GoModel 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.
Go · recorded build: enterpilot/gomodel:0.2.3. 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) |
|---|---|---|---|---|
| Cohere → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI → Anthropic | Added latency p50 (µs) | 332 | Valid · n=16,334 gateway / 245,181 direct | — |
| OpenAI → Anthropic | Added latency p99 (µs) | 508 | Valid · n=16,334 gateway / 245,181 direct | — |
| OpenAI → Anthropic | Gateway p99 at concurrency 1 (µs) | 538 | Valid · n=16,334 | — |
| OpenAI → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=245,181 | — |
| OpenAI → Anthropic | CPU per request (µs) | 424.9 | Valid | — |
| OpenAI → Anthropic | Requests per CPU-second | 2,353.4 | Valid | — |
| OpenAI → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI → Anthropic | Cost window core utilisation | 0.707 | Valid | — |
| OpenAI → Anthropic | Cost window successful requests | 40,079 | Valid | — |
| OpenAI → Anthropic | Cost window throughput (req/s) | 6,679 | Valid | — |
| OpenAI → Anthropic | Cost window threads | 13 | Valid | — |
| OpenAI → Anthropic | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Anthropic | Cost window major page faults | 0 | Valid | — |
| OpenAI → Anthropic | Added time to first event p50 (µs) | 482 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added time to first event p99 (µs) | 635 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p50 (µs) | 5 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p99 (µs) | 21 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Streams sustained (frames/s) | 47,311.5 | Valid | — |
| OpenAI → Anthropic | Streams sustained | 1,140 | Valid | — |
| OpenAI → Anthropic | Idle RSS (MiB) | 52.91 | Valid | — |
| OpenAI → Anthropic | Steady-state RSS (MiB) | 87.58 | Valid | — |
| OpenAI → Anthropic | Recovered RSS (MiB) | 87.09 | Valid | — |
| OpenAI → Anthropic | Peak RSS (MiB) | 89.44 | Valid | — |
| OpenAI → Anthropic | Peak RSS high-water mark (MiB) | 89.07 | Valid | — |
| OpenAI → Anthropic | Time to plateau (s) | — | Not measured | — |
| OpenAI → Anthropic | Memory growth (MiB/min) | -0.11 | 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) | 0.323 | Valid | — |
| OpenAI → Anthropic | Throughput (req/s) | 4,631 | concurrency 2; n=27,792 | 1 ms |
| OpenAI → Anthropic | Throughput (req/s) | 6,656 | concurrency 8; n=39,947 | 5 ms |
| OpenAI → Anthropic | Throughput (req/s) | 6,820 | concurrency 16; n=40,929 | 10 ms |
| OpenAI → Anthropic | Throughput (req/s) | 7,453 | concurrency 64; n=44,724 | 50 ms |
| OpenAI → Anthropic | Throughput (req/s) | 7,474 | concurrency 128; n=44,854 | 100 ms |
| OpenAI → Anthropic | Throughput (req/s) | 7,474 | concurrency 128; n=44,854 | Unbounded |
| OpenAI Responses → Anthropic | Added latency p50 (µs) | 363 | Valid · n=14,995 gateway / 248,903 direct | — |
| OpenAI Responses → Anthropic | Added latency p99 (µs) | 639 | Valid · n=14,995 gateway / 248,903 direct | — |
| OpenAI Responses → Anthropic | Gateway p99 at concurrency 1 (µs) | 669 | Valid · n=14,995 | — |
| OpenAI Responses → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=248,903 | — |
| OpenAI Responses → Anthropic | CPU per request (µs) | 572 | Valid | — |
| OpenAI Responses → Anthropic | Requests per CPU-second | 1,748.3 | Valid | — |
| OpenAI Responses → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Anthropic | Cost window core utilisation | 0.854 | Valid | — |
| OpenAI Responses → Anthropic | Cost window successful requests | 35,927 | Valid | — |
| OpenAI Responses → Anthropic | Cost window throughput (req/s) | 5,987 | Valid | — |
| OpenAI Responses → Anthropic | Cost window threads | 12 | Valid | — |
| OpenAI Responses → Anthropic | Non-voluntary context switches per request | 0.009 | 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) | 53.16 | Valid | — |
| OpenAI Responses → Anthropic | Steady-state RSS (MiB) | 240.9 | Valid | — |
| OpenAI Responses → Anthropic | Recovered RSS (MiB) | 157.5 | Valid | — |
| OpenAI Responses → Anthropic | Peak RSS (MiB) | 324.5 | Valid | — |
| OpenAI Responses → Anthropic | Peak RSS high-water mark (MiB) | 324.1 | Valid | — |
| OpenAI Responses → Anthropic | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Anthropic | Memory growth (MiB/min) | 10.7 | 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 | — | Not measured | — |
| OpenAI Responses → Anthropic | Idle memory static | 1 | Valid | — |
| OpenAI Responses → Anthropic | Idle memory growth (MiB/min) | 0.351 | Valid | — |
| OpenAI Responses → Anthropic | Throughput (req/s) | 4,280 | concurrency 2; n=25,689 | 1 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 5,982 | concurrency 8; n=35,897 | 5 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 5,982 | concurrency 8; n=35,897 | 10 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 6,343 | concurrency 64; n=38,060 | 50 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 6,343 | concurrency 64; n=38,060 | 100 ms |
| OpenAI Responses → Anthropic | Throughput (req/s) | 6,343 | concurrency 64; n=38,060 | Unbounded |
| Bedrock → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → Anthropic | — | — | Not declared: recorded note 1 | — |
| Anthropic → Anthropic | Added latency p50 (µs) | 386 | Valid · n=14,086 gateway / 240,685 direct | — |
| Anthropic → Anthropic | Added latency p99 (µs) | 722 | Valid · n=14,086 gateway / 240,685 direct | — |
| Anthropic → Anthropic | Gateway p99 at concurrency 1 (µs) | 753 | Valid · n=14,086 | — |
| Anthropic → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=240,685 | — |
| Anthropic → Anthropic | CPU per request (µs) | 498.8 | Valid | — |
| Anthropic → Anthropic | Requests per CPU-second | 2,004.7 | Valid | — |
| Anthropic → Anthropic | Cost window concurrency | 8 | Valid | — |
| Anthropic → Anthropic | Cost window core utilisation | 0.786 | Valid | — |
| Anthropic → Anthropic | Cost window successful requests | 37,928 | Valid | — |
| Anthropic → Anthropic | Cost window throughput (req/s) | 6,320 | Valid | — |
| Anthropic → Anthropic | Cost window threads | 13 | 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) | 485 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added time to first event p99 (µs) | 1,078 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p50 (µs) | — | Below resolution · 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) | 64,695.4 | Valid | — |
| Anthropic → Anthropic | Streams sustained | 1,559 | Valid | — |
| Anthropic → Anthropic | Idle RSS (MiB) | 52.96 | Valid | — |
| Anthropic → Anthropic | Steady-state RSS (MiB) | 86.85 | Valid | — |
| Anthropic → Anthropic | Recovered RSS (MiB) | 87.08 | Valid | — |
| Anthropic → Anthropic | Peak RSS (MiB) | 88.52 | Valid | — |
| Anthropic → Anthropic | Peak RSS high-water mark (MiB) | 88.11 | Valid | — |
| Anthropic → Anthropic | Time to plateau (s) | — | Not measured | — |
| Anthropic → Anthropic | Memory growth (MiB/min) | -0.254 | 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) | 0.315 | Valid | — |
| Anthropic → Anthropic | Throughput (req/s) | 2,351 | concurrency 1; n=14,110 | 1 ms |
| Anthropic → Anthropic | Throughput (req/s) | 6,462 | concurrency 8; n=38,778 | 5 ms |
| Anthropic → Anthropic | Throughput (req/s) | 6,654 | concurrency 16; n=39,931 | 10 ms |
| Anthropic → Anthropic | Throughput (req/s) | 7,222 | concurrency 64; n=43,337 | 50 ms |
| Anthropic → Anthropic | Throughput (req/s) | 7,237 | concurrency 128; n=43,430 | 100 ms |
| Anthropic → Anthropic | Throughput (req/s) | 7,237 | concurrency 128; n=43,430 | Unbounded |
| Bedrock → OpenAI | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI | — | — | Not declared: recorded note 1 | — |
| Anthropic → OpenAI | Added latency p50 (µs) | 348 | Valid · n=15,595 gateway / 242,839 direct | — |
| Anthropic → OpenAI | Added latency p99 (µs) | 531 | Valid · n=15,595 gateway / 242,839 direct | — |
| Anthropic → OpenAI | Gateway p99 at concurrency 1 (µs) | 561 | Valid · n=15,595 | — |
| Anthropic → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=242,839 | — |
| Anthropic → OpenAI | CPU per request (µs) | 449.6 | Valid | — |
| Anthropic → OpenAI | Requests per CPU-second | 2,224.3 | Valid | — |
| Anthropic → OpenAI | Cost window concurrency | 8 | Valid | — |
| Anthropic → OpenAI | Cost window core utilisation | 0.696 | Valid | — |
| Anthropic → OpenAI | Cost window successful requests | 37,257 | Valid | — |
| Anthropic → OpenAI | Cost window throughput (req/s) | 6,208 | Valid | — |
| Anthropic → OpenAI | Cost window threads | 13 | Valid | — |
| Anthropic → OpenAI | Non-voluntary context switches per request | 0.006 | Valid | — |
| Anthropic → OpenAI | Cost window major page faults | 0 | Valid | — |
| Anthropic → OpenAI | Added time to first event p50 (µs) | 482 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added time to first event p99 (µs) | 681 | 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) | 14 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Streams sustained (frames/s) | 61,069.6 | Valid | — |
| Anthropic → OpenAI | Streams sustained | 1,536 | Valid | — |
| Anthropic → OpenAI | Idle RSS (MiB) | 53.24 | Valid | — |
| Anthropic → OpenAI | Steady-state RSS (MiB) | 87.93 | Valid | — |
| Anthropic → OpenAI | Recovered RSS (MiB) | 89.77 | Valid | — |
| Anthropic → OpenAI | Peak RSS (MiB) | 90.31 | Valid | — |
| Anthropic → OpenAI | Peak RSS high-water mark (MiB) | 90 | Valid | — |
| Anthropic → OpenAI | Time to plateau (s) | — | Not measured | — |
| Anthropic → OpenAI | Memory growth (MiB/min) | 0.027 | Valid | — |
| Anthropic → OpenAI | Memory load duration (s) | 300 | Valid | — |
| Anthropic → OpenAI | Memory shape under load | 0 | Valid | — |
| Anthropic → OpenAI | Idle memory shape | — | Not measured | — |
| Anthropic → OpenAI | Idle memory static | 1 | Valid | — |
| Anthropic → OpenAI | Idle memory growth (MiB/min) | 0.191 | Valid | — |
| Anthropic → OpenAI | Throughput (req/s) | 4,318 | concurrency 2; n=25,914 | 1 ms |
| Anthropic → OpenAI | Throughput (req/s) | 6,214 | concurrency 8; n=37,292 | 5 ms |
| Anthropic → OpenAI | Throughput (req/s) | 6,384 | concurrency 16; n=38,313 | 10 ms |
| Anthropic → OpenAI | Throughput (req/s) | 6,988 | concurrency 64; n=41,937 | 50 ms |
| Anthropic → OpenAI | Throughput (req/s) | 7,071 | concurrency 128; n=42,435 | 100 ms |
| Anthropic → OpenAI | Throughput (req/s) | 7,071 | concurrency 128; n=42,435 | Unbounded |
| OpenAI → OpenAI | Added latency p50 (µs) | 343 | Valid · n=15,837 gateway / 239,533 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 565 | Valid · n=15,837 gateway / 239,533 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 596 | Valid · n=15,837 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=239,533 | — |
| OpenAI → OpenAI | CPU per request (µs) | 439.2 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 2,277.1 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.714 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 39,121 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 6,519 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 14 | 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) | 479 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 601 | 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) | 26 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 50,390.1 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 1,208 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 53 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 87.26 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 90.46 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 90.51 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 89.02 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | -0.338 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.411 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 4,555 | concurrency 2; n=27,335 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 6,685 | concurrency 8; n=40,117 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 6,862 | concurrency 16; n=41,180 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 7,415 | concurrency 64; n=44,496 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 7,475 | concurrency 128; n=44,859 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 7,475 | concurrency 128; n=44,859 | Unbounded |
| Gemini → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Cohere | Added latency p50 (µs) | 353 | Valid · n=15,319 gateway / 247,454 direct | — |
| OpenAI Responses → Cohere | Added latency p99 (µs) | 600 | Valid · n=15,319 gateway / 247,454 direct | — |
| OpenAI Responses → Cohere | Gateway p99 at concurrency 1 (µs) | 630 | Valid · n=15,319 | — |
| OpenAI Responses → Cohere | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=247,454 | — |
| OpenAI Responses → Cohere | CPU per request (µs) | 569.9 | Valid | — |
| OpenAI Responses → Cohere | Requests per CPU-second | 1,754.6 | Valid | — |
| OpenAI Responses → Cohere | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Cohere | Cost window core utilisation | 0.857 | Valid | — |
| OpenAI Responses → Cohere | Cost window successful requests | 36,198 | Valid | — |
| OpenAI Responses → Cohere | Cost window throughput (req/s) | 6,032 | Valid | — |
| OpenAI Responses → Cohere | Cost window threads | 12 | Valid | — |
| OpenAI Responses → Cohere | Non-voluntary context switches per request | 0.013 | Valid | — |
| OpenAI Responses → Cohere | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → Cohere | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → Cohere | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → Cohere | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → Cohere | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → Cohere | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → Cohere | Streams sustained | — | Untestable | — |
| OpenAI Responses → Cohere | Idle RSS (MiB) | 53.12 | Valid | — |
| OpenAI Responses → Cohere | Steady-state RSS (MiB) | 229.9 | Valid | — |
| OpenAI Responses → Cohere | Recovered RSS (MiB) | 145.3 | Valid | — |
| OpenAI Responses → Cohere | Peak RSS (MiB) | 317 | Valid | — |
| OpenAI Responses → Cohere | Peak RSS high-water mark (MiB) | 316.4 | Valid | — |
| OpenAI Responses → Cohere | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Cohere | Memory growth (MiB/min) | -59.17 | Valid | — |
| OpenAI Responses → Cohere | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → Cohere | Memory shape under load | -1 | Valid | — |
| OpenAI Responses → Cohere | Idle memory shape | — | Not measured | — |
| OpenAI Responses → Cohere | Idle memory static | 1 | Valid | — |
| OpenAI Responses → Cohere | Idle memory growth (MiB/min) | 0.344 | Valid | — |
| OpenAI Responses → Cohere | Throughput (req/s) | 4,322 | concurrency 2; n=25,940 | 1 ms |
| OpenAI Responses → Cohere | Throughput (req/s) | 6,006 | concurrency 8; n=36,046 | 5 ms |
| OpenAI Responses → Cohere | Throughput (req/s) | 6,006 | concurrency 8; n=36,046 | 10 ms |
| OpenAI Responses → Cohere | Throughput (req/s) | 6,311 | concurrency 64; n=37,871 | 50 ms |
| OpenAI Responses → Cohere | Throughput (req/s) | 6,311 | concurrency 64; n=37,871 | 100 ms |
| OpenAI Responses → Cohere | Throughput (req/s) | 6,311 | concurrency 64; n=37,871 | Unbounded |
| Anthropic → Cohere | Added latency p50 (µs) | 329 | Valid · n=16,446 gateway / 244,026 direct | — |
| Anthropic → Cohere | Added latency p99 (µs) | 513 | Valid · n=16,446 gateway / 244,026 direct | — |
| Anthropic → Cohere | Gateway p99 at concurrency 1 (µs) | 543 | Valid · n=16,446 | — |
| Anthropic → Cohere | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=244,026 | — |
| Anthropic → Cohere | CPU per request (µs) | 426.2 | Valid | — |
| Anthropic → Cohere | Requests per CPU-second | 2,346.4 | Valid | — |
| Anthropic → Cohere | Cost window concurrency | 8 | Valid | — |
| Anthropic → Cohere | Cost window core utilisation | 0.682 | Valid | — |
| Anthropic → Cohere | Cost window successful requests | 38,505 | Valid | — |
| Anthropic → Cohere | Cost window throughput (req/s) | 6,416 | Valid | — |
| Anthropic → Cohere | Cost window threads | 12 | Valid | — |
| Anthropic → Cohere | Non-voluntary context switches per request | 0.006 | Valid | — |
| Anthropic → Cohere | Cost window major page faults | 0 | Valid | — |
| Anthropic → Cohere | Added time to first event p50 (µs) | — | Untestable | — |
| Anthropic → Cohere | Added time to first event p99 (µs) | — | Untestable | — |
| Anthropic → Cohere | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Anthropic → Cohere | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Anthropic → Cohere | Streams sustained (frames/s) | — | Untestable | — |
| Anthropic → Cohere | Streams sustained | — | Untestable | — |
| Anthropic → Cohere | Idle RSS (MiB) | 53.11 | Valid | — |
| Anthropic → Cohere | Steady-state RSS (MiB) | 87.6 | Valid | — |
| Anthropic → Cohere | Recovered RSS (MiB) | 88.75 | Valid | — |
| Anthropic → Cohere | Peak RSS (MiB) | 89.65 | Valid | — |
| Anthropic → Cohere | Peak RSS high-water mark (MiB) | 89.16 | Valid | — |
| Anthropic → Cohere | Time to plateau (s) | — | Not measured | — |
| Anthropic → Cohere | Memory growth (MiB/min) | 0.114 | Valid | — |
| Anthropic → Cohere | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Cohere | Memory shape under load | 0 | Valid | — |
| Anthropic → Cohere | Idle memory shape | — | Not measured | — |
| Anthropic → Cohere | Idle memory static | 1 | Valid | — |
| Anthropic → Cohere | Idle memory growth (MiB/min) | 0.251 | Valid | — |
| Anthropic → Cohere | Throughput (req/s) | 4,543 | concurrency 2; n=27,264 | 1 ms |
| Anthropic → Cohere | Throughput (req/s) | 6,320 | concurrency 8; n=37,931 | 5 ms |
| Anthropic → Cohere | Throughput (req/s) | 6,500 | concurrency 16; n=39,010 | 10 ms |
| Anthropic → Cohere | Throughput (req/s) | 7,107 | concurrency 64; n=42,647 | 50 ms |
| Anthropic → Cohere | Throughput (req/s) | 7,172 | concurrency 128; n=43,039 | 100 ms |
| Anthropic → Cohere | Throughput (req/s) | 7,172 | concurrency 128; n=43,039 | Unbounded |
| Cohere → Cohere | — | — | Not declared: recorded note 1 | — |
| Bedrock → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI → Cohere | Added latency p50 (µs) | 335 | Valid · n=16,166 gateway / 236,668 direct | — |
| OpenAI → Cohere | Added latency p99 (µs) | 515 | Valid · n=16,166 gateway / 236,668 direct | — |
| OpenAI → Cohere | Gateway p99 at concurrency 1 (µs) | 546 | Valid · n=16,166 | — |
| OpenAI → Cohere | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=236,668 | — |
| OpenAI → Cohere | CPU per request (µs) | 418.7 | Valid | — |
| OpenAI → Cohere | Requests per CPU-second | 2,388.3 | Valid | — |
| OpenAI → Cohere | Cost window concurrency | 8 | Valid | — |
| OpenAI → Cohere | Cost window core utilisation | 0.707 | Valid | — |
| OpenAI → Cohere | Cost window successful requests | 40,625 | Valid | — |
| OpenAI → Cohere | Cost window throughput (req/s) | 6,769 | Valid | — |
| OpenAI → Cohere | Cost window threads | 12 | Valid | — |
| OpenAI → Cohere | Non-voluntary context switches per request | 0.005 | Valid | — |
| OpenAI → Cohere | Cost window major page faults | 0 | Valid | — |
| OpenAI → Cohere | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Cohere | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Cohere | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Cohere | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Cohere | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Cohere | Streams sustained | — | Untestable | — |
| OpenAI → Cohere | Idle RSS (MiB) | 52.88 | Valid | — |
| OpenAI → Cohere | Steady-state RSS (MiB) | 87.43 | Valid | — |
| OpenAI → Cohere | Recovered RSS (MiB) | 90.28 | Valid | — |
| OpenAI → Cohere | Peak RSS (MiB) | 90.28 | Valid | — |
| OpenAI → Cohere | Peak RSS high-water mark (MiB) | 88.98 | Valid | — |
| OpenAI → Cohere | Time to plateau (s) | — | Not measured | — |
| OpenAI → Cohere | Memory growth (MiB/min) | 0.204 | Valid | — |
| OpenAI → Cohere | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Cohere | Memory shape under load | 0 | Valid | — |
| OpenAI → Cohere | Idle memory shape | — | Not measured | — |
| OpenAI → Cohere | Idle memory static | 1 | Valid | — |
| OpenAI → Cohere | Idle memory growth (MiB/min) | 0.26 | Valid | — |
| OpenAI → Cohere | Throughput (req/s) | 4,690 | concurrency 2; n=28,153 | 1 ms |
| OpenAI → Cohere | Throughput (req/s) | 6,742 | concurrency 8; n=40,458 | 5 ms |
| OpenAI → Cohere | Throughput (req/s) | 6,886 | concurrency 16; n=41,331 | 10 ms |
| OpenAI → Cohere | Throughput (req/s) | 7,538 | concurrency 64; n=45,232 | 50 ms |
| OpenAI → Cohere | Throughput (req/s) | 7,549 | concurrency 128; n=45,303 | 100 ms |
| OpenAI → Cohere | Throughput (req/s) | 7,549 | concurrency 128; n=45,303 | Unbounded |
| Anthropic → Bedrock | Added latency p50 (µs) | 452 | Valid · n=12,219 gateway / 247,325 direct | — |
| Anthropic → Bedrock | Added latency p99 (µs) | 774 | Valid · n=12,219 gateway / 247,325 direct | — |
| Anthropic → Bedrock | Gateway p99 at concurrency 1 (µs) | 804 | Valid · n=12,219 | — |
| Anthropic → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=247,325 | — |
| Anthropic → Bedrock | CPU per request (µs) | 553.6 | Valid | — |
| Anthropic → Bedrock | Requests per CPU-second | 1,806.4 | Valid | — |
| Anthropic → Bedrock | Cost window concurrency | 8 | Valid | — |
| Anthropic → Bedrock | Cost window core utilisation | 0.773 | Valid | — |
| Anthropic → Bedrock | Cost window successful requests | 33,617 | Valid | — |
| Anthropic → Bedrock | Cost window throughput (req/s) | 5,602 | Valid | — |
| Anthropic → Bedrock | Cost window threads | 12 | Valid | — |
| Anthropic → Bedrock | Non-voluntary context switches per request | 0.007 | 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) | 52.89 | Valid | — |
| Anthropic → Bedrock | Steady-state RSS (MiB) | 91.17 | Valid | — |
| Anthropic → Bedrock | Recovered RSS (MiB) | 91.67 | Valid | — |
| Anthropic → Bedrock | Peak RSS (MiB) | 93.25 | Valid | — |
| Anthropic → Bedrock | Peak RSS high-water mark (MiB) | 92.71 | Valid | — |
| Anthropic → Bedrock | Time to plateau (s) | — | Not measured | — |
| Anthropic → Bedrock | Memory growth (MiB/min) | -0.047 | Valid | — |
| Anthropic → Bedrock | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Bedrock | Memory shape under load | 0 | Valid | — |
| Anthropic → Bedrock | Idle memory shape | 0 | Valid | — |
| Anthropic → Bedrock | Idle memory static | 0 | Valid | — |
| Anthropic → Bedrock | Idle memory growth (MiB/min) | 0.384 | Valid | — |
| Anthropic → Bedrock | Throughput (req/s) | 2,020 | concurrency 1; n=12,127 | 1 ms |
| Anthropic → Bedrock | Throughput (req/s) | 5,567 | concurrency 8; n=33,409 | 5 ms |
| Anthropic → Bedrock | Throughput (req/s) | 5,567 | concurrency 8; n=33,409 | 10 ms |
| Anthropic → Bedrock | Throughput (req/s) | 6,093 | concurrency 64; n=36,562 | 50 ms |
| Anthropic → Bedrock | Throughput (req/s) | 6,134 | concurrency 128; n=36,811 | 100 ms |
| Anthropic → Bedrock | Throughput (req/s) | 6,134 | concurrency 128; n=36,811 | Unbounded |
| Cohere → Bedrock | — | — | Not declared: recorded note 1 | — |
| Gemini → Bedrock | — | — | Not declared: recorded note 1 | — |
| Bedrock → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Bedrock | Added latency p50 (µs) | 471 | Valid · n=11,671 gateway / 247,559 direct | — |
| OpenAI Responses → Bedrock | Added latency p99 (µs) | 809 | Valid · n=11,671 gateway / 247,559 direct | — |
| OpenAI Responses → Bedrock | Gateway p99 at concurrency 1 (µs) | 839 | Valid · n=11,671 | — |
| OpenAI Responses → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=247,559 | — |
| OpenAI Responses → Bedrock | CPU per request (µs) | 674.7 | Valid | — |
| OpenAI Responses → Bedrock | Requests per CPU-second | 1,482.2 | Valid | — |
| OpenAI Responses → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Bedrock | Cost window core utilisation | 0.87 | Valid | — |
| OpenAI Responses → Bedrock | Cost window successful requests | 31,052 | Valid | — |
| OpenAI Responses → Bedrock | Cost window throughput (req/s) | 5,174 | Valid | — |
| OpenAI Responses → Bedrock | Cost window threads | 13 | Valid | — |
| OpenAI Responses → Bedrock | Non-voluntary context switches per request | 0.024 | 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) | 53.07 | Valid | — |
| OpenAI Responses → Bedrock | Steady-state RSS (MiB) | 193.3 | Valid | — |
| OpenAI Responses → Bedrock | Recovered RSS (MiB) | 130.7 | Valid | — |
| OpenAI Responses → Bedrock | Peak RSS (MiB) | 276.3 | Valid | — |
| OpenAI Responses → Bedrock | Peak RSS high-water mark (MiB) | 276 | Valid | — |
| OpenAI Responses → Bedrock | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Bedrock | Memory growth (MiB/min) | -105.1 | 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 | — | Not measured | — |
| OpenAI Responses → Bedrock | Idle memory static | 1 | Valid | — |
| OpenAI Responses → Bedrock | Idle memory growth (MiB/min) | 0.277 | Valid | — |
| OpenAI Responses → Bedrock | Throughput (req/s) | 1,945 | concurrency 1; n=11,672 | 1 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 4,809 | concurrency 4; n=28,860 | 5 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 5,149 | concurrency 8; n=30,902 | 10 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 5,409 | concurrency 64; n=32,459 | 50 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 5,409 | concurrency 64; n=32,459 | 100 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 5,409 | concurrency 64; n=32,459 | Unbounded |
| OpenAI → Bedrock | Added latency p50 (µs) | 450 | Valid · n=12,265 gateway / 239,336 direct | — |
| OpenAI → Bedrock | Added latency p99 (µs) | 756 | Valid · n=12,265 gateway / 239,336 direct | — |
| OpenAI → Bedrock | Gateway p99 at concurrency 1 (µs) | 787 | Valid · n=12,265 | — |
| OpenAI → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=239,336 | — |
| OpenAI → Bedrock | CPU per request (µs) | 545.4 | Valid | — |
| OpenAI → Bedrock | Requests per CPU-second | 1,833.4 | Valid | — |
| OpenAI → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI → Bedrock | Cost window core utilisation | 0.799 | Valid | — |
| OpenAI → Bedrock | Cost window successful requests | 35,275 | Valid | — |
| OpenAI → Bedrock | Cost window throughput (req/s) | 5,878 | Valid | — |
| OpenAI → Bedrock | Cost window threads | 12 | 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) | 52.4 | Valid | — |
| OpenAI → Bedrock | Steady-state RSS (MiB) | 91.29 | Valid | — |
| OpenAI → Bedrock | Recovered RSS (MiB) | 88.52 | Valid | — |
| OpenAI → Bedrock | Peak RSS (MiB) | 92.88 | Valid | — |
| OpenAI → Bedrock | Peak RSS high-water mark (MiB) | 92.66 | Valid | — |
| OpenAI → Bedrock | Time to plateau (s) | — | Not measured | — |
| OpenAI → Bedrock | Memory growth (MiB/min) | 0.289 | 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) | 0.29 | Valid | — |
| OpenAI → Bedrock | Throughput (req/s) | 2,045 | concurrency 1; n=12,274 | 1 ms |
| OpenAI → Bedrock | Throughput (req/s) | 5,862 | concurrency 8; n=35,177 | 5 ms |
| OpenAI → Bedrock | Throughput (req/s) | 5,862 | concurrency 8; n=35,177 | 10 ms |
| OpenAI → Bedrock | Throughput (req/s) | 6,347 | concurrency 64; n=38,087 | 50 ms |
| OpenAI → Bedrock | Throughput (req/s) | 6,361 | concurrency 128; n=38,177 | 100 ms |
| OpenAI → Bedrock | Throughput (req/s) | 6,361 | concurrency 128; n=38,177 | Unbounded |
| Cohere → Gemini | — | — | Not declared: recorded note 1 | — |
| Bedrock → Gemini | — | — | Not declared: recorded note 1 | — |
| Gemini → Gemini | — | — | Not declared: recorded note 1 | — |
| Anthropic → Gemini | Added latency p50 (µs) | 336 | Valid · n=16,147 gateway / 237,693 direct | — |
| Anthropic → Gemini | Added latency p99 (µs) | 499 | Valid · n=16,147 gateway / 237,693 direct | — |
| Anthropic → Gemini | Gateway p99 at concurrency 1 (µs) | 530 | Valid · n=16,147 | — |
| Anthropic → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=237,693 | — |
| Anthropic → Gemini | CPU per request (µs) | 432.5 | Valid | — |
| Anthropic → Gemini | Requests per CPU-second | 2,312.2 | Valid | — |
| Anthropic → Gemini | Cost window concurrency | 8 | Valid | — |
| Anthropic → Gemini | Cost window core utilisation | 0.683 | Valid | — |
| Anthropic → Gemini | Cost window successful requests | 38,012 | Valid | — |
| Anthropic → Gemini | Cost window throughput (req/s) | 6,334 | Valid | — |
| Anthropic → Gemini | Cost window threads | 12 | 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) | 53.18 | Valid | — |
| Anthropic → Gemini | Steady-state RSS (MiB) | 88.14 | Valid | — |
| Anthropic → Gemini | Recovered RSS (MiB) | 88.41 | Valid | — |
| Anthropic → Gemini | Peak RSS (MiB) | 90 | Valid | — |
| Anthropic → Gemini | Peak RSS high-water mark (MiB) | 89.93 | Valid | — |
| Anthropic → Gemini | Time to plateau (s) | — | Not measured | — |
| Anthropic → Gemini | Memory growth (MiB/min) | 0.25 | Valid | — |
| Anthropic → Gemini | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Gemini | Memory shape under load | 0 | Valid | — |
| Anthropic → Gemini | Idle memory shape | 0 | Valid | — |
| Anthropic → Gemini | Idle memory static | 0 | Valid | — |
| Anthropic → Gemini | Idle memory growth (MiB/min) | 0.558 | Valid | — |
| Anthropic → Gemini | Throughput (req/s) | 4,493 | concurrency 2; n=26,962 | 1 ms |
| Anthropic → Gemini | Throughput (req/s) | 6,289 | concurrency 8; n=37,743 | 5 ms |
| Anthropic → Gemini | Throughput (req/s) | 6,450 | concurrency 16; n=38,708 | 10 ms |
| Anthropic → Gemini | Throughput (req/s) | 7,092 | concurrency 64; n=42,558 | 50 ms |
| Anthropic → Gemini | Throughput (req/s) | 7,137 | concurrency 128; n=42,837 | 100 ms |
| Anthropic → Gemini | Throughput (req/s) | 7,137 | concurrency 128; n=42,837 | Unbounded |
| OpenAI Responses → Gemini | Added latency p50 (µs) | 353 | Valid · n=15,337 gateway / 250,993 direct | — |
| OpenAI Responses → Gemini | Added latency p99 (µs) | 599 | Valid · n=15,337 gateway / 250,993 direct | — |
| OpenAI Responses → Gemini | Gateway p99 at concurrency 1 (µs) | 629 | Valid · n=15,337 | — |
| OpenAI Responses → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=250,993 | — |
| OpenAI Responses → Gemini | CPU per request (µs) | 571.8 | Valid | — |
| OpenAI Responses → Gemini | Requests per CPU-second | 1,749 | Valid | — |
| OpenAI Responses → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Gemini | Cost window core utilisation | 0.855 | Valid | — |
| OpenAI Responses → Gemini | Cost window successful requests | 36,012 | Valid | — |
| OpenAI Responses → Gemini | Cost window throughput (req/s) | 6,001 | Valid | — |
| OpenAI Responses → Gemini | Cost window threads | 12 | Valid | — |
| OpenAI Responses → Gemini | Non-voluntary context switches per request | 0.017 | 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) | 53.45 | Valid | — |
| OpenAI Responses → Gemini | Steady-state RSS (MiB) | 280.7 | Valid | — |
| OpenAI Responses → Gemini | Recovered RSS (MiB) | 149.6 | Valid | — |
| OpenAI Responses → Gemini | Peak RSS (MiB) | 371.7 | Valid | — |
| OpenAI Responses → Gemini | Peak RSS high-water mark (MiB) | 371.3 | Valid | — |
| OpenAI Responses → Gemini | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Gemini | Memory growth (MiB/min) | 70.65 | Valid | — |
| OpenAI Responses → Gemini | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → Gemini | Memory shape under load | 1 | Valid | — |
| OpenAI Responses → Gemini | Idle memory shape | 0 | Valid | — |
| OpenAI Responses → Gemini | Idle memory static | 0 | Valid | — |
| OpenAI Responses → Gemini | Idle memory growth (MiB/min) | 0.665 | Valid | — |
| OpenAI Responses → Gemini | Throughput (req/s) | 4,292 | concurrency 2; n=25,758 | 1 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 5,944 | concurrency 8; n=35,670 | 5 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 5,944 | concurrency 8; n=35,670 | 10 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 6,212 | concurrency 64; n=37,277 | 50 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 6,215 | concurrency 128; n=37,303 | 100 ms |
| OpenAI Responses → Gemini | Throughput (req/s) | 6,215 | concurrency 128; n=37,303 | Unbounded |
| OpenAI → Gemini | Added latency p50 (µs) | 336 | Valid · n=16,158 gateway / 241,090 direct | — |
| OpenAI → Gemini | Added latency p99 (µs) | 508 | Valid · n=16,158 gateway / 241,090 direct | — |
| OpenAI → Gemini | Gateway p99 at concurrency 1 (µs) | 539 | Valid · n=16,158 | — |
| OpenAI → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=241,090 | — |
| OpenAI → Gemini | CPU per request (µs) | 424.6 | Valid | — |
| OpenAI → Gemini | Requests per CPU-second | 2,355.2 | Valid | — |
| OpenAI → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI → Gemini | Cost window core utilisation | 0.707 | Valid | — |
| OpenAI → Gemini | Cost window successful requests | 40,086 | Valid | — |
| OpenAI → Gemini | Cost window throughput (req/s) | 6,680 | Valid | — |
| OpenAI → Gemini | Cost window threads | 12 | 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) | 53.06 | Valid | — |
| OpenAI → Gemini | Steady-state RSS (MiB) | 87.94 | Valid | — |
| OpenAI → Gemini | Recovered RSS (MiB) | 91.47 | Valid | — |
| OpenAI → Gemini | Peak RSS (MiB) | 91.51 | Valid | — |
| OpenAI → Gemini | Peak RSS high-water mark (MiB) | 89.38 | Valid | — |
| OpenAI → Gemini | Time to plateau (s) | — | Not measured | — |
| OpenAI → Gemini | Memory growth (MiB/min) | 0.081 | Valid | — |
| OpenAI → Gemini | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Gemini | Memory shape under load | 0 | Valid | — |
| OpenAI → Gemini | Idle memory shape | 0 | Valid | — |
| OpenAI → Gemini | Idle memory static | 0 | Valid | — |
| OpenAI → Gemini | Idle memory growth (MiB/min) | 0.486 | Valid | — |
| OpenAI → Gemini | Throughput (req/s) | 4,561 | concurrency 2; n=27,372 | 1 ms |
| OpenAI → Gemini | Throughput (req/s) | 6,538 | concurrency 8; n=39,236 | 5 ms |
| OpenAI → Gemini | Throughput (req/s) | 6,721 | concurrency 16; n=40,333 | 10 ms |
| OpenAI → Gemini | Throughput (req/s) | 7,332 | concurrency 64; n=43,996 | 50 ms |
| OpenAI → Gemini | Throughput (req/s) | 7,393 | concurrency 128; n=44,369 | 100 ms |
| OpenAI → Gemini | Throughput (req/s) | 7,393 | concurrency 128; n=44,369 | Unbounded |
| Anthropic → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI Responses | Added latency p50 (µs) | 363 | Valid · n=15,015 gateway / 246,146 direct | — |
| OpenAI Responses → OpenAI Responses | Added latency p99 (µs) | 591 | Valid · n=15,015 gateway / 246,146 direct | — |
| OpenAI Responses → OpenAI Responses | Gateway p99 at concurrency 1 (µs) | 621 | Valid · n=15,015 | — |
| OpenAI Responses → OpenAI Responses | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=246,146 | — |
| OpenAI Responses → OpenAI Responses | CPU per request (µs) | 577.7 | Valid | — |
| OpenAI Responses → OpenAI Responses | Requests per CPU-second | 1,731 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window core utilisation | 0.856 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window successful requests | 35,675 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window throughput (req/s) | 5,945 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window threads | 12 | 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) | 52.82 | Valid | — |
| OpenAI Responses → OpenAI Responses | Steady-state RSS (MiB) | 224.9 | Valid | — |
| OpenAI Responses → OpenAI Responses | Recovered RSS (MiB) | 125.7 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS (MiB) | 326.3 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS high-water mark (MiB) | 326 | Valid | — |
| OpenAI Responses → OpenAI Responses | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → OpenAI Responses | Memory growth (MiB/min) | 27.23 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory shape under load | 1 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory shape | — | Not measured | — |
| OpenAI Responses → OpenAI Responses | Idle memory static | 1 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory growth (MiB/min) | 0.309 | Valid | — |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 2,485 | concurrency 1; n=14,918 | 1 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 5,918 | concurrency 8; n=35,519 | 5 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 5,918 | concurrency 8; n=35,519 | 10 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,295 | concurrency 64; n=37,775 | 50 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,295 | concurrency 64; n=37,775 | 100 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,295 | concurrency 64; n=37,775 | 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 | — |
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 |
|---|---|---|---|---|---|---|---|
| Cohere → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI → Anthropic | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| OpenAI Responses → Anthropic | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Bedrock → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Gemini → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Anthropic → Anthropic | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Bedrock → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Cohere → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI Responses → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Gemini → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Anthropic → OpenAI | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| OpenAI → OpenAI | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Gemini → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI Responses → Cohere | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Anthropic → Cohere | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Cohere → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Bedrock → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI → Cohere | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Anthropic → Bedrock | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Cohere → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Gemini → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Bedrock → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI Responses → Bedrock | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| OpenAI → Bedrock | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Cohere → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Bedrock → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Gemini → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Anthropic → Gemini | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| OpenAI Responses → Gemini | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| OpenAI → Gemini | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Anthropic → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| OpenAI Responses → OpenAI Responses | Served | — | — | — | Recorded run evidence | — | enterpilot/gomodel:0.2.3 |
| Gemini → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Cohere → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
| Bedrock → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | enterpilot/gomodel:0.2.3 |
- 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 | 2,048 | HTTP 200: 2,048 | 0 |
| OpenAI → Anthropic | 1,536 | HTTP 200: 1,536 | 0 |
| OpenAI → Anthropic | 1,280 | HTTP 200: 1,280 | 0 |
| OpenAI → Anthropic | 1,152 | HTTP 200: 1,152 | 0 |
| OpenAI → Anthropic | 1,088 | HTTP 200: 1,088 | 0 |
| OpenAI → Anthropic | 1,120 | HTTP 200: 1,120 | 0 |
| OpenAI → Anthropic | 1,136 | HTTP 200: 1,136 | 0 |
| OpenAI → Anthropic | 1,144 | HTTP 200: 1,144 | 0 |
| OpenAI → Anthropic | 1,140 | HTTP 200: 1,140 | 0 |
| OpenAI → Anthropic | 1,142 | HTTP 200: 1,142 | 0 |
| OpenAI → Anthropic | 1,141 | HTTP 200: 1,141 | 0 |
| OpenAI → Anthropic | 1,140 | HTTP 200: 1,140 | 0 |
| OpenAI → Anthropic | 1,140 | HTTP 200: 1,140 | 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 | 2,048 | HTTP 200: 2,048 | 0 |
| Anthropic → Anthropic | 1,536 | HTTP 200: 1,536 | 0 |
| Anthropic → Anthropic | 1,792 | HTTP 200: 1,792 | 0 |
| Anthropic → Anthropic | 1,664 | HTTP 200: 1,664 | 0 |
| Anthropic → Anthropic | 1,600 | HTTP 200: 1,600 | 0 |
| Anthropic → Anthropic | 1,568 | HTTP 200: 1,568 | 0 |
| Anthropic → Anthropic | 1,552 | HTTP 200: 1,552 | 0 |
| Anthropic → Anthropic | 1,560 | HTTP 200: 1,560 | 0 |
| Anthropic → Anthropic | 1,556 | HTTP 200: 1,556 | 0 |
| Anthropic → Anthropic | 1,558 | HTTP 200: 1,558 | 0 |
| Anthropic → Anthropic | 1,559 | HTTP 200: 1,559 | 0 |
| Anthropic → Anthropic | 1,559 | HTTP 200: 1,559 | 0 |
| Anthropic → Anthropic | 1,559 | HTTP 200: 1,559 | 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 | 2,048 | HTTP 200: 2,048 | 0 |
| Anthropic → OpenAI | 1,536 | HTTP 200: 1,536 | 0 |
| Anthropic → OpenAI | 1,792 | HTTP 200: 1,792 | 0 |
| Anthropic → OpenAI | 1,664 | HTTP 200: 1,664 | 0 |
| Anthropic → OpenAI | 1,600 | HTTP 200: 1,600 | 0 |
| Anthropic → OpenAI | 1,568 | HTTP 200: 1,568 | 0 |
| Anthropic → OpenAI | 1,552 | HTTP 200: 1,552 | 0 |
| Anthropic → OpenAI | 1,544 | HTTP 200: 1,544 | 0 |
| Anthropic → OpenAI | 1,540 | HTTP 200: 1,540 | 0 |
| Anthropic → OpenAI | 1,538 | HTTP 200: 1,538 | 0 |
| Anthropic → OpenAI | 1,537 | HTTP 200: 1,537 | 0 |
| Anthropic → OpenAI | 1,536 | HTTP 200: 1,536 | 0 |
| Anthropic → OpenAI | 1,536 | HTTP 200: 1,536 | 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 | 2,048 | HTTP 200: 2,048 | 0 |
| OpenAI → OpenAI | 1,536 | HTTP 200: 1,536 | 0 |
| OpenAI → OpenAI | 1,280 | HTTP 200: 1,280 | 0 |
| OpenAI → OpenAI | 1,152 | HTTP 200: 1,152 | 0 |
| OpenAI → OpenAI | 1,216 | HTTP 200: 1,216 | 0 |
| OpenAI → OpenAI | 1,184 | HTTP 200: 1,184 | 0 |
| OpenAI → OpenAI | 1,200 | HTTP 200: 1,200 | 0 |
| OpenAI → OpenAI | 1,208 | HTTP 200: 1,208 | 0 |
| OpenAI → OpenAI | 1,212 | HTTP 200: 1,212 | 0 |
| OpenAI → OpenAI | 1,210 | HTTP 200: 1,210 | 0 |
| OpenAI → OpenAI | 1,209 | HTTP 200: 1,209 | 0 |
| OpenAI → OpenAI | 1,208 | HTTP 200: 1,208 | 0 |
| OpenAI → OpenAI | 1,208 | HTTP 200: 1,208 | 0 |
Recorded notes
Text recorded with the cells above. Each note is shown once; rows refer to it by number.
- GoModel v0.2.3 source 86dbeffc254e0166367d72e0404f5a27aceeeaaa: local single-request checks using the engine's request bodies and authentication headers establish 16 exact protocol pairs; 15 are enabled on the pinned image. The 0.2.3 default configured-model allowlist remains enabled; no legacy fallback override is applied. OpenAI CompatibleProvider uses Chat Completions for chat/messages ingress and native Responses for responses ingress; the other OpenAI cross-operation cells do not select the requested upstream wire. Cohere supports translated chat/responses/messages. Native Cohere passthrough is opt-in (not in the default ENABLED_PASSTHROUGH_PROVIDERS), so cohere>cohere is not configured under the benchmark's out-of-the-box rule. Gemini and Bedrock implement upstream adapters but no native ingress/passthrough interface. These checks verify protocol routing only, not performance. Evidence: results/diagnostics/refresh-configuration/gomodel-0.2.3-correctness-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-gomodel-f6e038780b29f86549f840f902ac96740154f0f0ef2a66a3fd9dcd4bc3b83bad · complete raw record including RSS series
Configuration recorded by the run
Not recorded.
Compare a shared protocol cell
- GoModel vs agentgateway
- GoModel vs AISIX (api7)
- GoModel vs APISIX
- GoModel vs Bifrost
- GoModel vs Busbar
- GoModel vs Helicone
- GoModel vs Higress
- GoModel vs Kong
- GoModel vs LiteLLM · Python
- GoModel vs LiteLLM · Rust
- GoModel vs One-API
- GoModel vs Plano
- GoModel vs Portkey
- GoModel vs TensorZero