Higress 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.
Other · recorded build: higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5. 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 → Cohere | Added latency p50 (µs) | 615 | Valid · n=9,341 gateway / 267,984 direct | — |
| Cohere → Cohere | Added latency p99 (µs) | 747 | Valid · n=9,341 gateway / 267,984 direct | — |
| Cohere → Cohere | Gateway p99 at concurrency 1 (µs) | 774 | Valid · n=9,341 | — |
| Cohere → Cohere | Direct-to-mock p99 at concurrency 1 (µs) | 27 | Valid · n=267,984 | — |
| Cohere → Cohere | CPU per request (µs) | 613.2 | Valid | — |
| Cohere → Cohere | Requests per CPU-second | 1,630.7 | Valid | — |
| Cohere → Cohere | Cost window concurrency | 8 | Valid | — |
| Cohere → Cohere | Cost window core utilisation | 0.805 | Valid | — |
| Cohere → Cohere | Cost window successful requests | 31,620 | Valid | — |
| Cohere → Cohere | Cost window throughput (req/s) | 5,269 | Valid | — |
| Cohere → Cohere | Cost window threads | 143 | Valid | — |
| Cohere → Cohere | Non-voluntary context switches per request | 0.008 | Valid | — |
| Cohere → Cohere | Cost window major page faults | 0 | Valid | — |
| Cohere → Cohere | Added time to first event p50 (µs) | — | Untestable | — |
| Cohere → Cohere | Added time to first event p99 (µs) | — | Untestable | — |
| Cohere → Cohere | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Cohere → Cohere | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Cohere → Cohere | Streams sustained (frames/s) | — | Untestable | — |
| Cohere → Cohere | Streams sustained | — | Untestable | — |
| Cohere → Cohere | Idle RSS (MiB) | 1,207.9 | Valid | — |
| Cohere → Cohere | Steady-state RSS (MiB) | 1,217.3 | Valid | — |
| Cohere → Cohere | Recovered RSS (MiB) | 1,218.4 | Valid | — |
| Cohere → Cohere | Peak RSS (MiB) | 1,226.8 | Valid | — |
| Cohere → Cohere | Peak RSS high-water mark (MiB) | 1,324.4 | Valid | — |
| Cohere → Cohere | Time to plateau (s) | 60 | Valid | — |
| Cohere → Cohere | Memory growth (MiB/min) | 0.748 | Valid | — |
| Cohere → Cohere | Memory load duration (s) | 300 | Valid | — |
| Cohere → Cohere | Memory shape under load | — | Not measured | — |
| Cohere → Cohere | Idle memory shape | — | Not measured | — |
| Cohere → Cohere | Idle memory static | 1 | Valid | — |
| Cohere → Cohere | Idle memory growth (MiB/min) | 1.03 | Valid | — |
| Cohere → Cohere | Throughput (req/s) | 3,092 | concurrency 2; n=18,555 | 1 ms |
| Cohere → Cohere | Throughput (req/s) | 5,921 | concurrency 8; n=35,536 | 5 ms |
| Cohere → Cohere | Throughput (req/s) | 6,529 | concurrency 32; n=39,189 | 10 ms |
| Cohere → Cohere | Throughput (req/s) | 6,633 | concurrency 64; n=39,805 | 50 ms |
| Cohere → Cohere | Throughput (req/s) | 6,633 | concurrency 64; n=39,805 | 100 ms |
| Cohere → Cohere | Throughput (req/s) | 6,633 | concurrency 64; n=39,805 | Unbounded |
| Bedrock → Cohere | — | — | Not declared: recorded note 1 | — |
| Gemini → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI → Cohere | — | — | Not served: probed and answered HTTP 200, but the body is not a usable openai response (see body_snippet) | — |
| Anthropic → Cohere | — | — | Not served: probed and answered HTTP 200, but the body is not a usable anthropic response (see body_snippet) | — |
| OpenAI Responses → Cohere | — | — | Not declared: recorded note 1 | — |
| Cohere → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI → Anthropic | Added latency p50 (µs) | 859 | Valid · n=6,739 gateway / 262,868 direct | — |
| OpenAI → Anthropic | Added latency p99 (µs) | 1,112 | Valid · n=6,739 gateway / 262,868 direct | — |
| OpenAI → Anthropic | Gateway p99 at concurrency 1 (µs) | 1,140 | Valid · n=6,739 | — |
| OpenAI → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=262,868 | — |
| OpenAI → Anthropic | CPU per request (µs) | 882.4 | Valid | — |
| OpenAI → Anthropic | Requests per CPU-second | 1,133.2 | Valid | — |
| OpenAI → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI → Anthropic | Cost window core utilisation | 0.98 | Valid | — |
| OpenAI → Anthropic | Cost window successful requests | 26,744 | Valid | — |
| OpenAI → Anthropic | Cost window throughput (req/s) | 4,456 | Valid | — |
| OpenAI → Anthropic | Cost window threads | 145 | Valid | — |
| OpenAI → Anthropic | Non-voluntary context switches per request | 0.001 | Valid | — |
| OpenAI → Anthropic | Cost window major page faults | 0 | Valid | — |
| OpenAI → Anthropic | Added time to first event p50 (µs) | 1,095 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added time to first event p99 (µs) | 1,556 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p50 (µs) | 8 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p99 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Streams sustained (frames/s) | 23,656.6 | Valid | — |
| OpenAI → Anthropic | Streams sustained | 5,767 | Valid | — |
| OpenAI → Anthropic | Idle RSS (MiB) | 1,148.4 | Valid | — |
| OpenAI → Anthropic | Steady-state RSS (MiB) | 1,158.9 | Valid | — |
| OpenAI → Anthropic | Recovered RSS (MiB) | 1,159.8 | Valid | — |
| OpenAI → Anthropic | Peak RSS (MiB) | 1,167.3 | Valid | — |
| OpenAI → Anthropic | Peak RSS high-water mark (MiB) | 1,264.9 | Valid | — |
| OpenAI → Anthropic | Time to plateau (s) | 60 | Valid | — |
| OpenAI → Anthropic | Memory growth (MiB/min) | 0.702 | Valid | — |
| OpenAI → Anthropic | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Anthropic | Memory shape under load | — | Not measured | — |
| OpenAI → Anthropic | Idle memory shape | — | Not measured | — |
| OpenAI → Anthropic | Idle memory static | 1 | Valid | — |
| OpenAI → Anthropic | Idle memory growth (MiB/min) | 0.889 | Valid | — |
| OpenAI → Anthropic | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| OpenAI → Anthropic | Throughput (req/s) | 4,788 | concurrency 16; n=28,736 | 5 ms |
| OpenAI → Anthropic | Throughput (req/s) | 4,909 | concurrency 32; n=29,464 | 10 ms |
| OpenAI → Anthropic | Throughput (req/s) | 4,944 | concurrency 64; n=29,673 | 50 ms |
| OpenAI → Anthropic | Throughput (req/s) | 4,944 | concurrency 64; n=29,673 | 100 ms |
| OpenAI → Anthropic | Throughput (req/s) | 4,944 | concurrency 64; n=29,673 | Unbounded |
| Bedrock → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Anthropic | — | — | Not declared: recorded note 1 | — |
| Anthropic → Anthropic | Added latency p50 (µs) | 680 | Valid · n=8,481 gateway / 262,245 direct | — |
| Anthropic → Anthropic | Added latency p99 (µs) | 822 | Valid · n=8,481 gateway / 262,245 direct | — |
| Anthropic → Anthropic | Gateway p99 at concurrency 1 (µs) | 850 | Valid · n=8,481 | — |
| Anthropic → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=262,245 | — |
| Anthropic → Anthropic | CPU per request (µs) | 674.8 | Valid | — |
| Anthropic → Anthropic | Requests per CPU-second | 1,481.9 | Valid | — |
| Anthropic → Anthropic | Cost window concurrency | 8 | Valid | — |
| Anthropic → Anthropic | Cost window core utilisation | 0.977 | Valid | — |
| Anthropic → Anthropic | Cost window successful requests | 34,868 | Valid | — |
| Anthropic → Anthropic | Cost window throughput (req/s) | 5,810 | Valid | — |
| Anthropic → Anthropic | Cost window threads | 144 | Valid | — |
| Anthropic → Anthropic | Non-voluntary context switches per request | 0.002 | Valid | — |
| Anthropic → Anthropic | Cost window major page faults | 0 | Valid | — |
| Anthropic → Anthropic | Added time to first event p50 (µs) | 822 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added time to first event p99 (µs) | 1,012 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p50 (µs) | 0 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p99 (µs) | 35 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Streams sustained (frames/s) | 52,509.7 | Valid | — |
| Anthropic → Anthropic | Streams sustained | 16,391 | Valid | — |
| Anthropic → Anthropic | Idle RSS (MiB) | 1,153.9 | Valid | — |
| Anthropic → Anthropic | Steady-state RSS (MiB) | 1,161.8 | Valid | — |
| Anthropic → Anthropic | Recovered RSS (MiB) | 1,162.2 | Valid | — |
| Anthropic → Anthropic | Peak RSS (MiB) | 1,171.8 | Valid | — |
| Anthropic → Anthropic | Peak RSS high-water mark (MiB) | 1,272.5 | Valid | — |
| Anthropic → Anthropic | Time to plateau (s) | 60 | Valid | — |
| Anthropic → Anthropic | Memory growth (MiB/min) | 0.275 | Valid | — |
| Anthropic → Anthropic | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Anthropic | Memory shape under load | — | Not measured | — |
| Anthropic → Anthropic | Idle memory shape | — | Not measured | — |
| Anthropic → Anthropic | Idle memory static | 1 | Valid | — |
| Anthropic → Anthropic | Idle memory growth (MiB/min) | 0.582 | Valid | — |
| Anthropic → Anthropic | Throughput (req/s) | 1,352 | concurrency 1; n=8,115 | 1 ms |
| Anthropic → Anthropic | Throughput (req/s) | 5,967 | concurrency 16; n=35,809 | 5 ms |
| Anthropic → Anthropic | Throughput (req/s) | 6,123 | concurrency 32; n=36,743 | 10 ms |
| Anthropic → Anthropic | Throughput (req/s) | 6,224 | concurrency 128; n=37,352 | 50 ms |
| Anthropic → Anthropic | Throughput (req/s) | 6,224 | concurrency 128; n=37,352 | 100 ms |
| Anthropic → Anthropic | Throughput (req/s) | 6,224 | concurrency 128; n=37,352 | Unbounded |
| OpenAI → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Bedrock → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI Responses | Added latency p50 (µs) | 642 | Valid · n=8,971 gateway / 260,207 direct | — |
| OpenAI Responses → OpenAI Responses | Added latency p99 (µs) | 747 | Valid · n=8,971 gateway / 260,207 direct | — |
| OpenAI Responses → OpenAI Responses | Gateway p99 at concurrency 1 (µs) | 775 | Valid · n=8,971 | — |
| OpenAI Responses → OpenAI Responses | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=260,207 | — |
| OpenAI Responses → OpenAI Responses | CPU per request (µs) | 633.8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Requests per CPU-second | 1,577.8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window core utilisation | 0.986 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window successful requests | 37,457 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window throughput (req/s) | 6,242 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window threads | 141 | Valid | — |
| OpenAI Responses → OpenAI Responses | Non-voluntary context switches per request | 0.001 | 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) | 1,147.2 | Valid | — |
| OpenAI Responses → OpenAI Responses | Steady-state RSS (MiB) | 1,156.6 | Valid | — |
| OpenAI Responses → OpenAI Responses | Recovered RSS (MiB) | 1,157.9 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS (MiB) | 1,165.5 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS high-water mark (MiB) | 1,186.6 | Valid | — |
| OpenAI Responses → OpenAI Responses | Time to plateau (s) | 66 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory growth (MiB/min) | 0.599 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory shape under load | — | Not measured | — |
| 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) | 0.697 | Valid | — |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 2,925 | concurrency 2; n=17,553 | 1 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,438 | concurrency 16; n=38,636 | 5 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,717 | concurrency 32; n=40,311 | 10 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,791 | concurrency 128; n=40,754 | 50 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,791 | concurrency 128; n=40,754 | 100 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 6,791 | concurrency 128; n=40,754 | Unbounded |
| Anthropic → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI → Gemini | Added latency p50 (µs) | 923 | Valid · n=6,239 gateway / 265,561 direct | — |
| OpenAI → Gemini | Added latency p99 (µs) | 1,226 | Valid · n=6,239 gateway / 265,561 direct | — |
| OpenAI → Gemini | Gateway p99 at concurrency 1 (µs) | 1,254 | Valid · n=6,239 | — |
| OpenAI → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=265,561 | — |
| OpenAI → Gemini | CPU per request (µs) | 951.7 | Valid | — |
| OpenAI → Gemini | Requests per CPU-second | 1,050.8 | Valid | — |
| OpenAI → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI → Gemini | Cost window core utilisation | 0.751 | Valid | — |
| OpenAI → Gemini | Cost window successful requests | 19,009 | Valid | — |
| OpenAI → Gemini | Cost window throughput (req/s) | 3,167 | Valid | — |
| OpenAI → Gemini | Cost window threads | 141 | Valid | — |
| OpenAI → Gemini | Non-voluntary context switches per request | 0.011 | 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) | 1,150.6 | Valid | — |
| OpenAI → Gemini | Steady-state RSS (MiB) | 1,160.3 | Valid | — |
| OpenAI → Gemini | Recovered RSS (MiB) | 1,160.6 | Valid | — |
| OpenAI → Gemini | Peak RSS (MiB) | 1,170.9 | Valid | — |
| OpenAI → Gemini | Peak RSS high-water mark (MiB) | 1,268.9 | Valid | — |
| OpenAI → Gemini | Time to plateau (s) | 60 | Valid | — |
| OpenAI → Gemini | Memory growth (MiB/min) | 0.259 | Valid | — |
| OpenAI → Gemini | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Gemini | Memory shape under load | — | Not measured | — |
| OpenAI → Gemini | Idle memory shape | — | Not measured | — |
| OpenAI → Gemini | Idle memory static | 1 | Valid | — |
| OpenAI → Gemini | Idle memory growth (MiB/min) | 0.605 | Valid | — |
| OpenAI → Gemini | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| OpenAI → Gemini | Throughput (req/s) | 4,171 | concurrency 8; n=25,035 | 5 ms |
| OpenAI → Gemini | Throughput (req/s) | 4,327 | concurrency 16; n=25,969 | 10 ms |
| OpenAI → Gemini | Throughput (req/s) | 4,449 | concurrency 64; n=26,699 | 50 ms |
| OpenAI → Gemini | Throughput (req/s) | 4,449 | concurrency 64; n=26,699 | 100 ms |
| OpenAI → Gemini | Throughput (req/s) | 4,449 | concurrency 64; n=26,699 | Unbounded |
| Gemini → Gemini | Added latency p50 (µs) | 750 | Valid · n=7,714 gateway / 265,544 direct | — |
| Gemini → Gemini | Added latency p99 (µs) | 932 | Valid · n=7,714 gateway / 265,544 direct | — |
| Gemini → Gemini | Gateway p99 at concurrency 1 (µs) | 959 | Valid · n=7,714 | — |
| Gemini → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 27 | Valid · n=265,544 | — |
| Gemini → Gemini | CPU per request (µs) | 737.7 | Valid | — |
| Gemini → Gemini | Requests per CPU-second | 1,355.5 | Valid | — |
| Gemini → Gemini | Cost window concurrency | 8 | Valid | — |
| Gemini → Gemini | Cost window core utilisation | 0.743 | Valid | — |
| Gemini → Gemini | Cost window successful requests | 24,237 | Valid | — |
| Gemini → Gemini | Cost window throughput (req/s) | 4,038 | Valid | — |
| Gemini → Gemini | Cost window threads | 140 | Valid | — |
| Gemini → Gemini | Non-voluntary context switches per request | 0.007 | Valid | — |
| Gemini → Gemini | Cost window major page faults | 0 | Valid | — |
| Gemini → Gemini | Added time to first event p50 (µs) | — | Untestable | — |
| Gemini → Gemini | Added time to first event p99 (µs) | — | Untestable | — |
| Gemini → Gemini | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Gemini → Gemini | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Gemini → Gemini | Streams sustained (frames/s) | — | Untestable | — |
| Gemini → Gemini | Streams sustained | — | Untestable | — |
| Gemini → Gemini | Idle RSS (MiB) | 1,156.9 | Valid | — |
| Gemini → Gemini | Steady-state RSS (MiB) | 1,165.8 | Valid | — |
| Gemini → Gemini | Recovered RSS (MiB) | 1,166.6 | Valid | — |
| Gemini → Gemini | Peak RSS (MiB) | 1,175.8 | Valid | — |
| Gemini → Gemini | Peak RSS high-water mark (MiB) | 1,269.3 | Valid | — |
| Gemini → Gemini | Time to plateau (s) | 66 | Valid | — |
| Gemini → Gemini | Memory growth (MiB/min) | 1.08 | Valid | — |
| Gemini → Gemini | Memory load duration (s) | 300 | Valid | — |
| Gemini → Gemini | Memory shape under load | — | Not measured | — |
| Gemini → Gemini | Idle memory shape | — | Not measured | — |
| Gemini → Gemini | Idle memory static | 1 | Valid | — |
| Gemini → Gemini | Idle memory growth (MiB/min) | 0.895 | Valid | — |
| Gemini → Gemini | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| Gemini → Gemini | Throughput (req/s) | 5,241 | concurrency 16; n=31,452 | 5 ms |
| Gemini → Gemini | Throughput (req/s) | 5,428 | concurrency 32; n=32,577 | 10 ms |
| Gemini → Gemini | Throughput (req/s) | 5,506 | concurrency 64; n=33,045 | 50 ms |
| Gemini → Gemini | Throughput (req/s) | 5,506 | concurrency 64; n=33,045 | 100 ms |
| Gemini → Gemini | Throughput (req/s) | 5,506 | concurrency 64; n=33,045 | Unbounded |
| Bedrock → Gemini | — | — | Not declared: recorded note 1 | — |
| Cohere → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Gemini | — | — | Not declared: recorded note 1 | — |
| Anthropic → Gemini | Added latency p50 (µs) | 1,045 | Valid · n=5,488 gateway / 262,925 direct | — |
| Anthropic → Gemini | Added latency p99 (µs) | 1,360 | Valid · n=5,488 gateway / 262,925 direct | — |
| Anthropic → Gemini | Gateway p99 at concurrency 1 (µs) | 1,388 | Valid · n=5,488 | — |
| Anthropic → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=262,925 | — |
| Anthropic → Gemini | CPU per request (µs) | 1,055.3 | Valid | — |
| Anthropic → Gemini | Requests per CPU-second | 947.6 | Valid | — |
| Anthropic → Gemini | Cost window concurrency | 8 | Valid | — |
| Anthropic → Gemini | Cost window core utilisation | 0.744 | Valid | — |
| Anthropic → Gemini | Cost window successful requests | 16,971 | Valid | — |
| Anthropic → Gemini | Cost window throughput (req/s) | 2,828 | Valid | — |
| Anthropic → Gemini | Cost window threads | 142 | Valid | — |
| Anthropic → Gemini | Non-voluntary context switches per request | 0.01 | 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) | 1,151.5 | Valid | — |
| Anthropic → Gemini | Steady-state RSS (MiB) | 1,164.6 | Valid | — |
| Anthropic → Gemini | Recovered RSS (MiB) | 1,165.8 | Valid | — |
| Anthropic → Gemini | Peak RSS (MiB) | 1,173.3 | Valid | — |
| Anthropic → Gemini | Peak RSS high-water mark (MiB) | 1,280.2 | Valid | — |
| Anthropic → Gemini | Time to plateau (s) | 60 | Valid | — |
| Anthropic → Gemini | Memory growth (MiB/min) | 1.17 | Valid | — |
| Anthropic → Gemini | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Gemini | Memory shape under load | — | Not measured | — |
| Anthropic → Gemini | Idle memory shape | — | Not measured | — |
| Anthropic → Gemini | Idle memory static | 1 | Valid | — |
| Anthropic → Gemini | Idle memory growth (MiB/min) | 1.21 | Valid | — |
| Anthropic → Gemini | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| Anthropic → Gemini | Throughput (req/s) | 3,821 | concurrency 8; n=22,929 | 5 ms |
| Anthropic → Gemini | Throughput (req/s) | 3,862 | concurrency 16; n=23,185 | 10 ms |
| Anthropic → Gemini | Throughput (req/s) | 3,961 | concurrency 64; n=23,771 | 50 ms |
| Anthropic → Gemini | Throughput (req/s) | 3,961 | concurrency 64; n=23,771 | 100 ms |
| Anthropic → Gemini | Throughput (req/s) | 3,961 | concurrency 64; n=23,771 | Unbounded |
| OpenAI Responses → Bedrock | — | — | Not declared: recorded note 1 | — |
| Gemini → Bedrock | — | — | Not declared: recorded note 1 | — |
| Cohere → Bedrock | — | — | Not declared: recorded note 1 | — |
| Bedrock → Bedrock | Added latency p50 (µs) | 727 | Valid · n=7,954 gateway / 263,620 direct | — |
| Bedrock → Bedrock | Added latency p99 (µs) | 861 | Valid · n=7,954 gateway / 263,620 direct | — |
| Bedrock → Bedrock | Gateway p99 at concurrency 1 (µs) | 889 | Valid · n=7,954 | — |
| Bedrock → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=263,620 | — |
| Bedrock → Bedrock | CPU per request (µs) | 778.2 | Valid | — |
| Bedrock → Bedrock | Requests per CPU-second | 1,285.1 | Valid | — |
| Bedrock → Bedrock | Cost window concurrency | 8 | Valid | — |
| Bedrock → Bedrock | Cost window core utilisation | 0.97 | Valid | — |
| Bedrock → Bedrock | Cost window successful requests | 30,007 | Valid | — |
| Bedrock → Bedrock | Cost window throughput (req/s) | 5,000 | Valid | — |
| Bedrock → Bedrock | Cost window threads | 143 | Valid | — |
| Bedrock → Bedrock | Non-voluntary context switches per request | 0.005 | Valid | — |
| Bedrock → Bedrock | Cost window major page faults | 0 | Valid | — |
| Bedrock → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| Bedrock → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| Bedrock → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Bedrock → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Bedrock → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| Bedrock → Bedrock | Streams sustained | — | Untestable | — |
| Bedrock → Bedrock | Idle RSS (MiB) | 1,157.4 | Valid | — |
| Bedrock → Bedrock | Steady-state RSS (MiB) | 1,165.7 | Valid | — |
| Bedrock → Bedrock | Recovered RSS (MiB) | 1,167.4 | Valid | — |
| Bedrock → Bedrock | Peak RSS (MiB) | 1,175.8 | Valid | — |
| Bedrock → Bedrock | Peak RSS high-water mark (MiB) | 1,275.2 | Valid | — |
| Bedrock → Bedrock | Time to plateau (s) | 60 | Valid | — |
| Bedrock → Bedrock | Memory growth (MiB/min) | 0.69 | Valid | — |
| Bedrock → Bedrock | Memory load duration (s) | 300 | Valid | — |
| Bedrock → Bedrock | Memory shape under load | — | Not measured | — |
| Bedrock → Bedrock | Idle memory shape | — | Not measured | — |
| Bedrock → Bedrock | Idle memory static | 1 | Valid | — |
| Bedrock → Bedrock | Idle memory growth (MiB/min) | 0.692 | Valid | — |
| Bedrock → Bedrock | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| Bedrock → Bedrock | Throughput (req/s) | 4,996 | concurrency 8; n=29,985 | 5 ms |
| Bedrock → Bedrock | Throughput (req/s) | 5,179 | concurrency 16; n=31,083 | 10 ms |
| Bedrock → Bedrock | Throughput (req/s) | 5,403 | concurrency 64; n=32,432 | 50 ms |
| Bedrock → Bedrock | Throughput (req/s) | 5,403 | concurrency 64; n=32,432 | 100 ms |
| Bedrock → Bedrock | Throughput (req/s) | 5,403 | concurrency 64; n=32,432 | Unbounded |
| OpenAI → Bedrock | Added latency p50 (µs) | 929 | Valid · n=6,162 gateway / 262,294 direct | — |
| OpenAI → Bedrock | Added latency p99 (µs) | 1,235 | Valid · n=6,162 gateway / 262,294 direct | — |
| OpenAI → Bedrock | Gateway p99 at concurrency 1 (µs) | 1,263 | Valid · n=6,162 | — |
| OpenAI → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=262,294 | — |
| OpenAI → Bedrock | CPU per request (µs) | 912.3 | Valid | — |
| OpenAI → Bedrock | Requests per CPU-second | 1,096.1 | Valid | — |
| OpenAI → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI → Bedrock | Cost window core utilisation | 0.751 | Valid | — |
| OpenAI → Bedrock | Cost window successful requests | 19,828 | Valid | — |
| OpenAI → Bedrock | Cost window throughput (req/s) | 3,304 | Valid | — |
| OpenAI → Bedrock | Cost window threads | 144 | Valid | — |
| OpenAI → Bedrock | Non-voluntary context switches per request | 0.008 | 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) | 1,158.7 | Valid | — |
| OpenAI → Bedrock | Steady-state RSS (MiB) | 1,172.1 | Valid | — |
| OpenAI → Bedrock | Recovered RSS (MiB) | 1,174 | Valid | — |
| OpenAI → Bedrock | Peak RSS (MiB) | 1,179.9 | Valid | — |
| OpenAI → Bedrock | Peak RSS high-water mark (MiB) | 1,198.7 | Valid | — |
| OpenAI → Bedrock | Time to plateau (s) | 60 | Valid | — |
| OpenAI → Bedrock | Memory growth (MiB/min) | 0.931 | Valid | — |
| OpenAI → Bedrock | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Bedrock | Memory shape under load | — | Not measured | — |
| OpenAI → Bedrock | Idle memory shape | — | Not measured | — |
| OpenAI → Bedrock | Idle memory static | 1 | Valid | — |
| OpenAI → Bedrock | Idle memory growth (MiB/min) | 1.08 | Valid | — |
| OpenAI → Bedrock | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| OpenAI → Bedrock | Throughput (req/s) | 4,316 | concurrency 8; n=25,900 | 5 ms |
| OpenAI → Bedrock | Throughput (req/s) | 4,440 | concurrency 16; n=26,646 | 10 ms |
| OpenAI → Bedrock | Throughput (req/s) | 4,587 | concurrency 64; n=27,530 | 50 ms |
| OpenAI → Bedrock | Throughput (req/s) | 4,587 | concurrency 64; n=27,530 | 100 ms |
| OpenAI → Bedrock | Throughput (req/s) | 4,587 | concurrency 64; n=27,530 | Unbounded |
| Anthropic → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI | Added latency p50 (µs) | 718 | Valid · n=7,996 gateway / 262,593 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 943 | Valid · n=7,996 gateway / 262,593 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 971 | Valid · n=7,996 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=262,593 | — |
| OpenAI → OpenAI | CPU per request (µs) | 709.3 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 1,409.8 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.733 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 24,883 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 4,146 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 142 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0.008 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 881 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 1,103 | 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) | 52,911.8 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 1,688 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 1,163.5 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 1,170.9 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 1,172 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 1,181.8 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 1,287.1 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 66 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.896 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | — | Not measured | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.606 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 2,688 | concurrency 2; n=16,131 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 5,685 | concurrency 8; n=34,120 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 6,095 | concurrency 32; n=36,576 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 6,138 | concurrency 64; n=36,832 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 6,138 | concurrency 64; n=36,832 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 6,138 | concurrency 64; n=36,832 | Unbounded |
| Gemini → OpenAI | — | — | Not declared: recorded note 1 | — |
| Bedrock → OpenAI | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI | — | — | Not declared: recorded note 1 | — |
| Anthropic → OpenAI | Added latency p50 (µs) | 954 | Valid · n=6,058 gateway / 259,722 direct | — |
| Anthropic → OpenAI | Added latency p99 (µs) | 1,252 | Valid · n=6,058 gateway / 259,722 direct | — |
| Anthropic → OpenAI | Gateway p99 at concurrency 1 (µs) | 1,280 | Valid · n=6,058 | — |
| Anthropic → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=259,722 | — |
| Anthropic → OpenAI | CPU per request (µs) | 968.3 | Valid | — |
| Anthropic → OpenAI | Requests per CPU-second | 1,032.7 | Valid | — |
| Anthropic → OpenAI | Cost window concurrency | 8 | Valid | — |
| Anthropic → OpenAI | Cost window core utilisation | 0.501 | Valid | — |
| Anthropic → OpenAI | Cost window successful requests | 12,465 | Valid | — |
| Anthropic → OpenAI | Cost window throughput (req/s) | 2,076 | Valid | — |
| Anthropic → OpenAI | Cost window threads | 142 | Valid | — |
| Anthropic → OpenAI | Non-voluntary context switches per request | 0.0000802 | Valid | — |
| Anthropic → OpenAI | Cost window major page faults | 0 | Valid | — |
| Anthropic → OpenAI | Added time to first event p50 (µs) | 1,262 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added time to first event p99 (µs) | 1,705 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p50 (µs) | 8 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p99 (µs) | 163 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Streams sustained (frames/s) | 19,376.7 | Valid | — |
| Anthropic → OpenAI | Streams sustained | 5,088 | Valid | — |
| Anthropic → OpenAI | Idle RSS (MiB) | 1,151.7 | Valid | — |
| Anthropic → OpenAI | Steady-state RSS (MiB) | 1,160.2 | Valid | — |
| Anthropic → OpenAI | Recovered RSS (MiB) | 1,161.2 | Valid | — |
| Anthropic → OpenAI | Peak RSS (MiB) | 1,177.2 | Valid | — |
| Anthropic → OpenAI | Peak RSS high-water mark (MiB) | 1,280.4 | Valid | — |
| Anthropic → OpenAI | Time to plateau (s) | 60 | Valid | — |
| Anthropic → OpenAI | Memory growth (MiB/min) | 0.529 | Valid | — |
| Anthropic → OpenAI | Memory load duration (s) | 300 | Valid | — |
| Anthropic → OpenAI | Memory shape under load | — | Not measured | — |
| Anthropic → OpenAI | Idle memory shape | — | Not measured | — |
| Anthropic → OpenAI | Idle memory static | 1 | Valid | — |
| Anthropic → OpenAI | Idle memory growth (MiB/min) | 1 | Valid | — |
| Anthropic → OpenAI | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| Anthropic → OpenAI | Throughput (req/s) | 3,867 | concurrency 8; n=23,211 | 5 ms |
| Anthropic → OpenAI | Throughput (req/s) | 3,999 | concurrency 16; n=23,998 | 10 ms |
| Anthropic → OpenAI | Throughput (req/s) | 4,118 | concurrency 64; n=24,713 | 50 ms |
| Anthropic → OpenAI | Throughput (req/s) | 4,118 | concurrency 64; n=24,713 | 100 ms |
| Anthropic → OpenAI | Throughput (req/s) | 4,118 | concurrency 64; n=24,713 | Unbounded |
| OpenAI Responses → OpenAI | — | — | 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 → Cohere | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Bedrock → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Gemini → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI → Cohere | Not served | 200 | failed | probed and answered HTTP 200, but the body is not a usable openai response (see body_snippet) | Recorded run evidence | the 2xx body is not a response of the openai dialect with assistant text at choices[].message.content: {"response_id":"x","generation_id":"x","text":"ok","finish_reason":"COMPLETE","meta":{"api_version":{"version":"1"},"tokens":{"input_tokens":10,"output_tokens":2},"billed_units":{"input_tokens":10,"output_tokens":2}}} | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Anthropic → Cohere | Not served | 200 | failed | probed and answered HTTP 200, but the body is not a usable anthropic response (see body_snippet) | Recorded run evidence | the 2xx body is not a response of the anthropic dialect with assistant text at content[type=text].text: {"id":"","type":"message","role":"assistant","content":null,"model":"","stop_reason":null,"stop_sequence":null,"usage":{},"error":null} | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI Responses → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Cohere → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Gemini → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI → Anthropic | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Bedrock → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI Responses → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Anthropic → Anthropic | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Gemini → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Cohere → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Bedrock → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI Responses → OpenAI Responses | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Anthropic → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI → Gemini | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Gemini → Gemini | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Bedrock → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Cohere → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI Responses → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Anthropic → Gemini | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI Responses → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Gemini → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Cohere → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Bedrock → Bedrock | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI → Bedrock | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Anthropic → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI → OpenAI | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Gemini → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Bedrock → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Cohere → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| Anthropic → OpenAI | Served | — | — | — | Recorded run evidence | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
| OpenAI Responses → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:2.2.5 |
- 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 | 4,096 | HTTP 200: 4,096 | 0 |
| OpenAI → Anthropic | 8,192 | HTTP 200: 8,082 | 110 |
| OpenAI → Anthropic | 6,144 | HTTP 200: 6,144 | 0 |
| OpenAI → Anthropic | 7,168 | HTTP 200: 7,168 | 0 |
| OpenAI → Anthropic | 7,680 | HTTP 200: 7,680 | 0 |
| OpenAI → Anthropic | 7,424 | HTTP 200: 7,424 | 0 |
| OpenAI → Anthropic | 7,552 | HTTP 200: 7,552 | 0 |
| OpenAI → Anthropic | 7,488 | HTTP 200: 7,488 | 0 |
| OpenAI → Anthropic | 7,456 | HTTP 200: 7,456 | 0 |
| OpenAI → Anthropic | 7,440 | HTTP 200: 7,440 | 0 |
| OpenAI → Anthropic | 7,432 | HTTP 200: 7,432 | 0 |
| OpenAI → Anthropic | 7,436 | HTTP 200: 7,436 | 0 |
| OpenAI → Anthropic | 7,438 | HTTP 200: 7,438 | 0 |
| OpenAI → Anthropic | 7,439 | HTTP 200: 7,439 | 0 |
| OpenAI → Anthropic | 7,438 | HTTP 200: 7,438 | 0 |
| OpenAI → Anthropic | 7,438 | HTTP 200: 7,438 | 0 |
| OpenAI → Anthropic | 5,767 | HTTP 200: 5,767 | 0 |
| OpenAI → Anthropic | 5,767 | HTTP 200: 5,767 | 0 |
| OpenAI → Anthropic | 5,767 | HTTP 200: 5,767 | 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 | 4,096 | HTTP 200: 4,096 | 0 |
| Anthropic → Anthropic | 8,192 | HTTP 200: 8,192 | 0 |
| Anthropic → Anthropic | 16,384 | HTTP 200: 16,384 | 0 |
| Anthropic → Anthropic | 32,768 | HTTP 200: 17,771 | 14,997 |
| Anthropic → Anthropic | 24,576 | HTTP 200: 17,562 | 7,014 |
| Anthropic → Anthropic | 20,480 | HTTP 200: 17,305 | 3,175 |
| Anthropic → Anthropic | 18,432 | HTTP 200: 17,810 | 622 |
| Anthropic → Anthropic | 17,408 | HTTP 200: 17,408 | 0 |
| Anthropic → Anthropic | 16,896 | HTTP 200: 16,896 | 0 |
| Anthropic → Anthropic | 16,640 | HTTP 200: 16,640 | 0 |
| Anthropic → Anthropic | 16,512 | HTTP 200: 16,512 | 0 |
| Anthropic → Anthropic | 16,448 | HTTP 200: 16,448 | 0 |
| Anthropic → Anthropic | 16,416 | HTTP 200: 16,416 | 0 |
| Anthropic → Anthropic | 16,400 | HTTP 200: 16,400 | 0 |
| Anthropic → Anthropic | 16,392 | HTTP 200: 16,392 | 0 |
| Anthropic → Anthropic | 16,388 | HTTP 200: 16,388 | 0 |
| Anthropic → Anthropic | 16,390 | HTTP 200: 16,390 | 0 |
| Anthropic → Anthropic | 16,391 | HTTP 200: 16,391 | 0 |
| Anthropic → Anthropic | 16,391 | HTTP 200: 16,391 | 0 |
| Anthropic → Anthropic | 16,391 | HTTP 200: 16,391 | 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 | 1,792 | HTTP 200: 1,792 | 0 |
| OpenAI → OpenAI | 1,664 | HTTP 200: 1,664 | 0 |
| OpenAI → OpenAI | 1,728 | HTTP 200: 1,728 | 0 |
| OpenAI → OpenAI | 1,696 | HTTP 200: 1,696 | 0 |
| OpenAI → OpenAI | 1,680 | HTTP 200: 1,680 | 0 |
| OpenAI → OpenAI | 1,688 | HTTP 200: 1,688 | 0 |
| OpenAI → OpenAI | 1,692 | HTTP 200: 1,692 | 0 |
| OpenAI → OpenAI | 1,690 | HTTP 200: 1,690 | 0 |
| OpenAI → OpenAI | 1,689 | HTTP 200: 1,689 | 0 |
| OpenAI → OpenAI | 1,688 | HTTP 200: 1,688 | 0 |
| OpenAI → OpenAI | 1,688 | HTTP 200: 1,688 | 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 | 4,096 | HTTP 200: 4,096 | 0 |
| Anthropic → OpenAI | 8,192 | HTTP 200: 6,688 | 1,504 |
| Anthropic → OpenAI | 6,144 | HTTP 200: 6,144 | 0 |
| Anthropic → OpenAI | 5,120 | HTTP 200: 5,120 | 0 |
| Anthropic → OpenAI | 5,632 | HTTP 200: 5,632 | 0 |
| Anthropic → OpenAI | 5,888 | HTTP 200: 5,888 | 0 |
| Anthropic → OpenAI | 6,016 | HTTP 200: 6,016 | 0 |
| Anthropic → OpenAI | 6,080 | HTTP 200: 6,080 | 0 |
| Anthropic → OpenAI | 6,112 | HTTP 200: 6,112 | 0 |
| Anthropic → OpenAI | 6,096 | HTTP 200: 6,096 | 0 |
| Anthropic → OpenAI | 6,088 | HTTP 200: 6,088 | 0 |
| Anthropic → OpenAI | 6,084 | HTTP 200: 6,084 | 0 |
| Anthropic → OpenAI | 6,082 | HTTP 200: 6,082 | 0 |
| Anthropic → OpenAI | 6,081 | HTTP 200: 6,081 | 0 |
| Anthropic → OpenAI | 6,080 | HTTP 200: 6,080 | 0 |
| Anthropic → OpenAI | 6,080 | HTTP 200: 6,080 | 0 |
| Anthropic → OpenAI | 5,088 | HTTP 200: 5,088 | 0 |
| Anthropic → OpenAI | 5,088 | HTTP 200: 5,088 | 0 |
| Anthropic → OpenAI | 5,088 | HTTP 200: 5,088 | 0 |
Recorded notes
Text recorded with the cells above. Each note is shown once; rows refer to it by number.
- Higress 2.2.5 with bundled AI Proxy 2.0.3. Source 4deae1dd3b4cb2707273748985e55bef28e747d1 and pinned-image probes establish 13 configured exact-wire pairs; two Cohere translations failed response correctness in the preflight. In the 2026-11-09 run the engine withheld performance and streaming numbers for six configured pairs because re-verification found the request did not arrive on the requested upstream wire: OpenAI to Anthropic, Gemini, Cohere and Bedrock arrived untranslated on the mock's OpenAI Chat Completions endpoint, and Anthropic to Gemini and Anthropic to Cohere also arrived on the OpenAI Chat Completions endpoint. Responses cross-conversion is not implemented; Messages-to-Bedrock uses Anthropic Mantle rather than Converse. Pairs outside the configured 13 are not configured: unsupported translations pass through the original wire or return unsupported API errors. Evidence: results/diagnostics/refresh-configuration/higress-adapter-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-higress-558a1502d4a7ea1f2b74c745739723084c953a3ae5dcf16760a2694a92c21270 · complete raw record including RSS series
Configuration recorded by the run
# data/ingresses/anthropic.gen.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: anthropic
namespace: higress-system
annotations:
higress.io/destination: mock.static
spec:
rules:
- host: anthropic.bench
http:
paths:
- path: /
pathType: Prefix
backend:
resource:
apiGroup: networking.higress.io
kind: McpBridge
name: default
# data/ingresses/openai-responses.gen.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: openai-responses
namespace: higress-system
annotations:
higress.io/destination: mock.static
spec:
rules:
- host: openai-responses.bench
http:
paths:
- path: /
pathType: Prefix
backend:
resource:
apiGroup: networking.higress.io
kind: McpBridge
name: default
# data/ingresses/bedrock.gen.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: bedrock
namespace: higress-system
annotations:
higress.io/destination: mock.static
spec:
rules:
- host: bedrock.bench
http:
paths:
- path: /
pathType: Prefix
backend:
resource:
apiGroup: networking.higress.io
kind: McpBridge
name: default
# data/ingresses/gemini.gen.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: gemini
namespace: higress-system
annotations:
higress.io/destination: mock.static
spec:
rules:
- host: gemini.bench
http:
paths:
- path: /
pathType: Prefix
backend:
resource:
apiGroup: networking.higress.io
kind: McpBridge
name: default
# data/ingresses/openai.gen.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: openai
namespace: higress-system
annotations:
higress.io/destination: mock.static
spec:
rules:
- http:
paths:
- path: /
pathType: Prefix
backend:
resource:
apiGroup: networking.higress.io
kind: McpBridge
name: default
# data/ingresses/cohere.gen.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: cohere
namespace: higress-system
annotations:
higress.io/destination: mock.static
spec:
rules:
- host: cohere.bench
http:
paths:
- path: /
pathType: Prefix
backend:
resource:
apiGroup: networking.higress.io
kind: McpBridge
name: default
# data/wasmplugins/bench.gen.yaml
apiVersion: extensions.higress.io/v1alpha1
kind: WasmPlugin
metadata:
name: bench
namespace: higress-system
spec:
defaultConfigDisable: true
matchRules:
- ingress: [openai]
config:
provider:
type: openai
apiTokens: [dummy]
modelMapping:
"*": gpt-4o-mini
- ingress: [openai-responses]
config:
provider:
type: openai
apiTokens: [dummy]
modelMapping:
"*": gpt-4o-mini
- ingress: [anthropic]
config:
provider:
type: claude
apiTokens: [dummy]
modelMapping:
"*": claude-3-5-sonnet-20241022
- ingress: [gemini]
config:
provider:
type: gemini
apiTokens: [dummy]
modelMapping:
"*": gemini-1.5-pro
- ingress: [cohere]
config:
provider:
type: cohere
apiTokens: [dummy]
modelMapping:
"*": command-r-plus
- ingress: [bedrock]
config:
provider:
type: bedrock
apiTokens: [dummy]
modelMapping:
"*": anthropic.claude-3-sonnet-20240229-v1:0
awsRegion: us-east-1
url: file:///usr/share/nginx/html/plugins/ai-proxy/2.0.3/plugin.wasm
# data/mcpbridges/default.gen.yaml
# The upstream registry this run drives: the harness's mock, on the host loopback. This file
# replaces the image's own default McpBridge (whose only registry is the console at 8001); the
# all-in-one bootstrap copies its defaults into /data with cp -n, so a file that already exists at
# this path is left alone and this one wins. 127.0.0.1 reaches the mock because the harness
# launches every container with host networking - the same fact apisix's override.endpoint and
# kong's upstream_url rely on. Shape mirrors the image's own all-in-one/config/mcpbridges/default.yaml.
apiVersion: networking.higress.io/v1
kind: McpBridge
metadata:
name: default
namespace: higress-system
creationTimestamp: "2000-01-01T00:00:00Z"
resourceVersion: "1"
spec:
registries:
- domain: "127.0.0.1:8000"
name: mock
port: 8000
type: static
Compare a shared protocol cell
- Higress vs agentgateway
- Higress vs AISIX (api7)
- Higress vs APISIX
- Higress vs Bifrost
- Higress vs Busbar
- Higress vs GoModel
- Higress vs Helicone
- Higress vs Kong
- Higress vs LiteLLM · Python
- Higress vs LiteLLM · Rust
- Higress vs One-API
- Higress vs Plano
- Higress vs Portkey
- Higress vs TensorZero