agentgateway benchmark measurements
Operated by the Busbar team; Busbar is also an entrant. Gateway overhead against a local mock is not end-to-end model latency. Methodology and limitations.
Rust · recorded build: ghcr.io/agentgateway/agentgateway:v1.7.0. Measured: .
JSON · Markdown · CSV · Project source · Interactive dashboard
Each row below names its protocol pair. A representative dashboard cell may differ between gateways; compare an identical pair before interpreting a ranking. Unavailable metrics retain their reason; below-resolution readings are not exact zeroes.
Published measurements
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI Responses → OpenAI Responses | Added latency p50 (µs) | 210 | Valid · n=25,353 gateway / 241,872 direct | — |
| OpenAI Responses → OpenAI Responses | Added latency p99 (µs) | 247 | Valid · n=25,353 gateway / 241,872 direct | — |
| OpenAI Responses → OpenAI Responses | Gateway p99 at concurrency 1 (µs) | 277 | Valid · n=25,353 | — |
| OpenAI Responses → OpenAI Responses | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=241,872 | — |
| OpenAI Responses → OpenAI Responses | CPU per request (µs) | 195.9 | Valid | — |
| OpenAI Responses → OpenAI Responses | Requests per CPU-second | 5,105.8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window core utilisation | 0.982 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window successful requests | 120,751 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window throughput (req/s) | 20,122 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window threads | 13 | Valid | — |
| OpenAI Responses → OpenAI Responses | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Streams sustained | — | Untestable | — |
| OpenAI Responses → OpenAI Responses | Idle RSS (MiB) | 34.46 | Valid | — |
| OpenAI Responses → OpenAI Responses | Steady-state RSS (MiB) | 53.24 | Valid | — |
| OpenAI Responses → OpenAI Responses | Recovered RSS (MiB) | 50.75 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS (MiB) | 54.41 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS high-water mark (MiB) | 54.24 | Valid | — |
| OpenAI Responses → OpenAI Responses | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → OpenAI Responses | Memory growth (MiB/min) | 0.764 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory shape under load | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory shape | — | Not measured | — |
| OpenAI Responses → OpenAI Responses | Idle memory static | 1 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory growth (MiB/min) | 0.032 | Valid | — |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 19,964 | concurrency 8; n=119,803 | 1 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 20,925 | concurrency 64; n=125,554 | 5 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 21,051 | concurrency 128; n=126,327 | 10 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 21,224 | concurrency 256; n=127,359 | 50 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 21,224 | concurrency 256; n=127,359 | 100 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 21,224 | concurrency 256; n=127,359 | Unbounded |
| Cohere → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Anthropic → OpenAI Responses | Added latency p50 (µs) | 227 | Valid · n=23,610 gateway / 229,535 direct | — |
| Anthropic → OpenAI Responses | Added latency p99 (µs) | 267 | Valid · n=23,610 gateway / 229,535 direct | — |
| Anthropic → OpenAI Responses | Gateway p99 at concurrency 1 (µs) | 299 | Valid · n=23,610 | — |
| Anthropic → OpenAI Responses | Direct-to-mock p99 at concurrency 1 (µs) | 32 | Valid · n=229,535 | — |
| Anthropic → OpenAI Responses | CPU per request (µs) | 207.8 | Valid | — |
| Anthropic → OpenAI Responses | Requests per CPU-second | 4,813.2 | Valid | — |
| Anthropic → OpenAI Responses | Cost window concurrency | 8 | Valid | — |
| Anthropic → OpenAI Responses | Cost window core utilisation | 0.984 | Valid | — |
| Anthropic → OpenAI Responses | Cost window successful requests | 114,025 | Valid | — |
| Anthropic → OpenAI Responses | Cost window throughput (req/s) | 19,002 | Valid | — |
| Anthropic → OpenAI Responses | Cost window threads | 13 | Valid | — |
| Anthropic → OpenAI Responses | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → OpenAI Responses | Cost window major page faults | 0 | Valid | — |
| Anthropic → OpenAI Responses | Added time to first event p50 (µs) | — | Untestable | — |
| Anthropic → OpenAI Responses | Added time to first event p99 (µs) | — | Untestable | — |
| Anthropic → OpenAI Responses | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Anthropic → OpenAI Responses | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Anthropic → OpenAI Responses | Streams sustained (frames/s) | — | Untestable | — |
| Anthropic → OpenAI Responses | Streams sustained | — | Untestable | — |
| Anthropic → OpenAI Responses | Idle RSS (MiB) | 34.34 | Valid | — |
| Anthropic → OpenAI Responses | Steady-state RSS (MiB) | 54.75 | Valid | — |
| Anthropic → OpenAI Responses | Recovered RSS (MiB) | 51.77 | Valid | — |
| Anthropic → OpenAI Responses | Peak RSS (MiB) | 55.42 | Valid | — |
| Anthropic → OpenAI Responses | Peak RSS high-water mark (MiB) | 55.16 | Valid | — |
| Anthropic → OpenAI Responses | Time to plateau (s) | 252 | Valid | — |
| Anthropic → OpenAI Responses | Memory growth (MiB/min) | 0.176 | Valid | — |
| Anthropic → OpenAI Responses | Memory load duration (s) | 300 | Valid | — |
| Anthropic → OpenAI Responses | Memory shape under load | — | Not measured | — |
| Anthropic → OpenAI Responses | Idle memory shape | — | Not measured | — |
| Anthropic → OpenAI Responses | Idle memory static | 1 | Valid | — |
| Anthropic → OpenAI Responses | Idle memory growth (MiB/min) | 0.049 | Valid | — |
| Anthropic → OpenAI Responses | Throughput (req/s) | 18,964 | concurrency 8; n=113,798 | 1 ms |
| Anthropic → OpenAI Responses | Throughput (req/s) | 19,692 | concurrency 32; n=118,168 | 5 ms |
| Anthropic → OpenAI Responses | Throughput (req/s) | 19,772 | concurrency 64; n=118,635 | 10 ms |
| Anthropic → OpenAI Responses | Throughput (req/s) | 20,024 | concurrency 256; n=120,161 | 50 ms |
| Anthropic → OpenAI Responses | Throughput (req/s) | 20,024 | concurrency 256; n=120,161 | 100 ms |
| Anthropic → OpenAI Responses | Throughput (req/s) | 20,024 | concurrency 256; n=120,161 | Unbounded |
| Bedrock → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Anthropic → Bedrock | Added latency p50 (µs) | 218 | Valid · n=24,390 gateway / 237,655 direct | — |
| Anthropic → Bedrock | Added latency p99 (µs) | 256 | Valid · n=24,390 gateway / 237,655 direct | — |
| Anthropic → Bedrock | Gateway p99 at concurrency 1 (µs) | 287 | Valid · n=24,390 | — |
| Anthropic → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=237,655 | — |
| Anthropic → Bedrock | CPU per request (µs) | 200.2 | Valid | — |
| Anthropic → Bedrock | Requests per CPU-second | 4,994.8 | Valid | — |
| Anthropic → Bedrock | Cost window concurrency | 8 | Valid | — |
| Anthropic → Bedrock | Cost window core utilisation | 0.982 | Valid | — |
| Anthropic → Bedrock | Cost window successful requests | 118,127 | Valid | — |
| Anthropic → Bedrock | Cost window throughput (req/s) | 19,685 | Valid | — |
| Anthropic → Bedrock | Cost window threads | 13 | Valid | — |
| Anthropic → Bedrock | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → Bedrock | Cost window major page faults | 0 | Valid | — |
| Anthropic → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| Anthropic → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| Anthropic → Bedrock | Streams sustained | — | Untestable | — |
| Anthropic → Bedrock | Idle RSS (MiB) | 34.07 | Valid | — |
| Anthropic → Bedrock | Steady-state RSS (MiB) | 54.66 | Valid | — |
| Anthropic → Bedrock | Recovered RSS (MiB) | 51.24 | Valid | — |
| Anthropic → Bedrock | Peak RSS (MiB) | 55.45 | Valid | — |
| Anthropic → Bedrock | Peak RSS high-water mark (MiB) | 55.26 | Valid | — |
| Anthropic → Bedrock | Time to plateau (s) | — | Not measured | — |
| Anthropic → Bedrock | Memory growth (MiB/min) | -1.3 | Valid | — |
| Anthropic → Bedrock | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Bedrock | Memory shape under load | -1 | Valid | — |
| Anthropic → Bedrock | Idle memory shape | — | Not measured | — |
| Anthropic → Bedrock | Idle memory static | 1 | Valid | — |
| Anthropic → Bedrock | Idle memory growth (MiB/min) | 0.049 | Valid | — |
| Anthropic → Bedrock | Throughput (req/s) | 19,560 | concurrency 8; n=117,376 | 1 ms |
| Anthropic → Bedrock | Throughput (req/s) | 20,404 | concurrency 64; n=122,433 | 5 ms |
| Anthropic → Bedrock | Throughput (req/s) | 20,404 | concurrency 64; n=122,433 | 10 ms |
| Anthropic → Bedrock | Throughput (req/s) | 20,660 | concurrency 256; n=123,971 | 50 ms |
| Anthropic → Bedrock | Throughput (req/s) | 20,660 | concurrency 256; n=123,971 | 100 ms |
| Anthropic → Bedrock | Throughput (req/s) | 20,660 | concurrency 256; n=123,971 | Unbounded |
| Gemini → Bedrock | — | — | Not declared: recorded note 1 | — |
| Cohere → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Bedrock | Added latency p50 (µs) | 231 | Valid · n=23,233 gateway / 241,925 direct | — |
| OpenAI Responses → Bedrock | Added latency p99 (µs) | 270 | Valid · n=23,233 gateway / 241,925 direct | — |
| OpenAI Responses → Bedrock | Gateway p99 at concurrency 1 (µs) | 301 | Valid · n=23,233 | — |
| OpenAI Responses → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=241,925 | — |
| OpenAI Responses → Bedrock | CPU per request (µs) | 208.7 | Valid | — |
| OpenAI Responses → Bedrock | Requests per CPU-second | 4,791.3 | Valid | — |
| OpenAI Responses → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → Bedrock | Cost window core utilisation | 0.984 | Valid | — |
| OpenAI Responses → Bedrock | Cost window successful requests | 113,505 | Valid | — |
| OpenAI Responses → Bedrock | Cost window throughput (req/s) | 18,915 | Valid | — |
| OpenAI Responses → Bedrock | Cost window threads | 13 | Valid | — |
| OpenAI Responses → Bedrock | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → Bedrock | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → Bedrock | Streams sustained | — | Untestable | — |
| OpenAI Responses → Bedrock | Idle RSS (MiB) | 34.1 | Valid | — |
| OpenAI Responses → Bedrock | Steady-state RSS (MiB) | 54.75 | Valid | — |
| OpenAI Responses → Bedrock | Recovered RSS (MiB) | 51.99 | Valid | — |
| OpenAI Responses → Bedrock | Peak RSS (MiB) | 55.73 | Valid | — |
| OpenAI Responses → Bedrock | Peak RSS high-water mark (MiB) | 55.29 | Valid | — |
| OpenAI Responses → Bedrock | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → Bedrock | Memory growth (MiB/min) | 0.023 | Valid | — |
| OpenAI Responses → Bedrock | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → Bedrock | Memory shape under load | 0 | 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) | 0.014 | Valid | — |
| OpenAI Responses → Bedrock | Throughput (req/s) | 18,692 | concurrency 8; n=112,168 | 1 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 19,412 | concurrency 32; n=116,482 | 5 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 19,442 | concurrency 64; n=116,658 | 10 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 19,736 | concurrency 256; n=118,430 | 50 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 19,736 | concurrency 256; n=118,430 | 100 ms |
| OpenAI Responses → Bedrock | Throughput (req/s) | 19,736 | concurrency 256; n=118,430 | Unbounded |
| Bedrock → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI → Bedrock | Added latency p50 (µs) | 219 | Valid · n=24,338 gateway / 241,582 direct | — |
| OpenAI → Bedrock | Added latency p99 (µs) | 256 | Valid · n=24,338 gateway / 241,582 direct | — |
| OpenAI → Bedrock | Gateway p99 at concurrency 1 (µs) | 286 | Valid · n=24,338 | — |
| OpenAI → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=241,582 | — |
| OpenAI → Bedrock | CPU per request (µs) | 205.6 | Valid | — |
| OpenAI → Bedrock | Requests per CPU-second | 4,863.4 | Valid | — |
| OpenAI → Bedrock | Cost window concurrency | 8 | Valid | — |
| OpenAI → Bedrock | Cost window core utilisation | 0.984 | Valid | — |
| OpenAI → Bedrock | Cost window successful requests | 115,215 | Valid | — |
| OpenAI → Bedrock | Cost window throughput (req/s) | 19,200 | Valid | — |
| OpenAI → Bedrock | Cost window threads | 13 | Valid | — |
| OpenAI → Bedrock | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Bedrock | Cost window major page faults | 0 | Valid | — |
| OpenAI → Bedrock | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Bedrock | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Bedrock | Streams sustained | — | Untestable | — |
| OpenAI → Bedrock | Idle RSS (MiB) | 34.2 | Valid | — |
| OpenAI → Bedrock | Steady-state RSS (MiB) | 53.94 | Valid | — |
| OpenAI → Bedrock | Recovered RSS (MiB) | 50.91 | Valid | — |
| OpenAI → Bedrock | Peak RSS (MiB) | 54.72 | Valid | — |
| OpenAI → Bedrock | Peak RSS high-water mark (MiB) | 54.31 | Valid | — |
| OpenAI → Bedrock | Time to plateau (s) | — | Not measured | — |
| OpenAI → Bedrock | Memory growth (MiB/min) | -0.637 | Valid | — |
| OpenAI → Bedrock | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Bedrock | Memory shape under load | -1 | Valid | — |
| OpenAI → Bedrock | Idle memory shape | — | Not measured | — |
| OpenAI → Bedrock | Idle memory static | 1 | Valid | — |
| OpenAI → Bedrock | Idle memory growth (MiB/min) | 0.045 | Valid | — |
| OpenAI → Bedrock | Throughput (req/s) | 19,159 | concurrency 8; n=114,971 | 1 ms |
| OpenAI → Bedrock | Throughput (req/s) | 19,912 | concurrency 32; n=119,487 | 5 ms |
| OpenAI → Bedrock | Throughput (req/s) | 20,007 | concurrency 64; n=120,063 | 10 ms |
| OpenAI → Bedrock | Throughput (req/s) | 20,265 | concurrency 256; n=121,609 | 50 ms |
| OpenAI → Bedrock | Throughput (req/s) | 20,265 | concurrency 256; n=121,609 | 100 ms |
| OpenAI → Bedrock | Throughput (req/s) | 20,265 | concurrency 256; n=121,609 | Unbounded |
| Anthropic → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Cohere | — | — | Not declared: recorded note 1 | — |
| Gemini → Cohere | — | — | Not declared: recorded note 1 | — |
| Cohere → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI → Cohere | — | — | Not declared: recorded note 1 | — |
| Bedrock → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI | Added latency p50 (µs) | 229 | Valid · n=23,446 gateway / 240,137 direct | — |
| OpenAI Responses → OpenAI | Added latency p99 (µs) | 267 | Valid · n=23,446 gateway / 240,137 direct | — |
| OpenAI Responses → OpenAI | Gateway p99 at concurrency 1 (µs) | 298 | Valid · n=23,446 | — |
| OpenAI Responses → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=240,137 | — |
| OpenAI Responses → OpenAI | CPU per request (µs) | 207.5 | Valid | — |
| OpenAI Responses → OpenAI | Requests per CPU-second | 4,818.3 | Valid | — |
| OpenAI Responses → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI | Cost window core utilisation | 0.984 | Valid | — |
| OpenAI Responses → OpenAI | Cost window successful requests | 114,146 | Valid | — |
| OpenAI Responses → OpenAI | Cost window throughput (req/s) | 19,022 | Valid | — |
| OpenAI Responses → OpenAI | Cost window threads | 13 | Valid | — |
| OpenAI Responses → OpenAI | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI Responses → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI Responses → OpenAI | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI Responses → OpenAI | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI Responses → OpenAI | Streams sustained | — | Untestable | — |
| OpenAI Responses → OpenAI | Idle RSS (MiB) | 34.04 | Valid | — |
| OpenAI Responses → OpenAI | Steady-state RSS (MiB) | 53.94 | Valid | — |
| OpenAI Responses → OpenAI | Recovered RSS (MiB) | 51.01 | Valid | — |
| OpenAI Responses → OpenAI | Peak RSS (MiB) | 54.8 | Valid | — |
| OpenAI Responses → OpenAI | Peak RSS high-water mark (MiB) | 54.57 | Valid | — |
| OpenAI Responses → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI Responses → OpenAI | Memory growth (MiB/min) | 1.19 | Valid | — |
| OpenAI Responses → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI Responses → OpenAI | Memory shape under load | 1 | Valid | — |
| OpenAI Responses → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI Responses → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI Responses → OpenAI | Idle memory growth (MiB/min) | 0.045 | Valid | — |
| OpenAI Responses → OpenAI | Throughput (req/s) | 19,011 | concurrency 8; n=114,080 | 1 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 19,731 | concurrency 32; n=118,399 | 5 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 19,868 | concurrency 64; n=119,220 | 10 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 20,063 | concurrency 256; n=120,396 | 50 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 20,063 | concurrency 256; n=120,396 | 100 ms |
| OpenAI Responses → OpenAI | Throughput (req/s) | 20,063 | concurrency 256; n=120,396 | Unbounded |
| Cohere → OpenAI | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI | Added latency p50 (µs) | 216 | Valid · n=24,618 gateway / 233,879 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 251 | Valid · n=24,618 gateway / 233,879 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 282 | Valid · n=24,618 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=233,879 | — |
| OpenAI → OpenAI | CPU per request (µs) | 188.6 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 5,302.9 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.972 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 124,088 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 20,679 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 13 | 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) | 327 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 360 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | 10 | 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) | 32,614.1 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 2,048 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 34 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 53.49 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 50 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 54.52 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 54.23 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | -2.07 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | -1 | Valid | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.036 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 21,156 | concurrency 8; n=126,952 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,239 | concurrency 64; n=133,447 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,380 | concurrency 128; n=134,304 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,545 | concurrency 256; n=135,283 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,545 | concurrency 256; n=135,283 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 22,545 | concurrency 256; n=135,283 | Unbounded |
| Anthropic → OpenAI | Added latency p50 (µs) | 212 | Valid · n=25,009 gateway / 233,282 direct | — |
| Anthropic → OpenAI | Added latency p99 (µs) | 247 | Valid · n=25,009 gateway / 233,282 direct | — |
| Anthropic → OpenAI | Gateway p99 at concurrency 1 (µs) | 279 | Valid · n=25,009 | — |
| Anthropic → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 32 | Valid · n=233,282 | — |
| Anthropic → OpenAI | CPU per request (µs) | 196.3 | Valid | — |
| Anthropic → OpenAI | Requests per CPU-second | 5,093 | Valid | — |
| Anthropic → OpenAI | Cost window concurrency | 8 | Valid | — |
| Anthropic → OpenAI | Cost window core utilisation | 0.968 | Valid | — |
| Anthropic → OpenAI | Cost window successful requests | 118,717 | Valid | — |
| Anthropic → OpenAI | Cost window throughput (req/s) | 19,784 | Valid | — |
| Anthropic → OpenAI | Cost window threads | 13 | Valid | — |
| Anthropic → OpenAI | Non-voluntary context switches per request | 0 | Valid | — |
| Anthropic → OpenAI | Cost window major page faults | 0 | Valid | — |
| Anthropic → OpenAI | Added time to first event p50 (µs) | 341 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added time to first event p99 (µs) | 395 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p50 (µs) | 3 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p99 (µs) | 17 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Streams sustained (frames/s) | — | Not measured | — |
| Anthropic → OpenAI | Streams sustained | — | Not measured | — |
| Anthropic → OpenAI | Idle RSS (MiB) | 33.7 | Valid | — |
| Anthropic → OpenAI | Steady-state RSS (MiB) | 53.57 | Valid | — |
| Anthropic → OpenAI | Recovered RSS (MiB) | 49.9 | Valid | — |
| Anthropic → OpenAI | Peak RSS (MiB) | 54.21 | Valid | — |
| Anthropic → OpenAI | Peak RSS high-water mark (MiB) | 54.05 | Valid | — |
| Anthropic → OpenAI | Time to plateau (s) | 156 | Valid | — |
| Anthropic → OpenAI | Memory growth (MiB/min) | 0.1 | 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) | 0.049 | Valid | — |
| Anthropic → OpenAI | Throughput (req/s) | 19,933 | concurrency 8; n=119,616 | 1 ms |
| Anthropic → OpenAI | Throughput (req/s) | 20,841 | concurrency 64; n=125,053 | 5 ms |
| Anthropic → OpenAI | Throughput (req/s) | 20,997 | concurrency 128; n=126,001 | 10 ms |
| Anthropic → OpenAI | Throughput (req/s) | 21,100 | concurrency 256; n=126,618 | 50 ms |
| Anthropic → OpenAI | Throughput (req/s) | 21,100 | concurrency 256; n=126,618 | 100 ms |
| Anthropic → OpenAI | Throughput (req/s) | 21,100 | concurrency 256; n=126,618 | Unbounded |
| Bedrock → OpenAI | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI | — | — | Not declared: recorded note 1 | — |
| Anthropic → Anthropic | Added latency p50 (µs) | 206 | Valid · n=25,747 gateway / 233,859 direct | — |
| Anthropic → Anthropic | Added latency p99 (µs) | 240 | Valid · n=25,747 gateway / 233,859 direct | — |
| Anthropic → Anthropic | Gateway p99 at concurrency 1 (µs) | 271 | Valid · n=25,747 | — |
| Anthropic → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=233,859 | — |
| Anthropic → Anthropic | CPU per request (µs) | 191.3 | Valid | — |
| Anthropic → Anthropic | Requests per CPU-second | 5,226.9 | Valid | — |
| Anthropic → Anthropic | Cost window concurrency | 8 | Valid | — |
| Anthropic → Anthropic | Cost window core utilisation | 0.963 | Valid | — |
| Anthropic → Anthropic | Cost window successful requests | 121,211 | Valid | — |
| Anthropic → Anthropic | Cost window throughput (req/s) | 20,199 | 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) | 323 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added time to first event p99 (µs) | 362 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p50 (µs) | 3 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p99 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Streams sustained (frames/s) | 29,596.7 | Valid | — |
| Anthropic → Anthropic | Streams sustained | 4,104 | Valid | — |
| Anthropic → Anthropic | Idle RSS (MiB) | 34.16 | Valid | — |
| Anthropic → Anthropic | Steady-state RSS (MiB) | 53.17 | Valid | — |
| Anthropic → Anthropic | Recovered RSS (MiB) | 50.18 | Valid | — |
| Anthropic → Anthropic | Peak RSS (MiB) | 54.41 | Valid | — |
| Anthropic → Anthropic | Peak RSS high-water mark (MiB) | 54.25 | Valid | — |
| Anthropic → Anthropic | Time to plateau (s) | — | Not measured | — |
| Anthropic → Anthropic | Memory growth (MiB/min) | -0.237 | 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) | 0.049 | Valid | — |
| Anthropic → Anthropic | Throughput (req/s) | 20,502 | concurrency 8; n=123,033 | 1 ms |
| Anthropic → Anthropic | Throughput (req/s) | 21,665 | concurrency 64; n=130,000 | 5 ms |
| Anthropic → Anthropic | Throughput (req/s) | 21,795 | concurrency 128; n=130,775 | 10 ms |
| Anthropic → Anthropic | Throughput (req/s) | 21,982 | concurrency 256; n=131,913 | 50 ms |
| Anthropic → Anthropic | Throughput (req/s) | 21,982 | concurrency 256; n=131,913 | 100 ms |
| Anthropic → Anthropic | Throughput (req/s) | 21,982 | concurrency 256; n=131,913 | Unbounded |
| Bedrock → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI → Anthropic | Added latency p50 (µs) | 228 | Valid · n=23,411 gateway / 237,919 direct | — |
| OpenAI → Anthropic | Added latency p99 (µs) | 268 | Valid · n=23,411 gateway / 237,919 direct | — |
| OpenAI → Anthropic | Gateway p99 at concurrency 1 (µs) | 299 | Valid · n=23,411 | — |
| OpenAI → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 31 | Valid · n=237,919 | — |
| OpenAI → Anthropic | CPU per request (µs) | 207 | Valid | — |
| OpenAI → Anthropic | Requests per CPU-second | 4,831.1 | Valid | — |
| OpenAI → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI → Anthropic | Cost window core utilisation | 0.968 | Valid | — |
| OpenAI → Anthropic | Cost window successful requests | 112,613 | Valid | — |
| OpenAI → Anthropic | Cost window throughput (req/s) | 18,767 | 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) | 405 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added time to first event p99 (µs) | 446 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p50 (µs) | 6 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p99 (µs) | 22 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Streams sustained (frames/s) | 18,079.4 | Valid | — |
| OpenAI → Anthropic | Streams sustained | 2,559 | Valid | — |
| OpenAI → Anthropic | Idle RSS (MiB) | 34.2 | Valid | — |
| OpenAI → Anthropic | Steady-state RSS (MiB) | 53.82 | Valid | — |
| OpenAI → Anthropic | Recovered RSS (MiB) | 50.53 | Valid | — |
| OpenAI → Anthropic | Peak RSS (MiB) | 54.71 | Valid | — |
| OpenAI → Anthropic | Peak RSS high-water mark (MiB) | 54.35 | Valid | — |
| OpenAI → Anthropic | Time to plateau (s) | — | Not measured | — |
| OpenAI → Anthropic | Memory growth (MiB/min) | -0.764 | 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) | 0.041 | Valid | — |
| OpenAI → Anthropic | Throughput (req/s) | 19,127 | concurrency 8; n=114,783 | 1 ms |
| OpenAI → Anthropic | Throughput (req/s) | 19,852 | concurrency 32; n=119,122 | 5 ms |
| OpenAI → Anthropic | Throughput (req/s) | 19,973 | concurrency 64; n=119,864 | 10 ms |
| OpenAI → Anthropic | Throughput (req/s) | 20,228 | concurrency 256; n=121,382 | 50 ms |
| OpenAI → Anthropic | Throughput (req/s) | 20,228 | concurrency 256; n=121,382 | 100 ms |
| OpenAI → Anthropic | Throughput (req/s) | 20,228 | concurrency 256; n=121,382 | Unbounded |
| Cohere → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → Anthropic | — | — | Not declared: recorded note 1 | — |
| Cohere → Gemini | — | — | Not declared: recorded note 1 | — |
| Gemini → Gemini | Added latency p50 (µs) | 211 | Valid · n=25,203 gateway / 241,373 direct | — |
| Gemini → Gemini | Added latency p99 (µs) | 248 | Valid · n=25,203 gateway / 241,373 direct | — |
| Gemini → Gemini | Gateway p99 at concurrency 1 (µs) | 278 | Valid · n=25,203 | — |
| Gemini → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=241,373 | — |
| Gemini → Gemini | CPU per request (µs) | 196.9 | Valid | — |
| Gemini → Gemini | Requests per CPU-second | 5,079 | Valid | — |
| Gemini → Gemini | Cost window concurrency | 8 | Valid | — |
| Gemini → Gemini | Cost window core utilisation | 0.982 | Valid | — |
| Gemini → Gemini | Cost window successful requests | 120,067 | Valid | — |
| Gemini → Gemini | Cost window throughput (req/s) | 20,008 | Valid | — |
| Gemini → Gemini | Cost window threads | 13 | Valid | — |
| Gemini → Gemini | Non-voluntary context switches per request | 0 | 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) | 33.96 | Valid | — |
| Gemini → Gemini | Steady-state RSS (MiB) | 54.24 | Valid | — |
| Gemini → Gemini | Recovered RSS (MiB) | 50.96 | Valid | — |
| Gemini → Gemini | Peak RSS (MiB) | 54.77 | Valid | — |
| Gemini → Gemini | Peak RSS high-water mark (MiB) | 54.52 | Valid | — |
| Gemini → Gemini | Time to plateau (s) | — | Not measured | — |
| Gemini → Gemini | Memory growth (MiB/min) | -0.178 | Valid | — |
| Gemini → Gemini | Memory load duration (s) | 300 | Valid | — |
| Gemini → Gemini | Memory shape under load | 0 | Valid | — |
| Gemini → Gemini | Idle memory shape | — | Not measured | — |
| Gemini → Gemini | Idle memory static | 1 | Valid | — |
| Gemini → Gemini | Idle memory growth (MiB/min) | 0.041 | Valid | — |
| Gemini → Gemini | Throughput (req/s) | 19,915 | concurrency 8; n=119,508 | 1 ms |
| Gemini → Gemini | Throughput (req/s) | 20,912 | concurrency 64; n=125,481 | 5 ms |
| Gemini → Gemini | Throughput (req/s) | 20,976 | concurrency 128; n=125,877 | 10 ms |
| Gemini → Gemini | Throughput (req/s) | 21,168 | concurrency 256; n=127,023 | 50 ms |
| Gemini → Gemini | Throughput (req/s) | 21,168 | concurrency 256; n=127,023 | 100 ms |
| Gemini → Gemini | Throughput (req/s) | 21,168 | concurrency 256; n=127,023 | Unbounded |
| OpenAI Responses → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI → Gemini | Added latency p50 (µs) | 217 | Valid · n=24,639 gateway / 244,550 direct | — |
| OpenAI → Gemini | Added latency p99 (µs) | 253 | Valid · n=24,639 gateway / 244,550 direct | — |
| OpenAI → Gemini | Gateway p99 at concurrency 1 (µs) | 283 | Valid · n=24,639 | — |
| OpenAI → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 30 | Valid · n=244,550 | — |
| OpenAI → Gemini | CPU per request (µs) | 202.1 | Valid | — |
| OpenAI → Gemini | Requests per CPU-second | 4,947.7 | Valid | — |
| OpenAI → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI → Gemini | Cost window core utilisation | 0.983 | Valid | — |
| OpenAI → Gemini | Cost window successful requests | 117,111 | Valid | — |
| OpenAI → Gemini | Cost window throughput (req/s) | 19,516 | Valid | — |
| OpenAI → Gemini | Cost window threads | 13 | Valid | — |
| OpenAI → Gemini | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Gemini | Cost window major page faults | 0 | Valid | — |
| OpenAI → Gemini | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Gemini | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Gemini | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Gemini | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Gemini | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Gemini | Streams sustained | — | Untestable | — |
| OpenAI → Gemini | Idle RSS (MiB) | 34.06 | Valid | — |
| OpenAI → Gemini | Steady-state RSS (MiB) | 53.59 | Valid | — |
| OpenAI → Gemini | Recovered RSS (MiB) | 50.47 | Valid | — |
| OpenAI → Gemini | Peak RSS (MiB) | 54.25 | Valid | — |
| OpenAI → Gemini | Peak RSS high-water mark (MiB) | 53.98 | Valid | — |
| OpenAI → Gemini | Time to plateau (s) | — | Not measured | — |
| OpenAI → Gemini | Memory growth (MiB/min) | -0.361 | Valid | — |
| OpenAI → Gemini | Memory load duration (s) | 300 | Valid | — |
| OpenAI → Gemini | Memory shape under load | 0 | Valid | — |
| OpenAI → Gemini | Idle memory shape | — | Not measured | — |
| OpenAI → Gemini | Idle memory static | 1 | Valid | — |
| OpenAI → Gemini | Idle memory growth (MiB/min) | 0.002 | Valid | — |
| OpenAI → Gemini | Throughput (req/s) | 19,532 | concurrency 8; n=117,207 | 1 ms |
| OpenAI → Gemini | Throughput (req/s) | 20,455 | concurrency 64; n=122,740 | 5 ms |
| OpenAI → Gemini | Throughput (req/s) | 20,455 | concurrency 64; n=122,740 | 10 ms |
| OpenAI → Gemini | Throughput (req/s) | 20,723 | concurrency 256; n=124,350 | 50 ms |
| OpenAI → Gemini | Throughput (req/s) | 20,723 | concurrency 256; n=124,350 | 100 ms |
| OpenAI → Gemini | Throughput (req/s) | 20,723 | concurrency 256; n=124,350 | Unbounded |
| Bedrock → Gemini | — | — | Not declared: recorded note 1 | — |
| Anthropic → Gemini | — | — | Not declared: recorded note 1 | — |
Probe evidence and instrument provenance
Historical capability notes may reference an earlier product version. They are not a new probe or a current support claim. Full RSS samples remain in the immutable raw JSON.
| Ingress → upstream | Cell state | Probe HTTP status | Recorded reason | Recorded detail | Evidence scope | Response excerpt | Tested build |
|---|---|---|---|---|---|---|---|
| OpenAI Responses → OpenAI Responses | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Cohere → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Anthropic → OpenAI Responses | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Bedrock → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Gemini → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Anthropic → Bedrock | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Gemini → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Cohere → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI Responses → Bedrock | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Bedrock → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI → Bedrock | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Anthropic → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI Responses → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Gemini → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Cohere → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Bedrock → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI Responses → OpenAI | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Cohere → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI → OpenAI | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Anthropic → OpenAI | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Bedrock → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Gemini → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Anthropic → Anthropic | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Bedrock → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI Responses → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI → Anthropic | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Cohere → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Gemini → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Cohere → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Gemini → Gemini | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI Responses → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| OpenAI → Gemini | Served | — | — | — | Recorded run evidence | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Bedrock → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
| Anthropic → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | ghcr.io/agentgateway/agentgateway:v1.7.0 |
- Harness commit
d240badd966933fa19eec0606b2d1f3945f18ad2- Mock SHA-256
99d01f709d8d9c1f49055aa265d5eb7475264d6b513911fe317aee74a71190f8- Load generator SHA-256
not recorded- net.core.somaxconn
- 65,535
- net.ipv4.tcp_max_syn_backlog
- 65,535
Stream sweep diagnostics
Per streaming-sweep concurrency, as recorded by the engine: lanes by final HTTP status, and lanes that received no response.
| Ingress → upstream | Concurrency | Lanes by HTTP status | Lanes with no response |
|---|---|---|---|
| OpenAI → 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 | 4,096 | HTTP 200: 4,096 | 0 |
| OpenAI → OpenAI | 3,072 | HTTP 200: 3,072 | 0 |
| OpenAI → OpenAI | 2,560 | HTTP 200: 2,560 | 0 |
| OpenAI → OpenAI | 2,304 | HTTP 200: 2,304 | 0 |
| OpenAI → OpenAI | 2,432 | HTTP 200: 2,432 | 0 |
| OpenAI → OpenAI | 2,496 | HTTP 200: 2,496 | 0 |
| OpenAI → OpenAI | 2,528 | HTTP 200: 2,528 | 0 |
| OpenAI → OpenAI | 2,544 | HTTP 200: 2,544 | 0 |
| OpenAI → OpenAI | 2,552 | HTTP 200: 2,552 | 0 |
| OpenAI → OpenAI | 2,556 | HTTP 200: 2,556 | 0 |
| OpenAI → OpenAI | 2,558 | HTTP 200: 2,558 | 0 |
| OpenAI → OpenAI | 2,557 | HTTP 200: 2,557 | 0 |
| OpenAI → OpenAI | 2,556 | HTTP 200: 2,556 | 0 |
| OpenAI → OpenAI | 2,556 | HTTP 200: 2,556 | 0 |
| OpenAI → OpenAI | 2,302 | HTTP 200: 2,302 | 0 |
| OpenAI → OpenAI | 2,175 | HTTP 200: 2,175 | 0 |
| OpenAI → OpenAI | 2,111 | HTTP 200: 2,111 | 0 |
| OpenAI → OpenAI | 2,079 | HTTP 200: 2,079 | 0 |
| OpenAI → OpenAI | 2,048 | HTTP 200: 2,048 | 0 |
| OpenAI → OpenAI | 2,048 | HTTP 200: 2,048 | 0 |
| OpenAI → OpenAI | 2,048 | HTTP 200: 2,048 | 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: 8,192 | 0 |
| Anthropic → OpenAI | 6,144 | HTTP 200: 6,144 | 0 |
| Anthropic → OpenAI | 5,120 | HTTP 200: 5,120 | 0 |
| Anthropic → OpenAI | 4,608 | HTTP 200: 4,608 | 0 |
| Anthropic → OpenAI | 4,352 | HTTP 200: 4,352 | 0 |
| Anthropic → OpenAI | 4,224 | HTTP 200: 4,224 | 0 |
| Anthropic → OpenAI | 4,160 | HTTP 200: 4,160 | 0 |
| Anthropic → OpenAI | 4,128 | HTTP 200: 4,128 | 0 |
| Anthropic → OpenAI | 4,144 | HTTP 200: 4,144 | 0 |
| Anthropic → OpenAI | 4,136 | HTTP 200: 3,945 | 191 |
| Anthropic → OpenAI | 4,132 | HTTP 200: 3,959 | 173 |
| Anthropic → OpenAI | 4,130 | HTTP 200: 4,130 | 0 |
| Anthropic → OpenAI | 4,129 | HTTP 200: 4,129 | 0 |
| Anthropic → OpenAI | 4,128 | HTTP 200: 3,234 | 894 |
| Anthropic → OpenAI | 4,128 | HTTP 200: 4,057 | 71 |
| Anthropic → OpenAI | 4,112 | HTTP 200: 3,242 | 870 |
| Anthropic → OpenAI | 4,104 | HTTP 200: 2,957 | 1,147 |
| Anthropic → OpenAI | 4,100 | HTTP 200: 3,860 | 240 |
| Anthropic → OpenAI | 4,098 | HTTP 200: 2,704 | 1,394 |
| Anthropic → OpenAI | 4,096 | HTTP 200: 3,404 | 692 |
| Anthropic → OpenAI | 4,096 | HTTP 200: 3,208 | 888 |
| Anthropic → OpenAI | 4,096 | HTTP 200: 3,250 | 846 |
| 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 | 6,144 | HTTP 200: 6,144 | 0 |
| Anthropic → Anthropic | 5,120 | HTTP 200: 5,120 | 0 |
| Anthropic → Anthropic | 4,608 | HTTP 200: 4,608 | 0 |
| Anthropic → Anthropic | 4,352 | HTTP 200: 4,352 | 0 |
| Anthropic → Anthropic | 4,224 | HTTP 200: 4,224 | 0 |
| Anthropic → Anthropic | 4,160 | HTTP 200: 4,160 | 0 |
| Anthropic → Anthropic | 4,128 | HTTP 200: 4,128 | 0 |
| Anthropic → Anthropic | 4,112 | HTTP 200: 4,112 | 0 |
| Anthropic → Anthropic | 4,104 | HTTP 200: 4,104 | 0 |
| Anthropic → Anthropic | 4,108 | HTTP 200: 4,108 | 0 |
| Anthropic → Anthropic | 4,106 | HTTP 200: 4,106 | 0 |
| Anthropic → Anthropic | 4,105 | HTTP 200: 4,105 | 0 |
| Anthropic → Anthropic | 4,104 | HTTP 200: 4,104 | 0 |
| Anthropic → Anthropic | 4,104 | HTTP 200: 3,923 | 181 |
| 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 | 3,072 | HTTP 200: 3,072 | 0 |
| OpenAI → Anthropic | 2,560 | HTTP 200: 2,560 | 0 |
| OpenAI → Anthropic | 2,304 | HTTP 200: 2,304 | 0 |
| OpenAI → Anthropic | 2,432 | HTTP 200: 2,432 | 0 |
| OpenAI → Anthropic | 2,496 | HTTP 200: 2,496 | 0 |
| OpenAI → Anthropic | 2,528 | HTTP 200: 2,528 | 0 |
| OpenAI → Anthropic | 2,544 | HTTP 200: 2,544 | 0 |
| OpenAI → Anthropic | 2,552 | HTTP 200: 2,552 | 0 |
| OpenAI → Anthropic | 2,556 | HTTP 200: 2,556 | 0 |
| OpenAI → Anthropic | 2,558 | HTTP 200: 2,558 | 0 |
| OpenAI → Anthropic | 2,559 | HTTP 200: 2,559 | 0 |
| OpenAI → Anthropic | 2,559 | HTTP 200: 2,559 | 0 |
| OpenAI → Anthropic | 2,559 | HTTP 200: 2,559 | 0 |
Recorded notes
Text recorded with the cells above. Each note is shown once; rows refer to it by number.
- Pinned v1.7.0 image and source 26f5aebe99a36a037fe54f8080a608aca5547e15: CHAT_TRANSLATIONS in crates/agentgateway/src/llm/mod.rs defines supported conversions. Separate custom providers constrain Chat versus Responses wire. Gemini native and Chat-to-Gemini are supported; Messages/Responses use Google OpenAI compatibility instead of native Gemini and are not counted as Gemini wire. Cohere preset similarly uses OpenAI compatibility, not Cohere native chat. No native Cohere or Bedrock ingress conversion is registered. Local recorder and response checks establish 12 pairs. Responses mock token-details correction is required for Messages-to-Responses. Evidence: results/diagnostics/refresh-configuration/agentgateway-protocol-preflight.json
- Historical capability research, not a fresh probe of the tested build. Referenced versions may differ from gateway_build; do not infer current capability.
Evidence for the current measurements
- run-agentgateway-fa351efdcee949e977dd1d4331440512b3e913a74b878f4bd1b19a7c7ca2900c · complete raw record including RSS series
Configuration recorded by the run
llm:
port: 8080
models:
- name: gpt-4o-mini
provider: openAI
params:
model: gpt-4o-mini
apiKey: "sk-dummy-openai"
baseUrl: "http://127.0.0.1:8000/v1"
- name: claude-3-5-sonnet-20241022
provider: anthropic
params:
model: claude-3-5-sonnet-20241022
apiKey: "sk-ant-dummy"
baseUrl: "http://127.0.0.1:8000/v1"
- name: anthropic.claude-3-sonnet-20240229-v1:0
provider: bedrock
params:
model: anthropic.claude-3-sonnet-20240229-v1:0
awsRegion: us-east-1
baseUrl: "http://127.0.0.1:8000/bedrock"
- name: gemini-1.5-pro
provider: gemini
params:
model: gemini-1.5-pro
apiKey: dummy
baseUrl: http://127.0.0.1:8000
- name: bench-chat
provider:
custom:
formats:
- type: completions
params:
model: gpt-4o-mini
apiKey: dummy
baseUrl: http://127.0.0.1:8000/v1
- name: bench-responses
provider:
custom:
formats:
- type: responses
params:
model: gpt-4o-mini
apiKey: dummy
baseUrl: http://127.0.0.1:8000/v1
Compare a shared protocol cell
- agentgateway vs AISIX (api7)
- agentgateway vs APISIX
- agentgateway vs Bifrost
- agentgateway vs Busbar
- agentgateway vs GoModel
- agentgateway vs Helicone
- agentgateway vs Higress
- agentgateway vs Kong
- agentgateway vs LiteLLM · Python
- agentgateway vs LiteLLM · Rust
- agentgateway vs One-API
- agentgateway vs Plano
- agentgateway vs Portkey
- agentgateway vs TensorZero