | — |
| Anthropic → Gemini | Cost window throughput (req/s) | 24,191 | Valid | — |
| Anthropic → Gemini | Cost window threads | 16 | Valid | — |
| Anthropic → Gemini | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → Gemini | Cost window major page faults | 0 | Valid | — |
| Anthropic → Gemini | Added time to first event p50 (µs) | — | Untestable | — |
| Anthropic → Gemini | Added time to first event p99 (µs) | — | Untestable | — |
| Anthropic → Gemini | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Anthropic → Gemini | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Anthropic → Gemini | Streams sustained (frames/s) | — | Untestable | — |
| Anthropic → Gemini | Streams sustained | — | Untestable | — |
| Anthropic → Gemini | Idle RSS (MiB) | 34.72 | Valid | — |
| Anthropic → Gemini | Steady-state RSS (MiB) | 67.52 | Valid | — |
| Anthropic → Gemini | Recovered RSS (MiB) | 52.1 | Valid | — |
| Anthropic → Gemini | Peak RSS (MiB) | 69.29 | Valid | — |
| Anthropic → Gemini | Peak RSS high-water mark (MiB) | 69.11 | Valid | — |
| Anthropic → Gemini | Time to plateau (s) | — | Not measured | — |
| Anthropic → Gemini | Memory growth (MiB/min) | 0.615 | Valid | — |
| Anthropic → Gemini | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Gemini | Memory shape under load | 0 | Valid | — |
| Anthropic → Gemini | Idle memory shape | -1 | Valid | — |
| Anthropic → Gemini | Idle memory static | 0 | Valid | — |
| Anthropic → Gemini | Idle memory growth (MiB/min) | -0.757 | Valid | — |
| Anthropic → Gemini | Throughput (req/s) | 26,504 | concurrency 16; n=159,044 | 1 ms |
| Anthropic → Gemini | Throughput (req/s) | 28,918 | concurrency 64; n=173,514 | 5 ms |
| Anthropic → Gemini | Throughput (req/s) | 29,709 | concurrency 128; n=178,283 | 10 ms |
| Anthropic → Gemini | Throughput (req/s) | 29,709 | concurrency 128; n=178,283 | 50 ms |
| Anthropic → Gemini | Throughput (req/s) | 29,709 | concurrency 128; n=178,283 | 100 ms |
| Anthropic → Gemini | Throughput (req/s) | 29,709 | concurrency 128; n=178,283 | Unbounded |
| Bedrock → Gemini | — | — | Not declared: recorded note 1 | — |
| Gemini → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI → Gemini | Added latency p50 (µs) | 163 | Valid · n=31,889 gateway / 261,875 direct | — |
| OpenAI → Gemini | Added latency p99 (µs) | 191 | Valid · n=31,889 gateway / 261,875 direct | — |
| OpenAI → Gemini | Gateway p99 at concurrency 1 (µs) | 219 | Valid · n=31,889 | — |
| OpenAI → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=261,875 | — |
| OpenAI → Gemini | CPU per request (µs) | 160 | Valid | — |
| OpenAI → Gemini | Requests per CPU-second | 6,250.6 | Valid | — |
| OpenAI → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI → Gemini | Cost window core utilisation | 0.982 | Valid | — |
| OpenAI → Gemini | Cost window successful requests | 147,826 | Valid | — |
| OpenAI → Gemini | Cost window throughput (req/s) | 24,634 | Valid | — |
| OpenAI → Gemini | Cost window threads | 16 | Valid | — |
| OpenAI → Gemini | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Gemini | Cost window major page faults | 0 | Valid | — |
| OpenAI → Gemini | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Gemini | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Gemini | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Gemini | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Gemini | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Gemini | Streams sustained | — | Untestable | — |
| OpenAI → Gemini | Idle RSS (MiB) | 34.73 | Valid | — |
| OpenAI → Gemini | Steady-state RSS (MiB) | 67.99 | Valid | — |
| OpenAI → Gemini | Recovered RSS (MiB) | 53.27 | Valid | — |
| OpenAI → Gemini | Peak RSS (MiB) | 69.95 | Valid | — |
| OpenAI → Gemini | Peak RSS high-water mark (MiB) | 69.71 | Valid | — |
| OpenAI → Gemini | Time to plateau (s) | — | Not measured | — |
| OpenAI → Gemini | Memory growth (MiB/min) | 2.06 | Valid | — |
| OpenAI → Gemini | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Gemini | Memory shape under load | 1 | Valid | — |
| OpenAI → Gemini | Idle memory shape | — | Not measured | — |
| OpenAI → Gemini | Idle memory static | 1 | Valid | — |
| OpenAI → Gemini | Idle memory growth (MiB/min) | -0.425 | Valid | — |
| OpenAI → Gemini | Throughput (req/s) | 24,347 | concurrency 8; n=146,100 | 1 ms |
| OpenAI → Gemini | Throughput (req/s) | 29,193 | concurrency 64; n=175,189 | 5 ms |
| OpenAI → Gemini | Throughput (req/s) | 29,862 | concurrency 128; n=179,198 | 10 ms |
| OpenAI → Gemini | Throughput (req/s) | 29,862 | concurrency 128; n=179,198 | 50 ms |
| OpenAI → Gemini | Throughput (req/s) | 29,862 | concurrency 128; n=179,198 | 100 ms |
| OpenAI → Gemini | Throughput (req/s) | 29,862 | concurrency 128; n=179,198 | Unbounded |
| OpenAI Responses → Gemini | Added latency p50 (µs) | 179 | Valid · n=29,315 gateway / 264,153 direct | — |
| OpenAI Responses → Gemini | Added latency p99 (µs) | 209 | Valid · n=29,315 gateway / 264,153 direct | — |
| OpenAI Responses → Gemini | Gateway p99 at concurrency 1 (µs) | 237 | Valid · n=29,315 | — |
| OpenAI Responses → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=264,153 | — |
| OpenAI Responses → Gemini | CPU per request (µs) | 173.7 | Valid | — |
| OpenAI Responses → Gemini | Requests per CPU-second | 5,755.8 | Valid | — |
| OpenAI Responses → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Gemini | Cost window core utilisation | 0.984 | Valid | — |
| OpenAI Responses → Gemini | Cost window successful requests | 136,412 | Valid | — |
| OpenAI Responses → Gemini | Cost window throughput (req/s) | 22,732 | Valid | — |
| OpenAI Responses → Gemini | Cost window threads | 16 | Valid | — |
| OpenAI Responses → Gemini | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → Gemini | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → Gemini | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → Gemini | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → Gemini | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → Gemini | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → Gemini | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → Gemini | Streams sustained | — | Untestable | — |
| OpenAI Responses → Gemini | Idle RSS (MiB) | 34.34 | Valid | — |
| OpenAI Responses → Gemini | Steady-state RSS (MiB) | 67.02 | Valid | — |
| OpenAI Responses → Gemini | Recovered RSS (MiB) | 52.66 | Valid | — |
| OpenAI Responses → Gemini | Peak RSS (MiB) | 68.57 | Valid | — |
| OpenAI Responses → Gemini | Peak RSS high-water mark (MiB) | 68.23 | Valid | — |
| OpenAI Responses → Gemini | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Gemini | Memory growth (MiB/min) | -0.081 | Valid | — |
| OpenAI Responses → Gemini | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → Gemini | Memory shape under load | 0 | Valid | — |
| OpenAI Responses → Gemini | Idle memory shape | -1 | Valid | — |
| OpenAI Responses → Gemini | Idle memory static | 0 | Valid | — |
| OpenAI Responses → Gemini | Idle memory growth (MiB/min) | -0.873 | Valid | — |
| OpenAI Responses → Gemini | Throughput (req/s) | 24,971 | concurrency 16; n=149,843 | 1 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 27,134 | concurrency 64; n=162,810 | 5 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 27,902 | concurrency 128; n=167,436 | 10 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 27,902 | concurrency 128; n=167,436 | 50 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 27,902 | concurrency 128; n=167,436 | 100 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 27,902 | concurrency 128; n=167,436 | Unbounded |
| Cohere → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Bedrock | Added latency p50 (µs) | 408 | Valid · n=13,815 gateway / 263,299 direct | — |
| OpenAI Responses → Bedrock | Added latency p99 (µs) | 458 | Valid · n=13,815 gateway / 263,299 direct | — |
| OpenAI Responses → Bedrock | Gateway p99 at concurrency 1 (µs) | 486 | Valid · n=13,815 | — |
| OpenAI Responses → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=263,299 | — |
| OpenAI Responses → Bedrock | CPU per request (µs) | 417.1 | Valid | — |
| OpenAI Responses → Bedrock | Requests per CPU-second | 2,397.4 | Valid | — |
| OpenAI Responses → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Bedrock | Cost window core utilisation | 0.516 | Valid | — |
| OpenAI Responses → Bedrock | Cost window successful requests | 29,752 | Valid | — |
| OpenAI Responses → Bedrock | Cost window throughput (req/s) | 4,958 | Valid | — |
| OpenAI Responses → Bedrock | Cost window threads | 16 | Valid | — |
| OpenAI Responses → Bedrock | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → Bedrock | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → Bedrock | Streams sustained | — | Untestable | — |
| OpenAI Responses → Bedrock | Idle RSS (MiB) | 34.14 | Valid | — |
| OpenAI Responses → Bedrock | Steady-state RSS (MiB) | 63.89 | Valid | — |
| OpenAI Responses → Bedrock | Recovered RSS (MiB) | 57.61 | Valid | — |
| OpenAI Responses → Bedrock | Peak RSS (MiB) | 66.15 | Valid | — |
| OpenAI Responses → Bedrock | Peak RSS high-water mark (MiB) | 65.87 | Valid | — |
| OpenAI Responses → Bedrock | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Bedrock | Memory growth (MiB/min) | 2.17 | Valid | — |
| OpenAI Responses → Bedrock | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → Bedrock | Memory shape under load | 1 | Valid | — |
| OpenAI Responses → Bedrock | Idle memory shape | -1 | Valid | — |
| OpenAI Responses → Bedrock | Idle memory static | 0 | Valid | — |
| OpenAI Responses → Bedrock | Idle memory growth (MiB/min) | -0.775 | Valid | — |
| OpenAI Responses → Bedrock | Throughput (req/s) | 6,806 | concurrency 4; n=40,846 | 1 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 8,726 | concurrency 16; n=52,362 | 5 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 9,937 | concurrency 32; n=59,631 | 10 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 10,099 | concurrency 64; n=60,598 | 50 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 10,099 | concurrency 64; n=60,598 | 100 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 10,099 | concurrency 64; n=60,598 | Unbounded |
| Gemini → Bedrock | — | — | Not declared: recorded note 1 | — |
| Bedrock → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI → Bedrock | Added latency p50 (µs) | 381 | Valid · n=14,735 gateway / 261,517 direct | — |
| OpenAI → Bedrock | Added latency p99 (µs) | 427 | Valid · n=14,735 gateway / 261,517 direct | — |
| OpenAI → Bedrock | Gateway p99 at concurrency 1 (µs) | 455 | Valid · n=14,735 | — |
| OpenAI → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=261,517 | — |
| OpenAI → Bedrock | CPU per request (µs) | 387.2 | Valid | — |
| OpenAI → Bedrock | Requests per CPU-second | 2,582.6 | Valid | — |
| OpenAI → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI → Bedrock | Cost window core utilisation | 0.589 | Valid | — |
| OpenAI → Bedrock | Cost window successful requests | 36,595 | Valid | — |
| OpenAI → Bedrock | Cost window throughput (req/s) | 6,098 | Valid | — |
| OpenAI → Bedrock | Cost window threads | 16 | Valid | — |
| OpenAI → Bedrock | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Bedrock | Cost window major page faults | 0 | Valid | — |
| OpenAI → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Bedrock | Streams sustained | — | Untestable | — |
| OpenAI → Bedrock | Idle RSS (MiB) | 34.75 | Valid | — |
| OpenAI → Bedrock | Steady-state RSS (MiB) | 63.51 | Valid | — |
| OpenAI → Bedrock | Recovered RSS (MiB) | 56.62 | Valid | — |
| OpenAI → Bedrock | Peak RSS (MiB) | 64.69 | Valid | — |
| OpenAI → Bedrock | Peak RSS high-water mark (MiB) | 64.43 | Valid | — |
| OpenAI → Bedrock | Time to plateau (s) | — | Not measured | — |
| OpenAI → Bedrock | Memory growth (MiB/min) | 0.349 | Valid | — |
| OpenAI → Bedrock | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Bedrock | Memory shape under load | 0 | Valid | — |
| OpenAI → Bedrock | Idle memory shape | — | Not measured | — |
| OpenAI → Bedrock | Idle memory static | 1 | Valid | — |
| OpenAI → Bedrock | Idle memory growth (MiB/min) | -0.498 | Valid | — |
| OpenAI → Bedrock | Throughput (req/s) | 4,228 | concurrency 2; n=25,376 | 1 ms |
| OpenAI → Bedrock | Throughput (req/s) | 10,244 | concurrency 16; n=61,474 | 5 ms |
| OpenAI → Bedrock | Throughput (req/s) | 10,358 | concurrency 32; n=62,160 | 10 ms |
| OpenAI → Bedrock | Throughput (req/s) | 10,529 | concurrency 64; n=63,182 | 50 ms |
| OpenAI → Bedrock | Throughput (req/s) | 10,529 | concurrency 64; n=63,182 | 100 ms |
| OpenAI → Bedrock | Throughput (req/s) | 10,529 | concurrency 64; n=63,182 | Unbounded |
| Cohere → Bedrock | — | — | Not declared: recorded note 1 | — |
| Anthropic → Bedrock | Added latency p50 (µs) | 400 | Valid · n=14,087 gateway / 261,607 direct | — |
| Anthropic → Bedrock | Added latency p99 (µs) | 448 | Valid · n=14,087 gateway / 261,607 direct | — |
| Anthropic → Bedrock | Gateway p99 at concurrency 1 (µs) | 476 | Valid · n=14,087 | — |
| Anthropic → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=261,607 | — |
| Anthropic → Bedrock | CPU per request (µs) | 389.4 | Valid | — |
| Anthropic → Bedrock | Requests per CPU-second | 2,568 | Valid | — |
| Anthropic → Bedrock | Cost window concurrency | 8 | Valid | — |
| Anthropic → Bedrock | Cost window core utilisation | 0.514 | Valid | — |
| Anthropic → Bedrock | Cost window successful requests | 31,766 | Valid | — |
| Anthropic → Bedrock | Cost window throughput (req/s) | 5,293 | Valid | — |
| Anthropic → Bedrock | Cost window threads | 16 | Valid | — |
| Anthropic → Bedrock | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → Bedrock | Cost window major page faults | 0 | Valid | — |
| Anthropic → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| Anthropic → Bedrock | Streams sustained | — | Untestable | — |
| Anthropic → Bedrock | Idle RSS (MiB) | 34.21 | Valid | — |
| Anthropic → Bedrock | Steady-state RSS (MiB) | 62.88 | Valid | — |
| Anthropic → Bedrock | Recovered RSS (MiB) | 56.08 | Valid | — |
| Anthropic → Bedrock | Peak RSS (MiB) | 64.55 | Valid | — |
| Anthropic → Bedrock | Peak RSS high-water mark (MiB) | 64.27 | Valid | — |
| Anthropic → Bedrock | Time to plateau (s) | — | Not measured | — |
| Anthropic → Bedrock | Memory growth (MiB/min) | 1.52 | Valid | — |
| Anthropic → Bedrock | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Bedrock | Memory shape under load | 1 | Valid | — |
| Anthropic → Bedrock | Idle memory shape | — | Not measured | — |
| Anthropic → Bedrock | Idle memory static | 1 | Valid | — |
| Anthropic → Bedrock | Idle memory growth (MiB/min) | -0.409 | Valid | — |
| Anthropic → Bedrock | Throughput (req/s) | 5,623 | concurrency 4; n=33,749 | 1 ms |
| Anthropic → Bedrock | Throughput (req/s) | 10,290 | concurrency 32; n=61,750 | 5 ms |
| Anthropic → Bedrock | Throughput (req/s) | 10,340 | concurrency 64; n=62,052 | 10 ms |
| Anthropic → Bedrock | Throughput (req/s) | 10,340 | concurrency 64; n=62,052 | 50 ms |
| Anthropic → Bedrock | Throughput (req/s) | 10,340 | concurrency 64; n=62,052 | 100 ms |
| Anthropic → Bedrock | Throughput (req/s) | 10,340 | concurrency 64; n=62,052 | Unbounded |
| Gemini → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Bedrock → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Anthropic → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI Responses | Added latency p50 (µs) | 160 | Valid · n=32,575 gateway / 260,507 direct | — |
| OpenAI Responses → OpenAI Responses | Added latency p99 (µs) | 188 | Valid · n=32,575 gateway / 260,507 direct | — |
| OpenAI Responses → OpenAI Responses | Gateway p99 at concurrency 1 (µs) | 217 | Valid · n=32,575 | — |
| OpenAI Responses → OpenAI Responses | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=260,507 | — |
| OpenAI Responses → OpenAI Responses | CPU per request (µs) | 148.1 | Valid | — |
| OpenAI Responses → OpenAI Responses | Requests per CPU-second | 6,752.7 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window core utilisation | 0.788 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window successful requests | 128,099 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window throughput (req/s) | 21,347 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window threads | 16 | Valid | — |
| OpenAI Responses → OpenAI Responses | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Streams sustained | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Idle RSS (MiB) | 34.33 | Valid | — |
| OpenAI Responses → OpenAI Responses | Steady-state RSS (MiB) | 67.35 | Valid | — |
| OpenAI Responses → OpenAI Responses | Recovered RSS (MiB) | 51.9 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS (MiB) | 69.07 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS high-water mark (MiB) | 68.7 | Valid | — |
| OpenAI Responses → OpenAI Responses | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → OpenAI Responses | Memory growth (MiB/min) | -0.651 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory shape under load | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory shape | -1 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory static | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory growth (MiB/min) | -0.804 | Valid | — |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 25,391 | concurrency 8; n=152,368 | 1 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 30,114 | concurrency 64; n=180,699 | 5 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 31,044 | concurrency 128; n=186,270 | 10 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 31,044 | concurrency 128; n=186,270 | 50 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 31,044 | concurrency 128; n=186,270 | 100 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 31,044 | concurrency 128; n=186,270 | Unbounded |
| OpenAI → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
Probe evidence and instrument provenance
Historical capability notes may reference an earlier product version. They are not a new probe or a current support claim. Full RSS samples remain in the immutable raw JSON.
| Ingress → upstream | Cell state | Probe HTTP status | Recorded reason | Recorded detail | Evidence scope | Response excerpt | Tested build |
|---|---|---|---|---|---|---|---|
| OpenAI → Anthropic | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Bedrock → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Gemini → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Anthropic → Anthropic | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI Responses → Anthropic | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Cohere → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Cohere → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Bedrock → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Anthropic → OpenAI | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Gemini → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI Responses → OpenAI | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI → OpenAI | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI Responses → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Bedrock → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Gemini → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Cohere → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Anthropic → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Anthropic → Gemini | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Bedrock → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Gemini → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI → Gemini | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI Responses → Gemini | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Cohere → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI Responses → Bedrock | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Gemini → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Bedrock → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI → Bedrock | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Cohere → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Anthropic → Bedrock | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| Gemini → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Cohere → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Bedrock → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| Anthropic → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI Responses → OpenAI Responses | Served | — | — | — | Recorded run evidence | — | ghcr.io/api7/aisix:1.9.0 |
| OpenAI → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/api7/aisix:1.9.0 |
- Harness commit
d240badd966933fa19eec0606b2d1f3945f18ad2- Mock SHA-256
99d01f709d8d9c1f49055aa265d5eb7475264d6b513911fe317aee74a71190f8- Load generator SHA-256
not recorded- net.core.somaxconn
- 65,535
- net.ipv4.tcp_max_syn_backlog
- 65,535
Stream sweep diagnostics
Per streaming-sweep concurrency, as recorded by the engine: lanes by final HTTP status, and lanes that received no response.
| Ingress → upstream | Concurrency | Lanes by HTTP status | Lanes with no response |
|---|---|---|---|
| OpenAI → Anthropic | 1 | HTTP 200: 1 | 0 |
| OpenAI → Anthropic | 2 | HTTP 200: 2 | 0 |
| OpenAI → Anthropic | 4 | HTTP 200: 4 | 0 |
| OpenAI → Anthropic | 8 | HTTP 200: 8 | 0 |
| OpenAI → Anthropic | 16 | HTTP 200: 16 | 0 |
| OpenAI → Anthropic | 32 | HTTP 200: 32 | 0 |
| OpenAI → Anthropic | 64 | HTTP 200: 64 | 0 |
| OpenAI → Anthropic | 128 | HTTP 200: 128 | 0 |
| OpenAI → Anthropic | 256 | HTTP 200: 256 | 0 |
| OpenAI → Anthropic | 512 | HTTP 200: 512 | 0 |
| OpenAI → Anthropic | 1,024 | HTTP 200: 1,024 | 0 |
| OpenAI → Anthropic | 768 | HTTP 200: 768 | 0 |
| OpenAI → Anthropic | 896 | HTTP 200: 896 | 0 |
| OpenAI → Anthropic | 832 | HTTP 200: 832 | 0 |
| OpenAI → Anthropic | 800 | HTTP 200: 800 | 0 |
| OpenAI → Anthropic | 784 | HTTP 200: 784 | 0 |
| OpenAI → Anthropic | 776 | HTTP 200: 776 | 0 |
| OpenAI → Anthropic | 772 | HTTP 200: 772 | 0 |
| OpenAI → Anthropic | 774 | HTTP 200: 774 | 0 |
| OpenAI → Anthropic | 775 | HTTP 200: 775 | 0 |
| OpenAI → Anthropic | 775 | HTTP 200: 775 | 0 |
| OpenAI → Anthropic | 775 | HTTP 200: 775 | 0 |
| Anthropic → Anthropic | 1 | HTTP 200: 1 | 0 |
| Anthropic → Anthropic | 2 | HTTP 200: 2 | 0 |
| Anthropic → Anthropic | 4 | HTTP 200: 4 | 0 |
| Anthropic → Anthropic | 8 | HTTP 200: 8 | 0 |
| Anthropic → Anthropic | 16 | HTTP 200: 16 | 0 |
| Anthropic → Anthropic | 32 | HTTP 200: 32 | 0 |
| Anthropic → Anthropic | 64 | HTTP 200: 64 | 0 |
| Anthropic → Anthropic | 128 | HTTP 200: 128 | 0 |
| Anthropic → Anthropic | 256 | HTTP 200: 256 | 0 |
| Anthropic → Anthropic | 512 | HTTP 200: 512 | 0 |
| Anthropic → Anthropic | 1,024 | HTTP 200: 1,024 | 0 |
| Anthropic → Anthropic | 768 | HTTP 200: 768 | 0 |
| Anthropic → Anthropic | 896 | HTTP 200: 896 | 0 |
| Anthropic → Anthropic | 832 | HTTP 200: 832 | 0 |
| Anthropic → Anthropic | 864 | HTTP 200: 864 | 0 |
| Anthropic → Anthropic | 848 | HTTP 200: 848 | 0 |
| Anthropic → Anthropic | 840 | HTTP 200: 840 | 0 |
| Anthropic → Anthropic | 844 | HTTP 200: 844 | 0 |
| Anthropic → Anthropic | 842 | HTTP 200: 842 | 0 |
| Anthropic → Anthropic | 843 | HTTP 200: 843 | 0 |
| Anthropic → Anthropic | 843 | HTTP 200: 843 | 0 |
| Anthropic → Anthropic | 843 | HTTP 200: 843 | 0 |
| Anthropic → Anthropic | 677 | HTTP 200: 677 | 0 |
| Anthropic → Anthropic | 677 | HTTP 200: 677 | 0 |
| Anthropic → Anthropic | 677 | HTTP 200: 677 | 0 |
| Anthropic → OpenAI | 1 | HTTP 200: 1 | 0 |
| Anthropic → OpenAI | 2 | HTTP 200: 2 | 0 |
| Anthropic → OpenAI | 4 | HTTP 200: 4 | 0 |
| Anthropic → OpenAI | 8 | HTTP 200: 8 | 0 |
| Anthropic → OpenAI | 16 | HTTP 200: 16 | 0 |
| Anthropic → OpenAI | 32 | HTTP 200: 32 | 0 |
| Anthropic → OpenAI | 64 | HTTP 200: 64 | 0 |
| Anthropic → OpenAI | 128 | HTTP 200: 128 | 0 |
| Anthropic → OpenAI | 256 | HTTP 200: 256 | 0 |
| Anthropic → OpenAI | 512 | HTTP 200: 512 | 0 |
| Anthropic → OpenAI | 1,024 | HTTP 200: 1,024 | 0 |
| Anthropic → OpenAI | 768 | HTTP 200: 768 | 0 |
| Anthropic → OpenAI | 896 | HTTP 200: 896 | 0 |
| Anthropic → OpenAI | 832 | HTTP 200: 832 | 0 |
| Anthropic → OpenAI | 800 | HTTP 200: 800 | 0 |
| Anthropic → OpenAI | 816 | HTTP 200: 816 | 0 |
| Anthropic → OpenAI | 808 | HTTP 200: 808 | 0 |
| Anthropic → OpenAI | 804 | HTTP 200: 804 | 0 |
| Anthropic → OpenAI | 806 | HTTP 200: 806 | 0 |
| Anthropic → OpenAI | 805 | HTTP 200: 805 | 0 |
| Anthropic → OpenAI | 804 | HTTP 200: 804 | 0 |
| Anthropic → OpenAI | 804 | HTTP 200: 804 | 0 |
| Anthropic → OpenAI | 658 | HTTP 200: 658 | 0 |
| Anthropic → OpenAI | 658 | HTTP 200: 658 | 0 |
| Anthropic → OpenAI | 658 | HTTP 200: 658 | 0 |
| OpenAI → OpenAI | 1 | HTTP 200: 1 | 0 |
| OpenAI → OpenAI | 2 | HTTP 200: 2 | 0 |
| OpenAI → OpenAI | 4 | HTTP 200: 4 | 0 |
| OpenAI → OpenAI | 8 | HTTP 200: 8 | 0 |
| OpenAI → OpenAI | 16 | HTTP 200: 16 | 0 |
| OpenAI → OpenAI | 32 | HTTP 200: 32 | 0 |
| OpenAI → OpenAI | 64 | HTTP 200: 64 | 0 |
| OpenAI → OpenAI | 128 | HTTP 200: 128 | 0 |
| OpenAI → OpenAI | 256 | HTTP 200: 256 | 0 |
| OpenAI → OpenAI | 512 | HTTP 200: 512 | 0 |
| OpenAI → OpenAI | 1,024 | HTTP 200: 1,024 | 0 |
| OpenAI → OpenAI | 768 | HTTP 200: 768 | 0 |
| OpenAI → OpenAI | 896 | HTTP 200: 896 | 0 |
| OpenAI → OpenAI | 832 | HTTP 200: 832 | 0 |
| OpenAI → OpenAI | 800 | HTTP 200: 800 | 0 |
| OpenAI → OpenAI | 784 | HTTP 200: 784 | 0 |
| OpenAI → OpenAI | 776 | HTTP 200: 776 | 0 |
| OpenAI → OpenAI | 780 | HTTP 200: 780 | 0 |
| OpenAI → OpenAI | 778 | HTTP 200: 778 | 0 |
| OpenAI → OpenAI | 779 | HTTP 200: 779 | 0 |
| OpenAI → OpenAI | 779 | HTTP 200: 779 | 0 |
| OpenAI → OpenAI | 779 | HTTP 200: 779 | 0 |
| OpenAI → OpenAI | 645 | HTTP 200: 645 | 0 |
| OpenAI → OpenAI | 645 | HTTP 200: 645 | 0 |
| OpenAI → OpenAI | 645 | HTTP 200: 645 | 0 |
Recorded notes
Text recorded with the cells above. Each note is shown once; rows refer to it by number.
- Pinned AISIX v1.9.0 source 7e070f0bde3f653c3b197ed18c5b9205b866a4c5: README native adapter families, aisix-proxy/src/lib.rs routes and dispatch.rs::serves_natively_with, provider-vertex/bedrock bridge configuration. OpenAI, Responses and Anthropic ingress translate to Chat Completions, Anthropic, Gemini and Bedrock; only Responses ingress selects the Responses upstream. Separate provider keys use explicit apis:{} for Chat-only routing and the native Responses declaration default for the Responses alias. Thirteen exact pairs passed local recorder checks. Evidence: results/diagnostics/refresh-configuration/aisix-protocol-preflight.json
- Historical capability research, not a fresh probe of the tested build. Referenced versions may differ from gateway_build; do not infer current capability.
Evidence for the current measurements
- run-aisix-ef0cff28391e0017f17c4b7c01e0171c62359468b787de48402bc3408df76915 · complete raw record including RSS series
Configuration recorded by the run
# config.gen.yaml
resources_file: "/etc/aisix/resources.yaml"
proxy:
addr: "0.0.0.0:3000"
admin:
admin_keys:
- "aisix-admin-dummy"
# resources.gen.yaml
_format_version: "1"
provider_keys:
- display_name: mock-openai
provider: openai
adapter: openai
apis: {}
api_base: "http://127.0.0.1:8000/v1"
api_key: "sk-mock"
- display_name: mock-anthropic
provider: anthropic
adapter: anthropic
api_base: "http://127.0.0.1:8000"
api_key: "sk-mock"
- display_name: mock-vertex
provider: google
adapter: vertex
api_base: "http://127.0.0.1:8000"
api_key: '{"access_token":"dummy","project":"mock","region":"us-central1"}'
- display_name: mock-bedrock
provider: bedrock
adapter: bedrock
api_base: "http://127.0.0.1:8000"
api_key: '{"access_key_id":"AKIAMOCKACCESSKEY","secret_access_key":"mock-secret","region":"us-east-1"}'
- display_name: mock-responses
provider: openai
adapter: openai
api_base: "http://127.0.0.1:8000/v1"
api_key: "sk-mock"
models:
- display_name: gpt-4o-mini
provider: openai
model_name: gpt-4o-mini
provider_key: mock-openai
- display_name: claude-3-5-sonnet-20241022
provider: anthropic
model_name: claude-3-5-sonnet-20241022
provider_key: mock-anthropic
- display_name: gemini-1.5-pro
provider: google
model_name: gemini-1.5-pro
provider_key: mock-vertex
- display_name: amazon.nova-micro-v1:0
provider: bedrock
model_name: amazon.nova-micro-v1:0
provider_key: mock-bedrock
- display_name: mock-responses
provider: openai
model_name: gpt-4o-mini
provider_key: mock-responses
api_keys:
- display_name: bench
key_env: BENCH_AISIX_KEY
allowed_models: ["*"]
Compare a shared protocol cell
- AISIX (api7) vs agentgateway
- AISIX (api7) vs APISIX
- AISIX (api7) vs Bifrost
- AISIX (api7) vs Busbar
- AISIX (api7) vs GoModel
- AISIX (api7) vs Helicone
- AISIX (api7) vs Higress
- AISIX (api7) vs Kong
- AISIX (api7) vs LiteLLM · Python
- AISIX (api7) vs LiteLLM · Rust
- AISIX (api7) vs One-API
- AISIX (api7) vs Plano
- AISIX (api7) vs Portkey
- AISIX (api7) vs TensorZero