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 → upstreamMetricValueState / reasonp99 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 → GeminiAdded latency p50 (µs)34,189Valid · n=178 gateway / 213,320 direct—
OpenAI → GeminiAdded latency p99 (µs)34,903Valid · n=178 gateway / 213,320 direct—
OpenAI → GeminiGateway p99 at concurrency 1 (µs)34,941Valid · n=178—
OpenAI → GeminiDirect-to-mock p99 at concurrency 1 (µs)38Valid · n=213,320—
OpenAI → GeminiCPU per request (µs)3,395.3Valid—
OpenAI → GeminiRequests per CPU-second294.5Valid—
OpenAI → GeminiCost window concurrency8Valid—
OpenAI → GeminiCost window core utilisation0.028Valid—
OpenAI → GeminiCost window successful requests215Valid—
OpenAI → GeminiCost window throughput (req/s)35Valid—
OpenAI → GeminiCost window threads84Valid—
OpenAI → GeminiNon-voluntary context switches per request0Valid—
OpenAI → GeminiCost window major page faults0Valid—
OpenAI → GeminiAdded time to first event p50 (µs)—Untestable—
OpenAI → GeminiAdded time to first event p99 (µs)—Untestable—
OpenAI → GeminiAdded inter-frame gap p50 (µs)—Untestable—
OpenAI → GeminiAdded inter-frame gap p99 (µs)—Untestable—
OpenAI → GeminiStreams sustained (frames/s)—Untestable—
OpenAI → GeminiStreams sustained—Untestable—
OpenAI → GeminiIdle RSS (MiB)80.32Valid—
OpenAI → GeminiSteady-state RSS (MiB)144.1Valid—
OpenAI → GeminiRecovered RSS (MiB)141.5Valid—
OpenAI → GeminiPeak RSS (MiB)144.8Valid—
OpenAI → GeminiPeak RSS high-water mark (MiB)144.7Valid—
OpenAI → GeminiTime to plateau (s)120Valid—
OpenAI → GeminiMemory growth (MiB/min)0.442Valid—
OpenAI → GeminiMemory load duration (s)300Valid—
OpenAI → GeminiMemory shape under load—Not measured—
OpenAI → GeminiIdle memory shape—Not measured—
OpenAI → GeminiIdle memory static1Valid—
OpenAI → GeminiIdle memory growth (MiB/min)-0.115Valid—
OpenAI → GeminiThroughput (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 bound1 ms
OpenAI → GeminiThroughput (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 bound5 ms
OpenAI → GeminiThroughput (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 bound10 ms
OpenAI → GeminiThroughput (req/s)30concurrency 1; n=18150 ms
OpenAI → GeminiThroughput (req/s)30concurrency 1; n=181100 ms
OpenAI → GeminiThroughput (req/s)38concurrency 16; n=230Unbounded
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 → CohereAdded latency p50 (µs)34,053Valid · n=178 gateway / 265,039 direct—
OpenAI → CohereAdded latency p99 (µs)42,953Valid · n=178 gateway / 265,039 direct—
OpenAI → CohereGateway p99 at concurrency 1 (µs)42,981Valid · n=178—
OpenAI → CohereDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=265,039—
OpenAI → CohereCPU per request (µs)3,063.1Valid—
OpenAI → CohereRequests per CPU-second326.5Valid—
OpenAI → CohereCost window concurrency8Valid—
OpenAI → CohereCost window core utilisation0.027Valid—
OpenAI → CohereCost window successful requests222Valid—
OpenAI → CohereCost window throughput (req/s)36Valid—
OpenAI → CohereCost window threads79Valid—
OpenAI → CohereNon-voluntary context switches per request0Valid—
OpenAI → CohereCost window major page faults0Valid—
OpenAI → CohereAdded time to first event p50 (µs)—Untestable—
OpenAI → CohereAdded time to first event p99 (µs)—Untestable—
OpenAI → CohereAdded inter-frame gap p50 (µs)—Untestable—
OpenAI → CohereAdded inter-frame gap p99 (µs)—Untestable—
OpenAI → CohereStreams sustained (frames/s)—Untestable—
OpenAI → CohereStreams sustained—Untestable—
OpenAI → CohereIdle RSS (MiB)86.47Valid—
OpenAI → CohereSteady-state RSS (MiB)141.6Valid—
OpenAI → CohereRecovered RSS (MiB)134.3Valid—
OpenAI → CoherePeak RSS (MiB)142.1Valid—
OpenAI → CoherePeak RSS high-water mark (MiB)142Valid—
OpenAI → CohereTime to plateau (s)127Valid—
OpenAI → CohereMemory growth (MiB/min)0.811Valid—
OpenAI → CohereMemory load duration (s)307Valid—
OpenAI → CohereMemory shape under load—Not measured—
OpenAI → CohereIdle memory shape—Not measured—
OpenAI → CohereIdle memory static1Valid—
OpenAI → CohereIdle memory growth (MiB/min)-0.111Valid—
OpenAI → CohereThroughput (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 bound1 ms
OpenAI → CohereThroughput (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 bound5 ms
OpenAI → CohereThroughput (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 bound10 ms
OpenAI → CohereThroughput (req/s)29concurrency 1; n=17850 ms
OpenAI → CohereThroughput (req/s)29concurrency 1; n=178100 ms
OpenAI → CohereThroughput (req/s)36concurrency 8; n=220Unbounded
OpenAI → Bedrock (upstream over HTTPS)Added latency p50 (µs)35,450Valid · n=170 gateway / 258,581 direct—
OpenAI → Bedrock (upstream over HTTPS)Added latency p99 (µs)35,742Valid · n=170 gateway / 258,581 direct—
OpenAI → Bedrock (upstream over HTTPS)Gateway p99 at concurrency 1 (µs)35,771Valid · n=170—
OpenAI → Bedrock (upstream over HTTPS)Direct-to-mock p99 at concurrency 1 (µs)29Valid · n=258,581—
OpenAI → Bedrock (upstream over HTTPS)CPU per request (µs)4,976.1Valid—
OpenAI → Bedrock (upstream over HTTPS)Requests per CPU-second201Valid—
OpenAI → Bedrock (upstream over HTTPS)Cost window concurrency8Valid—
OpenAI → Bedrock (upstream over HTTPS)Cost window core utilisation0.04Valid—
OpenAI → Bedrock (upstream over HTTPS)Cost window successful requests209Valid—
OpenAI → Bedrock (upstream over HTTPS)Cost window throughput (req/s)34Valid—
OpenAI → Bedrock (upstream over HTTPS)Cost window threads89Valid—
OpenAI → Bedrock (upstream over HTTPS)Non-voluntary context switches per request0Valid—
OpenAI → Bedrock (upstream over HTTPS)Cost window major page faults0Valid—
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)85.76Valid—
OpenAI → Bedrock (upstream over HTTPS)Steady-state RSS (MiB)348.8Valid—
OpenAI → Bedrock (upstream over HTTPS)Recovered RSS (MiB)332.7Valid—
OpenAI → Bedrock (upstream over HTTPS)Peak RSS (MiB)349.4Valid—
OpenAI → Bedrock (upstream over HTTPS)Peak RSS high-water mark (MiB)349.3Valid—
OpenAI → Bedrock (upstream over HTTPS)Time to plateau (s)174Valid—
OpenAI → Bedrock (upstream over HTTPS)Memory growth (MiB/min)0.605Valid—
OpenAI → Bedrock (upstream over HTTPS)Memory load duration (s)303Valid—
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 static1Valid—
OpenAI → Bedrock (upstream over HTTPS)Idle memory growth (MiB/min)-0.111Valid—
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 bound1 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 bound5 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 bound10 ms
OpenAI → Bedrock (upstream over HTTPS)Throughput (req/s)28concurrency 1; n=17250 ms
OpenAI → Bedrock (upstream over HTTPS)Throughput (req/s)28concurrency 1; n=172100 ms
OpenAI → Bedrock (upstream over HTTPS)Throughput (req/s)34concurrency 8; n=209Unbounded
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 → AnthropicAdded latency p50 (µs)34,189Valid · n=97 gateway / 264,624 direct—
OpenAI → AnthropicAdded latency p99 (µs)1,029,936Valid · n=97 gateway / 264,624 direct—
OpenAI → AnthropicGateway p99 at concurrency 1 (µs)1,029,964Valid · n=97—
OpenAI → AnthropicDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=264,624—
OpenAI → AnthropicCPU per request (µs)3,348.8Valid—
OpenAI → AnthropicRequests per CPU-second298.6Valid—
OpenAI → AnthropicCost window concurrency8Valid—
OpenAI → AnthropicCost window core utilisation0.027Valid—
OpenAI → AnthropicCost window successful requests215Valid—
OpenAI → AnthropicCost window throughput (req/s)35Valid—
OpenAI → AnthropicCost window threads214Valid—
OpenAI → AnthropicNon-voluntary context switches per request0Valid—
OpenAI → AnthropicCost window major page faults0Valid—
OpenAI → AnthropicAdded time to first event p50 (µs)751Valid · n=100 gateway / 100 direct—
OpenAI → AnthropicAdded time to first event p99 (µs)1,758Valid · n=100 gateway / 100 direct—
OpenAI → AnthropicAdded inter-frame gap p50 (µs)0Valid · n=63 gateway / 63 direct—
OpenAI → AnthropicAdded inter-frame gap p99 (µs)7Valid · n=63 gateway / 63 direct—
OpenAI → AnthropicStreams sustained (frames/s)4,429.7Valid—
OpenAI → AnthropicStreams sustained106Valid—
OpenAI → AnthropicIdle RSS (MiB)77.83Valid—
OpenAI → AnthropicSteady-state RSS (MiB)142.8Valid—
OpenAI → AnthropicRecovered RSS (MiB)139.7Valid—
OpenAI → AnthropicPeak RSS (MiB)143.1Valid—
OpenAI → AnthropicPeak RSS high-water mark (MiB)143.1Valid—
OpenAI → AnthropicTime to plateau (s)129Valid—
OpenAI → AnthropicMemory growth (MiB/min)0.171Valid—
OpenAI → AnthropicMemory load duration (s)301Valid—
OpenAI → AnthropicMemory shape under load—Not measured—
OpenAI → AnthropicIdle memory shape—Not measured—
OpenAI → AnthropicIdle memory static1Valid—
OpenAI → AnthropicIdle memory growth (MiB/min)-0.115Valid—
OpenAI → AnthropicThroughput (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 bound1 ms
OpenAI → AnthropicThroughput (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 bound5 ms
OpenAI → AnthropicThroughput (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 bound10 ms
OpenAI → AnthropicThroughput (req/s)30concurrency 1; n=18250 ms
OpenAI → AnthropicThroughput (req/s)30concurrency 1; n=182100 ms
OpenAI → AnthropicThroughput (req/s)38concurrency 16; n=229Unbounded
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 → OpenAIAdded latency p50 (µs)34,017Valid · n=102 gateway / 263,027 direct—
OpenAI → OpenAIAdded latency p99 (µs)589,609Valid · n=102 gateway / 263,027 direct—
OpenAI → OpenAIGateway p99 at concurrency 1 (µs)589,637Valid · n=102—
OpenAI → OpenAIDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=263,027—
OpenAI → OpenAICPU per request (µs)—Not measured—
OpenAI → OpenAIRequests per CPU-second—Not measured—
OpenAI → OpenAICost window concurrency—Not measured—
OpenAI → OpenAICost window core utilisation—Not measured—
OpenAI → OpenAICost window successful requests—Not measured—
OpenAI → OpenAICost window throughput (req/s)—Not measured—
OpenAI → OpenAICost window threads—Not measured—
OpenAI → OpenAINon-voluntary context switches per request—Not measured—
OpenAI → OpenAICost window major page faults—Not measured—
OpenAI → OpenAIAdded time to first event p50 (µs)728Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded time to first event p99 (µs)770Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded inter-frame gap p50 (µs)12Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIAdded inter-frame gap p99 (µs)27Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIStreams sustained (frames/s)7,497.8Valid—
OpenAI → OpenAIStreams sustained213Valid—
OpenAI → OpenAIIdle RSS (MiB)87.16Valid—
OpenAI → OpenAISteady-state RSS (MiB)141.9Valid—
OpenAI → OpenAIRecovered RSS (MiB)136.6Valid—
OpenAI → OpenAIPeak RSS (MiB)142.5Valid—
OpenAI → OpenAIPeak RSS high-water mark (MiB)142.5Valid—
OpenAI → OpenAITime to plateau (s)134Valid—
OpenAI → OpenAIMemory growth (MiB/min)0.116Valid—
OpenAI → OpenAIMemory load duration (s)300Valid—
OpenAI → OpenAIMemory shape under load—Not measured—
OpenAI → OpenAIIdle memory shape—Not measured—
OpenAI → OpenAIIdle memory static1Valid—
OpenAI → OpenAIIdle memory growth (MiB/min)-0.115Valid—
OpenAI → OpenAIThroughput (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 bound1 ms
OpenAI → OpenAIThroughput (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 bound5 ms
OpenAI → OpenAIThroughput (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 bound10 ms
OpenAI → OpenAIThroughput (req/s)32concurrency 1; n=19650 ms
OpenAI → OpenAIThroughput (req/s)32concurrency 1; n=196100 ms
OpenAI → OpenAIThroughput (req/s)38concurrency 16; n=229Unbounded
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 → upstreamCell stateProbe HTTP statusRecorded reasonRecorded detailEvidence scopeResponse excerptTested build
Anthropic → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Gemini → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Cohere → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI Responses → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Bedrock → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI Responses → GeminiNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Cohere → GeminiNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Bedrock → GeminiNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Anthropic → GeminiNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Gemini → GeminiNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI → GeminiServed———Recorded run evidence—justsong/one-api:v0.6.10
Bedrock → CohereNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Gemini → CohereNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Anthropic → CohereNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Cohere → CohereNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI Responses → CohereNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI → CohereServed———Recorded run evidence—justsong/one-api:v0.6.10
OpenAI → BedrockServed———Recorded run evidence—justsong/one-api:v0.6.10
Cohere → BedrockNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Gemini → BedrockNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Anthropic → BedrockNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Bedrock → BedrockNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI Responses → BedrockNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI → AnthropicServed———Recorded run evidence—justsong/one-api:v0.6.10
OpenAI Responses → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Cohere → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Gemini → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Bedrock → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Anthropic → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI Responses → OpenAINot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Cohere → OpenAINot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
OpenAI → OpenAIServed———Recorded run evidence—justsong/one-api:v0.6.10
Anthropic → OpenAINot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Gemini → OpenAINot declared—recorded note 1recorded note 1recorded note 2—justsong/one-api:v0.6.10
Bedrock → OpenAINot declared—recorded note 1recorded note 1recorded 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 → upstreamConcurrencyLanes by HTTP statusLanes with no response
OpenAI → Anthropic1HTTP 200: 10
OpenAI → Anthropic2HTTP 200: 20
OpenAI → Anthropic4HTTP 200: 40
OpenAI → Anthropic8HTTP 200: 80
OpenAI → Anthropic16HTTP 200: 160
OpenAI → Anthropic32HTTP 200: 320
OpenAI → Anthropic64HTTP 200: 640
OpenAI → Anthropic128HTTP 200: 115, HTTP 401: 5, HTTP 500: 4, HTTP 503: 40
OpenAI → Anthropic96HTTP 200: 960
OpenAI → Anthropic112HTTP 200: 108, HTTP 401: 3, HTTP 503: 10
OpenAI → Anthropic104HTTP 200: 1040
OpenAI → Anthropic108HTTP 200: 100, HTTP 401: 5, HTTP 500: 1, HTTP 503: 20
OpenAI → Anthropic106HTTP 200: 1060
OpenAI → Anthropic107HTTP 200: 101, HTTP 401: 5, HTTP 500: 10
OpenAI → Anthropic106HTTP 200: 1060
OpenAI → Anthropic106HTTP 200: 105, HTTP 401: 10
OpenAI → OpenAI1HTTP 200: 10
OpenAI → OpenAI2HTTP 200: 20
OpenAI → OpenAI4HTTP 200: 40
OpenAI → OpenAI8HTTP 200: 80
OpenAI → OpenAI16HTTP 200: 160
OpenAI → OpenAI32HTTP 200: 320
OpenAI → OpenAI64HTTP 200: 640
OpenAI → OpenAI128HTTP 200: 1280
OpenAI → OpenAI256HTTP 200: 238, HTTP 401: 8, HTTP 500: 3, HTTP 503: 70
OpenAI → OpenAI192HTTP 200: 1920
OpenAI → OpenAI224HTTP 200: 161, HTTP 401: 33, HTTP 500: 17, HTTP 503: 130
OpenAI → OpenAI208HTTP 200: 2080
OpenAI → OpenAI216HTTP 200: 150, HTTP 401: 50, HTTP 500: 6, HTTP 503: 100
OpenAI → OpenAI212HTTP 200: 2120
OpenAI → OpenAI214HTTP 200: 131, HTTP 401: 40, HTTP 500: 15, HTTP 503: 280
OpenAI → OpenAI213HTTP 200: 2130
OpenAI → OpenAI213HTTP 200: 155, HTTP 401: 37, HTTP 500: 7, HTTP 503: 140
OpenAI → OpenAI213HTTP 200: 2130

Recorded notes

Text recorded with the cells above. Each note is shown once; rows refer to it by number.

  1. 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
  2. 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

Configuration recorded by the run

Not recorded.

Compare a shared protocol cell

Historical measurements