One-API benchmark measurements
Operated by the Busbar team; Busbar is also an entrant. Gateway overhead against a local mock is not end-to-end model latency. Methodology and limitations.
Go · recorded build: justsong/one-api:v0.6.10. 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) |
|---|---|---|---|---|
| Anthropic → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| Bedrock → OpenAI Responses | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Gemini | — | — | Not declared: recorded note 1 | — |
| Cohere → Gemini | — | — | Not declared: recorded note 1 | — |
| Bedrock → Gemini | — | — | Not declared: recorded note 1 | — |
| Anthropic → Gemini | — | — | Not declared: recorded note 1 | — |
| Gemini → Gemini | — | — | Not declared: recorded note 1 | — |
| OpenAI → Gemini | Added latency p50 (µs) | 34,189 | Valid · n=178 gateway / 213,320 direct | — |
| OpenAI → Gemini | Added latency p99 (µs) | 34,903 | Valid · n=178 gateway / 213,320 direct | — |
| OpenAI → Gemini | Gateway p99 at concurrency 1 (µs) | 34,941 | Valid · n=178 | — |
| OpenAI → Gemini | Direct-to-mock p99 at concurrency 1 (µs) | 38 | Valid · n=213,320 | — |
| OpenAI → Gemini | CPU per request (µs) | 3,395.3 | Valid | — |
| OpenAI → Gemini | Requests per CPU-second | 294.5 | Valid | — |
| OpenAI → Gemini | Cost window concurrency | 8 | Valid | — |
| OpenAI → Gemini | Cost window core utilisation | 0.028 | Valid | — |
| OpenAI → Gemini | Cost window successful requests | 215 | Valid | — |
| OpenAI → Gemini | Cost window throughput (req/s) | 35 | Valid | — |
| OpenAI → Gemini | Cost window threads | 84 | 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) | 80.32 | Valid | — |
| OpenAI → Gemini | Steady-state RSS (MiB) | 144.1 | Valid | — |
| OpenAI → Gemini | Recovered RSS (MiB) | 141.5 | Valid | — |
| OpenAI → Gemini | Peak RSS (MiB) | 144.8 | Valid | — |
| OpenAI → Gemini | Peak RSS high-water mark (MiB) | 144.7 | Valid | — |
| OpenAI → Gemini | Time to plateau (s) | 120 | Valid | — |
| OpenAI → Gemini | Memory growth (MiB/min) | 0.442 | 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) | -0.115 | 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) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 ms |
| OpenAI → Gemini | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 ms |
| OpenAI → Gemini | Throughput (req/s) | 30 | concurrency 1; n=181 | 50 ms |
| OpenAI → Gemini | Throughput (req/s) | 30 | concurrency 1; n=181 | 100 ms |
| OpenAI → Gemini | Throughput (req/s) | 38 | concurrency 16; n=230 | Unbounded |
| Bedrock → Cohere | — | — | Not declared: recorded note 1 | — |
| Gemini → Cohere | — | — | Not declared: recorded note 1 | — |
| Anthropic → Cohere | — | — | Not declared: recorded note 1 | — |
| Cohere → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Cohere | — | — | Not declared: recorded note 1 | — |
| OpenAI → Cohere | Added latency p50 (µs) | 34,053 | Valid · n=178 gateway / 265,039 direct | — |
| OpenAI → Cohere | Added latency p99 (µs) | 42,953 | Valid · n=178 gateway / 265,039 direct | — |
| OpenAI → Cohere | Gateway p99 at concurrency 1 (µs) | 42,981 | Valid · n=178 | — |
| OpenAI → Cohere | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=265,039 | — |
| OpenAI → Cohere | CPU per request (µs) | 3,063.1 | Valid | — |
| OpenAI → Cohere | Requests per CPU-second | 326.5 | Valid | — |
| OpenAI → Cohere | Cost window concurrency | 8 | Valid | — |
| OpenAI → Cohere | Cost window core utilisation | 0.027 | Valid | — |
| OpenAI → Cohere | Cost window successful requests | 222 | Valid | — |
| OpenAI → Cohere | Cost window throughput (req/s) | 36 | Valid | — |
| OpenAI → Cohere | Cost window threads | 79 | Valid | — |
| OpenAI → Cohere | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Cohere | Cost window major page faults | 0 | Valid | — |
| OpenAI → Cohere | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Cohere | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Cohere | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Cohere | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Cohere | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Cohere | Streams sustained | — | Untestable | — |
| OpenAI → Cohere | Idle RSS (MiB) | 86.47 | Valid | — |
| OpenAI → Cohere | Steady-state RSS (MiB) | 141.6 | Valid | — |
| OpenAI → Cohere | Recovered RSS (MiB) | 134.3 | Valid | — |
| OpenAI → Cohere | Peak RSS (MiB) | 142.1 | Valid | — |
| OpenAI → Cohere | Peak RSS high-water mark (MiB) | 142 | Valid | — |
| OpenAI → Cohere | Time to plateau (s) | 127 | Valid | — |
| OpenAI → Cohere | Memory growth (MiB/min) | 0.811 | Valid | — |
| OpenAI → Cohere | Memory load duration (s) | 307 | Valid | — |
| OpenAI → Cohere | Memory shape under load | — | Not measured | — |
| OpenAI → Cohere | Idle memory shape | — | Not measured | — |
| OpenAI → Cohere | Idle memory static | 1 | Valid | — |
| OpenAI → Cohere | Idle memory growth (MiB/min) | -0.111 | Valid | — |
| OpenAI → Cohere | 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 → Cohere | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 ms |
| OpenAI → Cohere | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 ms |
| OpenAI → Cohere | Throughput (req/s) | 29 | concurrency 1; n=178 | 50 ms |
| OpenAI → Cohere | Throughput (req/s) | 29 | concurrency 1; n=178 | 100 ms |
| OpenAI → Cohere | Throughput (req/s) | 36 | concurrency 8; n=220 | Unbounded |
| OpenAI → Bedrock (upstream over HTTPS) | Added latency p50 (µs) | 35,450 | Valid · n=170 gateway / 258,581 direct | — |
| OpenAI → Bedrock (upstream over HTTPS) | Added latency p99 (µs) | 35,742 | Valid · n=170 gateway / 258,581 direct | — |
| OpenAI → Bedrock (upstream over HTTPS) | Gateway p99 at concurrency 1 (µs) | 35,771 | Valid · n=170 | — |
| OpenAI → Bedrock (upstream over HTTPS) | Direct-to-mock p99 at concurrency 1 (µs) | 29 | Valid · n=258,581 | — |
| OpenAI → Bedrock (upstream over HTTPS) | CPU per request (µs) | 4,976.1 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Requests per CPU-second | 201 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Cost window concurrency | 8 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Cost window core utilisation | 0.04 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Cost window successful requests | 209 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Cost window throughput (req/s) | 34 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Cost window threads | 89 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Cost window major page faults | 0 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Added time to first event p50 (µs) | — | Untestable | — |
| OpenAI → Bedrock (upstream over HTTPS) | Added time to first event p99 (µs) | — | Untestable | — |
| OpenAI → Bedrock (upstream over HTTPS) | Added inter-frame gap p50 (µs) | — | Untestable | — |
| OpenAI → Bedrock (upstream over HTTPS) | Added inter-frame gap p99 (µs) | — | Untestable | — |
| OpenAI → Bedrock (upstream over HTTPS) | Streams sustained (frames/s) | — | Untestable | — |
| OpenAI → Bedrock (upstream over HTTPS) | Streams sustained | — | Untestable | — |
| OpenAI → Bedrock (upstream over HTTPS) | Idle RSS (MiB) | 85.76 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Steady-state RSS (MiB) | 348.8 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Recovered RSS (MiB) | 332.7 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Peak RSS (MiB) | 349.4 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Peak RSS high-water mark (MiB) | 349.3 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Time to plateau (s) | 174 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Memory growth (MiB/min) | 0.605 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Memory load duration (s) | 303 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Memory shape under load | — | Not measured | — |
| OpenAI → Bedrock (upstream over HTTPS) | Idle memory shape | — | Not measured | — |
| OpenAI → Bedrock (upstream over HTTPS) | Idle memory static | 1 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | Idle memory growth (MiB/min) | -0.111 | Valid | — |
| OpenAI → Bedrock (upstream over HTTPS) | 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 (upstream over HTTPS) | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 ms |
| OpenAI → Bedrock (upstream over HTTPS) | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 ms |
| OpenAI → Bedrock (upstream over HTTPS) | Throughput (req/s) | 28 | concurrency 1; n=172 | 50 ms |
| OpenAI → Bedrock (upstream over HTTPS) | Throughput (req/s) | 28 | concurrency 1; n=172 | 100 ms |
| OpenAI → Bedrock (upstream over HTTPS) | Throughput (req/s) | 34 | concurrency 8; n=209 | Unbounded |
| Cohere → Bedrock | — | — | Not declared: recorded note 1 | — |
| Gemini → Bedrock | — | — | Not declared: recorded note 1 | — |
| Anthropic → Bedrock | — | — | Not declared: recorded note 1 | — |
| Bedrock → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → Bedrock | — | — | Not declared: recorded note 1 | — |
| OpenAI → Anthropic | Added latency p50 (µs) | 34,189 | Valid · n=97 gateway / 264,624 direct | — |
| OpenAI → Anthropic | Added latency p99 (µs) | 1,029,936 | Valid · n=97 gateway / 264,624 direct | — |
| OpenAI → Anthropic | Gateway p99 at concurrency 1 (µs) | 1,029,964 | Valid · n=97 | — |
| OpenAI → Anthropic | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=264,624 | — |
| OpenAI → Anthropic | CPU per request (µs) | 3,348.8 | Valid | — |
| OpenAI → Anthropic | Requests per CPU-second | 298.6 | Valid | — |
| OpenAI → Anthropic | Cost window concurrency | 8 | Valid | — |
| OpenAI → Anthropic | Cost window core utilisation | 0.027 | Valid | — |
| OpenAI → Anthropic | Cost window successful requests | 215 | Valid | — |
| OpenAI → Anthropic | Cost window throughput (req/s) | 35 | Valid | — |
| OpenAI → Anthropic | Cost window threads | 214 | 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) | 751 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added time to first event p99 (µs) | 1,758 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p50 (µs) | 0 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Added inter-frame gap p99 (µs) | 7 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → Anthropic | Streams sustained (frames/s) | 4,429.7 | Valid | — |
| OpenAI → Anthropic | Streams sustained | 106 | Valid | — |
| OpenAI → Anthropic | Idle RSS (MiB) | 77.83 | Valid | — |
| OpenAI → Anthropic | Steady-state RSS (MiB) | 142.8 | Valid | — |
| OpenAI → Anthropic | Recovered RSS (MiB) | 139.7 | Valid | — |
| OpenAI → Anthropic | Peak RSS (MiB) | 143.1 | Valid | — |
| OpenAI → Anthropic | Peak RSS high-water mark (MiB) | 143.1 | Valid | — |
| OpenAI → Anthropic | Time to plateau (s) | 129 | Valid | — |
| OpenAI → Anthropic | Memory growth (MiB/min) | 0.171 | Valid | — |
| OpenAI → Anthropic | Memory load duration (s) | 301 | 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) | -0.115 | 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) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 ms |
| OpenAI → Anthropic | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 ms |
| OpenAI → Anthropic | Throughput (req/s) | 30 | concurrency 1; n=182 | 50 ms |
| OpenAI → Anthropic | Throughput (req/s) | 30 | concurrency 1; n=182 | 100 ms |
| OpenAI → Anthropic | Throughput (req/s) | 38 | concurrency 16; n=229 | Unbounded |
| OpenAI Responses → Anthropic | — | — | Not declared: recorded note 1 | — |
| Cohere → Anthropic | — | — | Not declared: recorded note 1 | — |
| Gemini → Anthropic | — | — | Not declared: recorded note 1 | — |
| Bedrock → Anthropic | — | — | Not declared: recorded note 1 | — |
| Anthropic → Anthropic | — | — | Not declared: recorded note 1 | — |
| OpenAI Responses → OpenAI | — | — | Not declared: recorded note 1 | — |
| Cohere → OpenAI | — | — | Not declared: recorded note 1 | — |
| OpenAI → OpenAI | Added latency p50 (µs) | 34,017 | Valid · n=102 gateway / 263,027 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 589,609 | Valid · n=102 gateway / 263,027 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 589,637 | Valid · n=102 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=263,027 | — |
| OpenAI → OpenAI | CPU per request (µs) | — | Not measured | — |
| OpenAI → OpenAI | Requests per CPU-second | — | Not measured | — |
| OpenAI → OpenAI | Cost window concurrency | — | Not measured | — |
| OpenAI → OpenAI | Cost window core utilisation | — | Not measured | — |
| OpenAI → OpenAI | Cost window successful requests | — | Not measured | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | — | Not measured | — |
| OpenAI → OpenAI | Cost window threads | — | Not measured | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | — | Not measured | — |
| OpenAI → OpenAI | Cost window major page faults | — | Not measured | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 728 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 770 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | 12 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | 27 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 7,497.8 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 213 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 87.16 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 141.9 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 136.6 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 142.5 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 142.5 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 134 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.116 | 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) | -0.115 | Valid | — |
| OpenAI → 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 |
| OpenAI → OpenAI | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 32 | concurrency 1; n=196 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 32 | concurrency 1; n=196 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 38 | concurrency 16; n=229 | Unbounded |
| Anthropic → OpenAI | — | — | Not declared: recorded note 1 | — |
| Gemini → OpenAI | — | — | Not declared: recorded note 1 | — |
| Bedrock → 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 |
|---|---|---|---|---|---|---|---|
| Anthropic → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Gemini → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Cohere → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI Responses → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Bedrock → OpenAI Responses | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI Responses → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Cohere → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Bedrock → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Anthropic → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Gemini → Gemini | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI → Gemini | Served | — | — | — | Recorded run evidence | — | justsong/one-api:v0.6.10 |
| Bedrock → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Gemini → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Anthropic → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Cohere → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI Responses → Cohere | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI → Cohere | Served | — | — | — | Recorded run evidence | — | justsong/one-api:v0.6.10 |
| OpenAI → Bedrock | Served | — | — | — | Recorded run evidence | — | justsong/one-api:v0.6.10 |
| Cohere → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Gemini → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Anthropic → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Bedrock → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI Responses → Bedrock | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI → Anthropic | Served | — | — | — | Recorded run evidence | — | justsong/one-api:v0.6.10 |
| OpenAI Responses → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Cohere → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Gemini → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Bedrock → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Anthropic → Anthropic | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI Responses → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Cohere → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| OpenAI → OpenAI | Served | — | — | — | Recorded run evidence | — | justsong/one-api:v0.6.10 |
| Anthropic → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Gemini → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
| Bedrock → OpenAI | Not declared | — | recorded note 1 | recorded note 1 | recorded note 2 | — | justsong/one-api:v0.6.10 |
- 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: 115, HTTP 401: 5, HTTP 500: 4, HTTP 503: 4 | 0 |
| OpenAI → Anthropic | 96 | HTTP 200: 96 | 0 |
| OpenAI → Anthropic | 112 | HTTP 200: 108, HTTP 401: 3, HTTP 503: 1 | 0 |
| OpenAI → Anthropic | 104 | HTTP 200: 104 | 0 |
| OpenAI → Anthropic | 108 | HTTP 200: 100, HTTP 401: 5, HTTP 500: 1, HTTP 503: 2 | 0 |
| OpenAI → Anthropic | 106 | HTTP 200: 106 | 0 |
| OpenAI → Anthropic | 107 | HTTP 200: 101, HTTP 401: 5, HTTP 500: 1 | 0 |
| OpenAI → Anthropic | 106 | HTTP 200: 106 | 0 |
| OpenAI → Anthropic | 106 | HTTP 200: 105, HTTP 401: 1 | 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: 238, HTTP 401: 8, HTTP 500: 3, HTTP 503: 7 | 0 |
| OpenAI → OpenAI | 192 | HTTP 200: 192 | 0 |
| OpenAI → OpenAI | 224 | HTTP 200: 161, HTTP 401: 33, HTTP 500: 17, HTTP 503: 13 | 0 |
| OpenAI → OpenAI | 208 | HTTP 200: 208 | 0 |
| OpenAI → OpenAI | 216 | HTTP 200: 150, HTTP 401: 50, HTTP 500: 6, HTTP 503: 10 | 0 |
| OpenAI → OpenAI | 212 | HTTP 200: 212 | 0 |
| OpenAI → OpenAI | 214 | HTTP 200: 131, HTTP 401: 40, HTTP 500: 15, HTTP 503: 28 | 0 |
| OpenAI → OpenAI | 213 | HTTP 200: 213 | 0 |
| OpenAI → OpenAI | 213 | HTTP 200: 155, HTTP 401: 37, HTTP 500: 7, HTTP 503: 14 | 0 |
| OpenAI → OpenAI | 213 | HTTP 200: 213 | 0 |
Recorded notes
Text recorded with the cells above. Each note is shown once; rows refer to it by number.
- Pinned v0.6.10 source 3915ce9814b8261a1ab13ed93adec58b463cd75c: router/relay.go exposes OpenAI chat ingress, not native Responses, Anthropic, Gemini, Cohere or Bedrock ingress. relay/adaptor supports OpenAI, Anthropic, Gemini, Cohere (v1/chat) and AWS Bedrock (relay/adaptor/aws, InvokeModel through the AWS SDK at its default HTTPS endpoint, which the engine v1.2 catch-all DNS resolves to the mock) upstreams. This matrix describes the tested protocol routes, not all product features. Source: https://github.com/songquanpeng/one-api/blob/3915ce9814b8261a1ab13ed93adec58b463cd75c/router/relay.go
- 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-one-api-c9427cc70e392f48beb8e68d908f8924a7330748ac291dab1cd902b3f14c542f · complete raw record including RSS series
Configuration recorded by the run
Not recorded.
Compare a shared protocol cell
- One-API vs agentgateway
- One-API vs AISIX (api7)
- One-API vs APISIX
- One-API vs Bifrost
- One-API vs Busbar
- One-API vs GoModel
- One-API vs Helicone
- One-API vs Higress
- One-API vs Kong
- One-API vs LiteLLM · Python
- One-API vs LiteLLM · Rust
- One-API vs Plano
- One-API vs Portkey
- One-API vs TensorZero