APISIX 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: apache/apisix:3.19.0-debian. 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) |
|---|---|---|---|---|
| Bedrock → OpenAI | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI | Added latency p50 (µs) | 179 | Valid · n=28,247 gateway / 260,315 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 340 | Valid · n=28,247 gateway / 260,315 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 368 | Valid · n=28,247 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=260,315 | — |
| OpenAI → OpenAI | CPU per request (µs) | 185.7 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 5,386.2 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.711 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 92,266 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 15,375 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 12 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0.000455 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 10,584 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 11,228 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | 8,877 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 63,882.4 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 1,470 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 191.2 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 228.2 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 228.4 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 228.4 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 233.2 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 66 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.05 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | — | Not measured | — |
| OpenAI → OpenAI | Idle memory shape | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory static | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | -0.464 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 12,187 | concurrency 4; n=73,136 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 23,089 | concurrency 32; n=138,550 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 25,474 | concurrency 64; n=152,851 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 26,590 | concurrency 256; n=159,560 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 26,590 | concurrency 256; n=159,560 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 26,590 | concurrency 256; n=159,560 | Unbounded |
| Anthropic → OpenAI | Added latency p50 (µs) | 193 | Valid · n=26,470 gateway / 257,076 direct | — |
| Anthropic → OpenAI | Added latency p99 (µs) | 373 | Valid · n=26,470 gateway / 257,076 direct | — |
| Anthropic → OpenAI | Gateway p99 at concurrency 1 (µs) | 402 | Valid · n=26,470 | — |
| Anthropic → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=257,076 | — |
| Anthropic → OpenAI | CPU per request (µs) | 198.4 | Valid | — |
| Anthropic → OpenAI | Requests per CPU-second | 5,039.2 | Valid | — |
| Anthropic → OpenAI | Cost window concurrency | 8 | Valid | — |
| Anthropic → OpenAI | Cost window core utilisation | 0.716 | Valid | — |
| Anthropic → OpenAI | Cost window successful requests | 86,876 | Valid | — |
| Anthropic → OpenAI | Cost window throughput (req/s) | 14,477 | Valid | — |
| Anthropic → OpenAI | Cost window threads | 12 | Valid | — |
| Anthropic → OpenAI | Non-voluntary context switches per request | 0.000576 | Valid | — |
| Anthropic → OpenAI | Cost window major page faults | 0 | Valid | — |
| Anthropic → OpenAI | Added time to first event p50 (µs) | 10,646 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added time to first event p99 (µs) | 11,159 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p50 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Added inter-frame gap p99 (µs) | 9,055 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → OpenAI | Streams sustained (frames/s) | 77,198.5 | Valid | — |
| Anthropic → OpenAI | Streams sustained | 1,919 | Valid | — |
| Anthropic → OpenAI | Idle RSS (MiB) | 190.6 | Valid | — |
| Anthropic → OpenAI | Steady-state RSS (MiB) | 224.6 | Valid | — |
| Anthropic → OpenAI | Recovered RSS (MiB) | 224.7 | Valid | — |
| Anthropic → OpenAI | Peak RSS (MiB) | 224.8 | Valid | — |
| Anthropic → OpenAI | Peak RSS high-water mark (MiB) | 229.6 | Valid | — |
| Anthropic → OpenAI | Time to plateau (s) | 66 | Valid | — |
| Anthropic → OpenAI | Memory growth (MiB/min) | 0.026 | Valid | — |
| Anthropic → OpenAI | Memory load duration (s) | 300 | Valid | — |
| Anthropic → OpenAI | Memory shape under load | — | Not measured | — |
| Anthropic → OpenAI | Idle memory shape | 0 | Valid | — |
| Anthropic → OpenAI | Idle memory static | 0 | Valid | — |
| Anthropic → OpenAI | Idle memory growth (MiB/min) | -0.452 | Valid | — |
| Anthropic → OpenAI | Throughput (req/s) | 11,298 | concurrency 4; n=67,801 | 1 ms |
| Anthropic → OpenAI | Throughput (req/s) | 21,698 | concurrency 32; n=130,205 | 5 ms |
| Anthropic → OpenAI | Throughput (req/s) | 24,156 | concurrency 64; n=144,943 | 10 ms |
| Anthropic → OpenAI | Throughput (req/s) | 25,454 | concurrency 256; n=152,737 | 50 ms |
| Anthropic → OpenAI | Throughput (req/s) | 25,454 | concurrency 256; n=152,737 | 100 ms |
| Anthropic → OpenAI | Throughput (req/s) | 25,454 | concurrency 256; n=152,737 | Unbounded |
| Gemini → OpenAI | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI | — | — | Not declared: recorded note 1 | — |
| Gemini → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Gemini | — | — | Not declared: recorded note 1 | — |
| Bedrock → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI → Gemini | — | — | Not declared: recorded note 1 | — |
| Cohere → Gemini | — | — | Not declared: recorded note 1 | — |
| Anthropic → Gemini | — | — | Not declared: recorded note 1 | — |
| Anthropic → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI → Bedrock | — | — | Not declared: recorded note 1 | — |
| Gemini → Bedrock | — | — | Not declared: recorded note 1 | — |
| Bedrock → Bedrock | Added latency p50 (µs) | 234 | Valid · n=21,813 gateway / 263,299 direct | — |
| Bedrock → Bedrock | Added latency p99 (µs) | 463 | Valid · n=21,813 gateway / 263,299 direct | — |
| Bedrock → Bedrock | Gateway p99 at concurrency 1 (µs) | 491 | Valid · n=21,813 | — |
| Bedrock → Bedrock | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=263,299 | — |
| Bedrock → Bedrock | CPU per request (µs) | 244.2 | Valid | — |
| Bedrock → Bedrock | Requests per CPU-second | 4,095.4 | Valid | — |
| Bedrock → Bedrock | Cost window concurrency | 8 | Valid | — |
| Bedrock → Bedrock | Cost window core utilisation | 0.749 | Valid | — |
| Bedrock → Bedrock | Cost window successful requests | 73,840 | Valid | — |
| Bedrock → Bedrock | Cost window throughput (req/s) | 12,305 | Valid | — |
| Bedrock → Bedrock | Cost window threads | 12 | Valid | — |
| Bedrock → Bedrock | Non-voluntary context switches per request | 0.000637 | 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) | 190.5 | Valid | — |
| Bedrock → Bedrock | Steady-state RSS (MiB) | 238.9 | Valid | — |
| Bedrock → Bedrock | Recovered RSS (MiB) | 239.4 | Valid | — |
| Bedrock → Bedrock | Peak RSS (MiB) | 240.4 | Valid | — |
| Bedrock → Bedrock | Peak RSS high-water mark (MiB) | 244.8 | Valid | — |
| Bedrock → Bedrock | Time to plateau (s) | — | Not measured | — |
| Bedrock → Bedrock | Memory growth (MiB/min) | 0.375 | Valid | — |
| Bedrock → Bedrock | Memory load duration (s) | 300 | Valid | — |
| Bedrock → Bedrock | Memory shape under load | 0 | Valid | — |
| Bedrock → Bedrock | Idle memory shape | 0 | Valid | — |
| Bedrock → Bedrock | Idle memory static | 0 | Valid | — |
| Bedrock → Bedrock | Idle memory growth (MiB/min) | -0.458 | Valid | — |
| Bedrock → Bedrock | Throughput (req/s) | 6,434 | concurrency 2; n=38,611 | 1 ms |
| Bedrock → Bedrock | Throughput (req/s) | 18,244 | concurrency 32; n=109,475 | 5 ms |
| Bedrock → Bedrock | Throughput (req/s) | 19,877 | concurrency 64; n=119,271 | 10 ms |
| Bedrock → Bedrock | Throughput (req/s) | 20,783 | concurrency 256; n=124,713 | 50 ms |
| Bedrock → Bedrock | Throughput (req/s) | 20,783 | concurrency 256; n=124,713 | 100 ms |
| Bedrock → Bedrock | Throughput (req/s) | 20,783 | concurrency 256; n=124,713 | Unbounded |
| Cohere → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Cohere | — | — | Not declared: recorded note 1 | — |
| Bedrock → Cohere | — | — | Not declared: recorded note 1 | — |
| Gemini → Cohere | — | — | Not declared: recorded note 1 | — |
| Cohere → Cohere | — | — | Not declared: recorded note 1 | — |
| Anthropic → Cohere | — | — | Not declared: recorded note 1 | — |
| Cohere → Anthropic | — | — | Not declared: recorded note 1 | — |
| Anthropic → Anthropic | Added latency p50 (µs) | 181 | Valid · n=28,060 gateway / 258,354 direct | — |
| Anthropic → Anthropic | Added latency p99 (µs) | 340 | Valid · n=28,060 gateway / 258,354 direct | — |
| Anthropic → Anthropic | Gateway p99 at concurrency 1 (µs) | 368 | Valid · n=28,060 | — |
| Anthropic → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=258,354 | — |
| Anthropic → Anthropic | CPU per request (µs) | 185 | Valid | — |
| Anthropic → Anthropic | Requests per CPU-second | 5,405.8 | Valid | — |
| Anthropic → Anthropic | Cost window concurrency | 8 | Valid | — |
| Anthropic → Anthropic | Cost window core utilisation | 0.681 | Valid | — |
| Anthropic → Anthropic | Cost window successful requests | 88,601 | Valid | — |
| Anthropic → Anthropic | Cost window throughput (req/s) | 14,764 | Valid | — |
| Anthropic → Anthropic | Cost window threads | 12 | Valid | — |
| Anthropic → Anthropic | Non-voluntary context switches per request | 0.000372 | Valid | — |
| Anthropic → Anthropic | Cost window major page faults | 0 | Valid | — |
| Anthropic → Anthropic | Added time to first event p50 (µs) | 10,516 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added time to first event p99 (µs) | 11,171 | Valid · n=100 gateway / 100 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p50 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Added inter-frame gap p99 (µs) | 8,998 | Valid · n=63 gateway / 63 direct | — |
| Anthropic → Anthropic | Streams sustained (frames/s) | 80,658.8 | Valid | — |
| Anthropic → Anthropic | Streams sustained | 1,844 | Valid | — |
| Anthropic → Anthropic | Idle RSS (MiB) | 193.1 | Valid | — |
| Anthropic → Anthropic | Steady-state RSS (MiB) | 230 | Valid | — |
| Anthropic → Anthropic | Recovered RSS (MiB) | 230.2 | Valid | — |
| Anthropic → Anthropic | Peak RSS (MiB) | 230.4 | Valid | — |
| Anthropic → Anthropic | Peak RSS high-water mark (MiB) | 235.2 | Valid | — |
| Anthropic → Anthropic | Time to plateau (s) | 66 | Valid | — |
| Anthropic → Anthropic | Memory growth (MiB/min) | 0.164 | Valid | — |
| Anthropic → Anthropic | Memory load duration (s) | 300 | Valid | — |
| Anthropic → Anthropic | Memory shape under load | — | Not measured | — |
| Anthropic → Anthropic | Idle memory shape | 0 | Valid | — |
| Anthropic → Anthropic | Idle memory static | 0 | Valid | — |
| Anthropic → Anthropic | Idle memory growth (MiB/min) | -0.455 | Valid | — |
| Anthropic → Anthropic | Throughput (req/s) | 12,499 | concurrency 4; n=75,005 | 1 ms |
| Anthropic → Anthropic | Throughput (req/s) | 23,800 | concurrency 32; n=142,817 | 5 ms |
| Anthropic → Anthropic | Throughput (req/s) | 26,599 | concurrency 64; n=159,609 | 10 ms |
| Anthropic → Anthropic | Throughput (req/s) | 27,850 | concurrency 256; n=167,116 | 50 ms |
| Anthropic → Anthropic | Throughput (req/s) | 27,850 | concurrency 256; n=167,116 | 100 ms |
| Anthropic → Anthropic | Throughput (req/s) | 27,850 | concurrency 256; n=167,116 | Unbounded |
| OpenAI Responses → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI → Anthropic | — | — | Not declared: recorded note 1 | — |
| Bedrock → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Anthropic → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI → 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) | 189 | Valid · n=26,997 gateway / 261,509 direct | — |
| OpenAI Responses → OpenAI Responses | Added latency p99 (µs) | 358 | Valid · n=26,997 gateway / 261,509 direct | — |
| OpenAI Responses → OpenAI Responses | Gateway p99 at concurrency 1 (µs) | 386 | Valid · n=26,997 | — |
| OpenAI Responses → OpenAI Responses | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=261,509 | — |
| OpenAI Responses → OpenAI Responses | CPU per request (µs) | 189.5 | Valid | — |
| OpenAI Responses → OpenAI Responses | Requests per CPU-second | 5,278.1 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window concurrency | 8 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window core utilisation | 0.757 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window successful requests | 96,219 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window throughput (req/s) | 16,034 | Valid | — |
| OpenAI Responses → OpenAI Responses | Cost window threads | 12 | Valid | — |
| OpenAI Responses → OpenAI Responses | Non-voluntary context switches per request | 0.000437 | 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) | 192.4 | Valid | — |
| OpenAI Responses → OpenAI Responses | Steady-state RSS (MiB) | 228.3 | Valid | — |
| OpenAI Responses → OpenAI Responses | Recovered RSS (MiB) | 228.3 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS (MiB) | 228.5 | Valid | — |
| OpenAI Responses → OpenAI Responses | Peak RSS high-water mark (MiB) | 233 | Valid | — |
| OpenAI Responses → OpenAI Responses | Time to plateau (s) | 66 | Valid | — |
| OpenAI Responses → OpenAI Responses | Memory growth (MiB/min) | 0.018 | 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 | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory static | 0 | Valid | — |
| OpenAI Responses → OpenAI Responses | Idle memory growth (MiB/min) | -0.464 | Valid | — |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 11,636 | concurrency 4; n=69,830 | 1 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 24,247 | concurrency 32; n=145,490 | 5 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 25,825 | concurrency 64; n=154,951 | 10 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 28,066 | concurrency 128; n=168,422 | 50 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 28,066 | concurrency 128; n=168,422 | 100 ms |
| OpenAI Responses → OpenAI Responses | Throughput (req/s) | 28,066 | concurrency 128; n=168,422 | Unbounded |
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 |
|---|---|---|---|---|---|---|---|
| Bedrock → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI → OpenAI | Served | — | — | — | Recorded run evidence | — | apache/apisix:3.19.0-debian |
| Anthropic → OpenAI | Served | — | — | — | Recorded run evidence | — | apache/apisix:3.19.0-debian |
| Gemini → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI Responses → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Cohere → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Gemini → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI Responses → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Bedrock → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Cohere → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Anthropic → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Anthropic → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Gemini → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Bedrock → Bedrock | Served | — | — | — | Recorded run evidence | — | apache/apisix:3.19.0-debian |
| Cohere → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI Responses → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI Responses → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Bedrock → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Gemini → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Cohere → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Anthropic → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Cohere → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Anthropic → Anthropic | Served | — | — | — | Recorded run evidence | — | apache/apisix:3.19.0-debian |
| OpenAI Responses → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Bedrock → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Gemini → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Gemini → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Anthropic → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Cohere → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| Bedrock → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | apache/apisix:3.19.0-debian |
| OpenAI Responses → OpenAI Responses | Served | — | — | — | Recorded run evidence | — | apache/apisix:3.19.0-debian |
- 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 | 1,536 | HTTP 200: 1,536 | 0 |
| OpenAI → OpenAI | 1,280 | HTTP 200: 1,280 | 0 |
| OpenAI → OpenAI | 1,408 | HTTP 200: 1,408 | 0 |
| OpenAI → OpenAI | 1,472 | HTTP 200: 1,472 | 0 |
| OpenAI → OpenAI | 1,440 | HTTP 200: 1,440 | 0 |
| OpenAI → OpenAI | 1,456 | HTTP 200: 1,456 | 0 |
| OpenAI → OpenAI | 1,464 | HTTP 200: 1,464 | 0 |
| OpenAI → OpenAI | 1,468 | HTTP 200: 1,468 | 0 |
| OpenAI → OpenAI | 1,470 | HTTP 200: 1,470 | 0 |
| OpenAI → OpenAI | 1,471 | HTTP 200: 1,471 | 0 |
| OpenAI → OpenAI | 1,470 | HTTP 200: 1,470 | 0 |
| OpenAI → OpenAI | 1,470 | HTTP 200: 1,470 | 0 |
| Anthropic → OpenAI | 1 | HTTP 200: 1 | 0 |
| Anthropic → OpenAI | 2 | HTTP 200: 2 | 0 |
| Anthropic → OpenAI | 4 | HTTP 200: 4 | 0 |
| Anthropic → OpenAI | 8 | HTTP 200: 8 | 0 |
| Anthropic → OpenAI | 16 | HTTP 200: 16 | 0 |
| Anthropic → OpenAI | 32 | HTTP 200: 32 | 0 |
| Anthropic → OpenAI | 64 | HTTP 200: 64 | 0 |
| Anthropic → OpenAI | 128 | HTTP 200: 128 | 0 |
| Anthropic → OpenAI | 256 | HTTP 200: 256 | 0 |
| Anthropic → OpenAI | 512 | HTTP 200: 512 | 0 |
| Anthropic → OpenAI | 1,024 | HTTP 200: 1,024 | 0 |
| Anthropic → OpenAI | 2,048 | HTTP 200: 2,048 | 0 |
| Anthropic → OpenAI | 1,536 | HTTP 200: 1,536 | 0 |
| Anthropic → OpenAI | 1,792 | HTTP 200: 1,792 | 0 |
| Anthropic → OpenAI | 1,920 | HTTP 200: 1,920 | 0 |
| Anthropic → OpenAI | 1,856 | HTTP 200: 1,856 | 0 |
| Anthropic → OpenAI | 1,888 | HTTP 200: 1,888 | 0 |
| Anthropic → OpenAI | 1,904 | HTTP 200: 1,904 | 0 |
| Anthropic → OpenAI | 1,912 | HTTP 200: 1,912 | 0 |
| Anthropic → OpenAI | 1,916 | HTTP 200: 1,916 | 0 |
| Anthropic → OpenAI | 1,918 | HTTP 200: 1,918 | 0 |
| Anthropic → OpenAI | 1,919 | HTTP 200: 1,919 | 0 |
| Anthropic → OpenAI | 1,919 | HTTP 200: 1,919 | 0 |
| Anthropic → OpenAI | 1,919 | HTTP 200: 1,919 | 0 |
| Anthropic → Anthropic | 1 | HTTP 200: 1 | 0 |
| Anthropic → Anthropic | 2 | HTTP 200: 2 | 0 |
| Anthropic → Anthropic | 4 | HTTP 200: 4 | 0 |
| Anthropic → Anthropic | 8 | HTTP 200: 8 | 0 |
| Anthropic → Anthropic | 16 | HTTP 200: 16 | 0 |
| Anthropic → Anthropic | 32 | HTTP 200: 32 | 0 |
| Anthropic → Anthropic | 64 | HTTP 200: 64 | 0 |
| Anthropic → Anthropic | 128 | HTTP 200: 128 | 0 |
| Anthropic → Anthropic | 256 | HTTP 200: 256 | 0 |
| Anthropic → Anthropic | 512 | HTTP 200: 512 | 0 |
| Anthropic → Anthropic | 1,024 | HTTP 200: 1,024 | 0 |
| Anthropic → Anthropic | 2,048 | HTTP 200: 2,048 | 0 |
| Anthropic → Anthropic | 1,536 | HTTP 200: 1,536 | 0 |
| Anthropic → Anthropic | 1,792 | HTTP 200: 1,792 | 0 |
| Anthropic → Anthropic | 1,920 | HTTP 200: 1,920 | 0 |
| Anthropic → Anthropic | 1,856 | HTTP 200: 1,856 | 0 |
| Anthropic → Anthropic | 1,824 | HTTP 200: 1,824 | 0 |
| Anthropic → Anthropic | 1,840 | HTTP 200: 1,840 | 0 |
| Anthropic → Anthropic | 1,848 | HTTP 200: 1,848 | 0 |
| Anthropic → Anthropic | 1,844 | HTTP 200: 1,844 | 0 |
| Anthropic → Anthropic | 1,846 | HTTP 200: 1,846 | 0 |
| Anthropic → Anthropic | 1,845 | HTTP 200: 1,845 | 0 |
| Anthropic → Anthropic | 1,844 | HTTP 200: 1,844 | 0 |
| Anthropic → Anthropic | 1,844 | HTTP 200: 1,844 | 0 |
Recorded notes
Text recorded with the cells above. Each note is shown once; rows refer to it by number.
- Pinned APISIX 3.19.0 source 473043623c161966f3f6ef4e8f12d2d8667a12d2: ai-providers capability tables and ai-protocols/converters registry support four native chat protocol paths plus Anthropic Messages to OpenAI Chat Completions conversion. The Gemini provider uses an OpenAI-compatible endpoint, not native Gemini generateContent; provider brands are not protocol support. Five exact pairs passed local response and recorder checks. Evidence: results/diagnostics/refresh-configuration/apisix-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-apisix-cc145fc7e19bd52b5c47dc4c3db32fb0511f656418b54e198d2b3cf922523d3f · complete raw record including RSS series
Configuration recorded by the run
# apisix.gen.yaml
routes:
- id: ai-proxy-chat
uri: /v1/chat/completions
methods: [POST]
plugins:
ai-proxy:
provider: openai-compatible
auth: { header: { Authorization: "Bearer sk-fake-benchmark-key" } }
options: { model: gpt-4o-mini }
override: { endpoint: "http://127.0.0.1:8000" }
- id: ai-proxy-responses
uri: /v1/responses
methods: [POST]
plugins:
ai-proxy:
provider: openai-compatible
auth: { header: { Authorization: "Bearer sk-fake-benchmark-key" } }
options: { model: gpt-4o-mini }
override: { endpoint: "http://127.0.0.1:8000" }
- id: ai-proxy-messages
uri: /v1/messages
methods: [POST]
plugins:
ai-proxy:
provider: anthropic
auth: { header: { Authorization: "Bearer sk-fake-benchmark-key" } }
options: { model: claude-3-5-sonnet-20241022 }
override: { endpoint: "http://127.0.0.1:8000" }
- id: ai-proxy-converse
uri: /model/anthropic.claude-3-sonnet-20240229-v1:0/converse
methods: [POST]
plugins:
ai-proxy:
provider: bedrock
provider_conf: { region: "us-east-1" }
auth:
aws:
access_key_id: "AKIAMOCKACCESSKEY"
secret_access_key: "mock-secret-access-key"
options: { model: anthropic.claude-3-sonnet-20240229-v1:0 }
override: { endpoint: "http://127.0.0.1:8000" }
- id: anthropic-to-openai
uri: /v1/messages
priority: 10
vars: [["http_x_bench_egress", "==", "openai"]]
methods: [POST]
plugins:
ai-proxy:
provider: openai-compatible
auth: { header: { Authorization: "Bearer sk-fake-benchmark-key" } }
options: { model: gpt-4o-mini }
override: { endpoint: "http://127.0.0.1:8000" }
#END
# config.gen.yaml
deployment:
role: data_plane
role_data_plane:
config_provider: yaml
apisix:
node_listen:
- 9080
nginx_config:
worker_processes: 4
Compare a shared protocol cell
- APISIX vs agentgateway
- APISIX vs AISIX (api7)
- APISIX vs Bifrost
- APISIX vs Busbar
- APISIX vs GoModel
- APISIX vs Helicone
- APISIX vs Higress
- APISIX vs Kong
- APISIX vs LiteLLM · Python
- APISIX vs LiteLLM · Rust
- APISIX vs One-API
- APISIX vs Plano
- APISIX vs Portkey
- APISIX vs TensorZero