GoModel 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: enterpilot/gomodel:0.2.3. 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)
Cohere → Anthropic——Not declared: recorded note 1—
OpenAI → AnthropicAdded latency p50 (µs)332Valid · n=16,334 gateway / 245,181 direct—
OpenAI → AnthropicAdded latency p99 (µs)508Valid · n=16,334 gateway / 245,181 direct—
OpenAI → AnthropicGateway p99 at concurrency 1 (µs)538Valid · n=16,334—
OpenAI → AnthropicDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=245,181—
OpenAI → AnthropicCPU per request (µs)424.9Valid—
OpenAI → AnthropicRequests per CPU-second2,353.4Valid—
OpenAI → AnthropicCost window concurrency8Valid—
OpenAI → AnthropicCost window core utilisation0.707Valid—
OpenAI → AnthropicCost window successful requests40,079Valid—
OpenAI → AnthropicCost window throughput (req/s)6,679Valid—
OpenAI → AnthropicCost window threads13Valid—
OpenAI → AnthropicNon-voluntary context switches per request0Valid—
OpenAI → AnthropicCost window major page faults0Valid—
OpenAI → AnthropicAdded time to first event p50 (µs)482Valid · n=100 gateway / 100 direct—
OpenAI → AnthropicAdded time to first event p99 (µs)635Valid · n=100 gateway / 100 direct—
OpenAI → AnthropicAdded inter-frame gap p50 (µs)5Valid · n=63 gateway / 63 direct—
OpenAI → AnthropicAdded inter-frame gap p99 (µs)21Valid · n=63 gateway / 63 direct—
OpenAI → AnthropicStreams sustained (frames/s)47,311.5Valid—
OpenAI → AnthropicStreams sustained1,140Valid—
OpenAI → AnthropicIdle RSS (MiB)52.91Valid—
OpenAI → AnthropicSteady-state RSS (MiB)87.58Valid—
OpenAI → AnthropicRecovered RSS (MiB)87.09Valid—
OpenAI → AnthropicPeak RSS (MiB)89.44Valid—
OpenAI → AnthropicPeak RSS high-water mark (MiB)89.07Valid—
OpenAI → AnthropicTime to plateau (s)—Not measured—
OpenAI → AnthropicMemory growth (MiB/min)-0.11Valid—
OpenAI → AnthropicMemory load duration (s)300Valid—
OpenAI → AnthropicMemory shape under load0Valid—
OpenAI → AnthropicIdle memory shape—Not measured—
OpenAI → AnthropicIdle memory static1Valid—
OpenAI → AnthropicIdle memory growth (MiB/min)0.323Valid—
OpenAI → AnthropicThroughput (req/s)4,631concurrency 2; n=27,7921 ms
OpenAI → AnthropicThroughput (req/s)6,656concurrency 8; n=39,9475 ms
OpenAI → AnthropicThroughput (req/s)6,820concurrency 16; n=40,92910 ms
OpenAI → AnthropicThroughput (req/s)7,453concurrency 64; n=44,72450 ms
OpenAI → AnthropicThroughput (req/s)7,474concurrency 128; n=44,854100 ms
OpenAI → AnthropicThroughput (req/s)7,474concurrency 128; n=44,854Unbounded
OpenAI Responses → AnthropicAdded latency p50 (µs)363Valid · n=14,995 gateway / 248,903 direct—
OpenAI Responses → AnthropicAdded latency p99 (µs)639Valid · n=14,995 gateway / 248,903 direct—
OpenAI Responses → AnthropicGateway p99 at concurrency 1 (µs)669Valid · n=14,995—
OpenAI Responses → AnthropicDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=248,903—
OpenAI Responses → AnthropicCPU per request (µs)572Valid—
OpenAI Responses → AnthropicRequests per CPU-second1,748.3Valid—
OpenAI Responses → AnthropicCost window concurrency8Valid—
OpenAI Responses → AnthropicCost window core utilisation0.854Valid—
OpenAI Responses → AnthropicCost window successful requests35,927Valid—
OpenAI Responses → AnthropicCost window throughput (req/s)5,987Valid—
OpenAI Responses → AnthropicCost window threads12Valid—
OpenAI Responses → AnthropicNon-voluntary context switches per request0.009Valid—
OpenAI Responses → AnthropicCost window major page faults0Valid—
OpenAI Responses → AnthropicAdded time to first event p50 (µs)—Untestable—
OpenAI Responses → AnthropicAdded time to first event p99 (µs)—Untestable—
OpenAI Responses → AnthropicAdded inter-frame gap p50 (µs)—Untestable—
OpenAI Responses → AnthropicAdded inter-frame gap p99 (µs)—Untestable—
OpenAI Responses → AnthropicStreams sustained (frames/s)—Untestable—
OpenAI Responses → AnthropicStreams sustained—Untestable—
OpenAI Responses → AnthropicIdle RSS (MiB)53.16Valid—
OpenAI Responses → AnthropicSteady-state RSS (MiB)240.9Valid—
OpenAI Responses → AnthropicRecovered RSS (MiB)157.5Valid—
OpenAI Responses → AnthropicPeak RSS (MiB)324.5Valid—
OpenAI Responses → AnthropicPeak RSS high-water mark (MiB)324.1Valid—
OpenAI Responses → AnthropicTime to plateau (s)—Not measured—
OpenAI Responses → AnthropicMemory growth (MiB/min)10.7Valid—
OpenAI Responses → AnthropicMemory load duration (s)300Valid—
OpenAI Responses → AnthropicMemory shape under load0Valid—
OpenAI Responses → AnthropicIdle memory shape—Not measured—
OpenAI Responses → AnthropicIdle memory static1Valid—
OpenAI Responses → AnthropicIdle memory growth (MiB/min)0.351Valid—
OpenAI Responses → AnthropicThroughput (req/s)4,280concurrency 2; n=25,6891 ms
OpenAI Responses → AnthropicThroughput (req/s)5,982concurrency 8; n=35,8975 ms
OpenAI Responses → AnthropicThroughput (req/s)5,982concurrency 8; n=35,89710 ms
OpenAI Responses → AnthropicThroughput (req/s)6,343concurrency 64; n=38,06050 ms
OpenAI Responses → AnthropicThroughput (req/s)6,343concurrency 64; n=38,060100 ms
OpenAI Responses → AnthropicThroughput (req/s)6,343concurrency 64; n=38,060Unbounded
Bedrock → Anthropic——Not declared: recorded note 1—
Gemini → Anthropic——Not declared: recorded note 1—
Anthropic → AnthropicAdded latency p50 (µs)386Valid · n=14,086 gateway / 240,685 direct—
Anthropic → AnthropicAdded latency p99 (µs)722Valid · n=14,086 gateway / 240,685 direct—
Anthropic → AnthropicGateway p99 at concurrency 1 (µs)753Valid · n=14,086—
Anthropic → AnthropicDirect-to-mock p99 at concurrency 1 (µs)31Valid · n=240,685—
Anthropic → AnthropicCPU per request (µs)498.8Valid—
Anthropic → AnthropicRequests per CPU-second2,004.7Valid—
Anthropic → AnthropicCost window concurrency8Valid—
Anthropic → AnthropicCost window core utilisation0.786Valid—
Anthropic → AnthropicCost window successful requests37,928Valid—
Anthropic → AnthropicCost window throughput (req/s)6,320Valid—
Anthropic → AnthropicCost window threads13Valid—
Anthropic → AnthropicNon-voluntary context switches per request0Valid—
Anthropic → AnthropicCost window major page faults0Valid—
Anthropic → AnthropicAdded time to first event p50 (µs)485Valid · n=100 gateway / 100 direct—
Anthropic → AnthropicAdded time to first event p99 (µs)1,078Valid · n=100 gateway / 100 direct—
Anthropic → AnthropicAdded inter-frame gap p50 (µs)—Below resolution · n=63 gateway / 63 direct—
Anthropic → AnthropicAdded inter-frame gap p99 (µs)—Below resolution · n=63 gateway / 63 direct—
Anthropic → AnthropicStreams sustained (frames/s)64,695.4Valid—
Anthropic → AnthropicStreams sustained1,559Valid—
Anthropic → AnthropicIdle RSS (MiB)52.96Valid—
Anthropic → AnthropicSteady-state RSS (MiB)86.85Valid—
Anthropic → AnthropicRecovered RSS (MiB)87.08Valid—
Anthropic → AnthropicPeak RSS (MiB)88.52Valid—
Anthropic → AnthropicPeak RSS high-water mark (MiB)88.11Valid—
Anthropic → AnthropicTime to plateau (s)—Not measured—
Anthropic → AnthropicMemory growth (MiB/min)-0.254Valid—
Anthropic → AnthropicMemory load duration (s)300Valid—
Anthropic → AnthropicMemory shape under load0Valid—
Anthropic → AnthropicIdle memory shape—Not measured—
Anthropic → AnthropicIdle memory static1Valid—
Anthropic → AnthropicIdle memory growth (MiB/min)0.315Valid—
Anthropic → AnthropicThroughput (req/s)2,351concurrency 1; n=14,1101 ms
Anthropic → AnthropicThroughput (req/s)6,462concurrency 8; n=38,7785 ms
Anthropic → AnthropicThroughput (req/s)6,654concurrency 16; n=39,93110 ms
Anthropic → AnthropicThroughput (req/s)7,222concurrency 64; n=43,33750 ms
Anthropic → AnthropicThroughput (req/s)7,237concurrency 128; n=43,430100 ms
Anthropic → AnthropicThroughput (req/s)7,237concurrency 128; n=43,430Unbounded
Bedrock → OpenAI——Not declared: recorded note 1—
Cohere → OpenAI——Not declared: recorded note 1—
OpenAI Responses → OpenAI——Not declared: recorded note 1—
Gemini → OpenAI——Not declared: recorded note 1—
Anthropic → OpenAIAdded latency p50 (µs)348Valid · n=15,595 gateway / 242,839 direct—
Anthropic → OpenAIAdded latency p99 (µs)531Valid · n=15,595 gateway / 242,839 direct—
Anthropic → OpenAIGateway p99 at concurrency 1 (µs)561Valid · n=15,595—
Anthropic → OpenAIDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=242,839—
Anthropic → OpenAICPU per request (µs)449.6Valid—
Anthropic → OpenAIRequests per CPU-second2,224.3Valid—
Anthropic → OpenAICost window concurrency8Valid—
Anthropic → OpenAICost window core utilisation0.696Valid—
Anthropic → OpenAICost window successful requests37,257Valid—
Anthropic → OpenAICost window throughput (req/s)6,208Valid—
Anthropic → OpenAICost window threads13Valid—
Anthropic → OpenAINon-voluntary context switches per request0.006Valid—
Anthropic → OpenAICost window major page faults0Valid—
Anthropic → OpenAIAdded time to first event p50 (µs)482Valid · n=100 gateway / 100 direct—
Anthropic → OpenAIAdded time to first event p99 (µs)681Valid · n=100 gateway / 100 direct—
Anthropic → OpenAIAdded inter-frame gap p50 (µs)—Below resolution · n=63 gateway / 63 direct—
Anthropic → OpenAIAdded inter-frame gap p99 (µs)14Valid · n=63 gateway / 63 direct—
Anthropic → OpenAIStreams sustained (frames/s)61,069.6Valid—
Anthropic → OpenAIStreams sustained1,536Valid—
Anthropic → OpenAIIdle RSS (MiB)53.24Valid—
Anthropic → OpenAISteady-state RSS (MiB)87.93Valid—
Anthropic → OpenAIRecovered RSS (MiB)89.77Valid—
Anthropic → OpenAIPeak RSS (MiB)90.31Valid—
Anthropic → OpenAIPeak RSS high-water mark (MiB)90Valid—
Anthropic → OpenAITime to plateau (s)—Not measured—
Anthropic → OpenAIMemory growth (MiB/min)0.027Valid—
Anthropic → OpenAIMemory load duration (s)300Valid—
Anthropic → OpenAIMemory shape under load0Valid—
Anthropic → OpenAIIdle memory shape—Not measured—
Anthropic → OpenAIIdle memory static1Valid—
Anthropic → OpenAIIdle memory growth (MiB/min)0.191Valid—
Anthropic → OpenAIThroughput (req/s)4,318concurrency 2; n=25,9141 ms
Anthropic → OpenAIThroughput (req/s)6,214concurrency 8; n=37,2925 ms
Anthropic → OpenAIThroughput (req/s)6,384concurrency 16; n=38,31310 ms
Anthropic → OpenAIThroughput (req/s)6,988concurrency 64; n=41,93750 ms
Anthropic → OpenAIThroughput (req/s)7,071concurrency 128; n=42,435100 ms
Anthropic → OpenAIThroughput (req/s)7,071concurrency 128; n=42,435Unbounded
OpenAI → OpenAIAdded latency p50 (µs)343Valid · n=15,837 gateway / 239,533 direct—
OpenAI → OpenAIAdded latency p99 (µs)565Valid · n=15,837 gateway / 239,533 direct—
OpenAI → OpenAIGateway p99 at concurrency 1 (µs)596Valid · n=15,837—
OpenAI → OpenAIDirect-to-mock p99 at concurrency 1 (µs)31Valid · n=239,533—
OpenAI → OpenAICPU per request (µs)439.2Valid—
OpenAI → OpenAIRequests per CPU-second2,277.1Valid—
OpenAI → OpenAICost window concurrency8Valid—
OpenAI → OpenAICost window core utilisation0.714Valid—
OpenAI → OpenAICost window successful requests39,121Valid—
OpenAI → OpenAICost window throughput (req/s)6,519Valid—
OpenAI → OpenAICost window threads14Valid—
OpenAI → OpenAINon-voluntary context switches per request0Valid—
OpenAI → OpenAICost window major page faults0Valid—
OpenAI → OpenAIAdded time to first event p50 (µs)479Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded time to first event p99 (µs)601Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded inter-frame gap p50 (µs)—Below resolution · n=63 gateway / 63 direct—
OpenAI → OpenAIAdded inter-frame gap p99 (µs)26Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIStreams sustained (frames/s)50,390.1Valid—
OpenAI → OpenAIStreams sustained1,208Valid—
OpenAI → OpenAIIdle RSS (MiB)53Valid—
OpenAI → OpenAISteady-state RSS (MiB)87.26Valid—
OpenAI → OpenAIRecovered RSS (MiB)90.46Valid—
OpenAI → OpenAIPeak RSS (MiB)90.51Valid—
OpenAI → OpenAIPeak RSS high-water mark (MiB)89.02Valid—
OpenAI → OpenAITime to plateau (s)—Not measured—
OpenAI → OpenAIMemory growth (MiB/min)-0.338Valid—
OpenAI → OpenAIMemory load duration (s)300Valid—
OpenAI → OpenAIMemory shape under load0Valid—
OpenAI → OpenAIIdle memory shape—Not measured—
OpenAI → OpenAIIdle memory static1Valid—
OpenAI → OpenAIIdle memory growth (MiB/min)0.411Valid—
OpenAI → OpenAIThroughput (req/s)4,555concurrency 2; n=27,3351 ms
OpenAI → OpenAIThroughput (req/s)6,685concurrency 8; n=40,1175 ms
OpenAI → OpenAIThroughput (req/s)6,862concurrency 16; n=41,18010 ms
OpenAI → OpenAIThroughput (req/s)7,415concurrency 64; n=44,49650 ms
OpenAI → OpenAIThroughput (req/s)7,475concurrency 128; n=44,859100 ms
OpenAI → OpenAIThroughput (req/s)7,475concurrency 128; n=44,859Unbounded
Gemini → Cohere——Not declared: recorded note 1—
OpenAI Responses → CohereAdded latency p50 (µs)353Valid · n=15,319 gateway / 247,454 direct—
OpenAI Responses → CohereAdded latency p99 (µs)600Valid · n=15,319 gateway / 247,454 direct—
OpenAI Responses → CohereGateway p99 at concurrency 1 (µs)630Valid · n=15,319—
OpenAI Responses → CohereDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=247,454—
OpenAI Responses → CohereCPU per request (µs)569.9Valid—
OpenAI Responses → CohereRequests per CPU-second1,754.6Valid—
OpenAI Responses → CohereCost window concurrency8Valid—
OpenAI Responses → CohereCost window core utilisation0.857Valid—
OpenAI Responses → CohereCost window successful requests36,198Valid—
OpenAI Responses → CohereCost window throughput (req/s)6,032Valid—
OpenAI Responses → CohereCost window threads12Valid—
OpenAI Responses → CohereNon-voluntary context switches per request0.013Valid—
OpenAI Responses → CohereCost window major page faults0Valid—
OpenAI Responses → CohereAdded time to first event p50 (µs)—Untestable—
OpenAI Responses → CohereAdded time to first event p99 (µs)—Untestable—
OpenAI Responses → CohereAdded inter-frame gap p50 (µs)—Untestable—
OpenAI Responses → CohereAdded inter-frame gap p99 (µs)—Untestable—
OpenAI Responses → CohereStreams sustained (frames/s)—Untestable—
OpenAI Responses → CohereStreams sustained—Untestable—
OpenAI Responses → CohereIdle RSS (MiB)53.12Valid—
OpenAI Responses → CohereSteady-state RSS (MiB)229.9Valid—
OpenAI Responses → CohereRecovered RSS (MiB)145.3Valid—
OpenAI Responses → CoherePeak RSS (MiB)317Valid—
OpenAI Responses → CoherePeak RSS high-water mark (MiB)316.4Valid—
OpenAI Responses → CohereTime to plateau (s)—Not measured—
OpenAI Responses → CohereMemory growth (MiB/min)-59.17Valid—
OpenAI Responses → CohereMemory load duration (s)300Valid—
OpenAI Responses → CohereMemory shape under load-1Valid—
OpenAI Responses → CohereIdle memory shape—Not measured—
OpenAI Responses → CohereIdle memory static1Valid—
OpenAI Responses → CohereIdle memory growth (MiB/min)0.344Valid—
OpenAI Responses → CohereThroughput (req/s)4,322concurrency 2; n=25,9401 ms
OpenAI Responses → CohereThroughput (req/s)6,006concurrency 8; n=36,0465 ms
OpenAI Responses → CohereThroughput (req/s)6,006concurrency 8; n=36,04610 ms
OpenAI Responses → CohereThroughput (req/s)6,311concurrency 64; n=37,87150 ms
OpenAI Responses → CohereThroughput (req/s)6,311concurrency 64; n=37,871100 ms
OpenAI Responses → CohereThroughput (req/s)6,311concurrency 64; n=37,871Unbounded
Anthropic → CohereAdded latency p50 (µs)329Valid · n=16,446 gateway / 244,026 direct—
Anthropic → CohereAdded latency p99 (µs)513Valid · n=16,446 gateway / 244,026 direct—
Anthropic → CohereGateway p99 at concurrency 1 (µs)543Valid · n=16,446—
Anthropic → CohereDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=244,026—
Anthropic → CohereCPU per request (µs)426.2Valid—
Anthropic → CohereRequests per CPU-second2,346.4Valid—
Anthropic → CohereCost window concurrency8Valid—
Anthropic → CohereCost window core utilisation0.682Valid—
Anthropic → CohereCost window successful requests38,505Valid—
Anthropic → CohereCost window throughput (req/s)6,416Valid—
Anthropic → CohereCost window threads12Valid—
Anthropic → CohereNon-voluntary context switches per request0.006Valid—
Anthropic → CohereCost window major page faults0Valid—
Anthropic → CohereAdded time to first event p50 (µs)—Untestable—
Anthropic → CohereAdded time to first event p99 (µs)—Untestable—
Anthropic → CohereAdded inter-frame gap p50 (µs)—Untestable—
Anthropic → CohereAdded inter-frame gap p99 (µs)—Untestable—
Anthropic → CohereStreams sustained (frames/s)—Untestable—
Anthropic → CohereStreams sustained—Untestable—
Anthropic → CohereIdle RSS (MiB)53.11Valid—
Anthropic → CohereSteady-state RSS (MiB)87.6Valid—
Anthropic → CohereRecovered RSS (MiB)88.75Valid—
Anthropic → CoherePeak RSS (MiB)89.65Valid—
Anthropic → CoherePeak RSS high-water mark (MiB)89.16Valid—
Anthropic → CohereTime to plateau (s)—Not measured—
Anthropic → CohereMemory growth (MiB/min)0.114Valid—
Anthropic → CohereMemory load duration (s)300Valid—
Anthropic → CohereMemory shape under load0Valid—
Anthropic → CohereIdle memory shape—Not measured—
Anthropic → CohereIdle memory static1Valid—
Anthropic → CohereIdle memory growth (MiB/min)0.251Valid—
Anthropic → CohereThroughput (req/s)4,543concurrency 2; n=27,2641 ms
Anthropic → CohereThroughput (req/s)6,320concurrency 8; n=37,9315 ms
Anthropic → CohereThroughput (req/s)6,500concurrency 16; n=39,01010 ms
Anthropic → CohereThroughput (req/s)7,107concurrency 64; n=42,64750 ms
Anthropic → CohereThroughput (req/s)7,172concurrency 128; n=43,039100 ms
Anthropic → CohereThroughput (req/s)7,172concurrency 128; n=43,039Unbounded
Cohere → Cohere——Not declared: recorded note 1—
Bedrock → Cohere——Not declared: recorded note 1—
OpenAI → CohereAdded latency p50 (µs)335Valid · n=16,166 gateway / 236,668 direct—
OpenAI → CohereAdded latency p99 (µs)515Valid · n=16,166 gateway / 236,668 direct—
OpenAI → CohereGateway p99 at concurrency 1 (µs)546Valid · n=16,166—
OpenAI → CohereDirect-to-mock p99 at concurrency 1 (µs)31Valid · n=236,668—
OpenAI → CohereCPU per request (µs)418.7Valid—
OpenAI → CohereRequests per CPU-second2,388.3Valid—
OpenAI → CohereCost window concurrency8Valid—
OpenAI → CohereCost window core utilisation0.707Valid—
OpenAI → CohereCost window successful requests40,625Valid—
OpenAI → CohereCost window throughput (req/s)6,769Valid—
OpenAI → CohereCost window threads12Valid—
OpenAI → CohereNon-voluntary context switches per request0.005Valid—
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)52.88Valid—
OpenAI → CohereSteady-state RSS (MiB)87.43Valid—
OpenAI → CohereRecovered RSS (MiB)90.28Valid—
OpenAI → CoherePeak RSS (MiB)90.28Valid—
OpenAI → CoherePeak RSS high-water mark (MiB)88.98Valid—
OpenAI → CohereTime to plateau (s)—Not measured—
OpenAI → CohereMemory growth (MiB/min)0.204Valid—
OpenAI → CohereMemory load duration (s)300Valid—
OpenAI → CohereMemory shape under load0Valid—
OpenAI → CohereIdle memory shape—Not measured—
OpenAI → CohereIdle memory static1Valid—
OpenAI → CohereIdle memory growth (MiB/min)0.26Valid—
OpenAI → CohereThroughput (req/s)4,690concurrency 2; n=28,1531 ms
OpenAI → CohereThroughput (req/s)6,742concurrency 8; n=40,4585 ms
OpenAI → CohereThroughput (req/s)6,886concurrency 16; n=41,33110 ms
OpenAI → CohereThroughput (req/s)7,538concurrency 64; n=45,23250 ms
OpenAI → CohereThroughput (req/s)7,549concurrency 128; n=45,303100 ms
OpenAI → CohereThroughput (req/s)7,549concurrency 128; n=45,303Unbounded
Anthropic → BedrockAdded latency p50 (µs)452Valid · n=12,219 gateway / 247,325 direct—
Anthropic → BedrockAdded latency p99 (µs)774Valid · n=12,219 gateway / 247,325 direct—
Anthropic → BedrockGateway p99 at concurrency 1 (µs)804Valid · n=12,219—
Anthropic → BedrockDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=247,325—
Anthropic → BedrockCPU per request (µs)553.6Valid—
Anthropic → BedrockRequests per CPU-second1,806.4Valid—
Anthropic → BedrockCost window concurrency8Valid—
Anthropic → BedrockCost window core utilisation0.773Valid—
Anthropic → BedrockCost window successful requests33,617Valid—
Anthropic → BedrockCost window throughput (req/s)5,602Valid—
Anthropic → BedrockCost window threads12Valid—
Anthropic → BedrockNon-voluntary context switches per request0.007Valid—
Anthropic → BedrockCost window major page faults0Valid—
Anthropic → BedrockAdded time to first event p50 (µs)—Untestable—
Anthropic → BedrockAdded time to first event p99 (µs)—Untestable—
Anthropic → BedrockAdded inter-frame gap p50 (µs)—Untestable—
Anthropic → BedrockAdded inter-frame gap p99 (µs)—Untestable—
Anthropic → BedrockStreams sustained (frames/s)—Untestable—
Anthropic → BedrockStreams sustained—Untestable—
Anthropic → BedrockIdle RSS (MiB)52.89Valid—
Anthropic → BedrockSteady-state RSS (MiB)91.17Valid—
Anthropic → BedrockRecovered RSS (MiB)91.67Valid—
Anthropic → BedrockPeak RSS (MiB)93.25Valid—
Anthropic → BedrockPeak RSS high-water mark (MiB)92.71Valid—
Anthropic → BedrockTime to plateau (s)—Not measured—
Anthropic → BedrockMemory growth (MiB/min)-0.047Valid—
Anthropic → BedrockMemory load duration (s)300Valid—
Anthropic → BedrockMemory shape under load0Valid—
Anthropic → BedrockIdle memory shape0Valid—
Anthropic → BedrockIdle memory static0Valid—
Anthropic → BedrockIdle memory growth (MiB/min)0.384Valid—
Anthropic → BedrockThroughput (req/s)2,020concurrency 1; n=12,1271 ms
Anthropic → BedrockThroughput (req/s)5,567concurrency 8; n=33,4095 ms
Anthropic → BedrockThroughput (req/s)5,567concurrency 8; n=33,40910 ms
Anthropic → BedrockThroughput (req/s)6,093concurrency 64; n=36,56250 ms
Anthropic → BedrockThroughput (req/s)6,134concurrency 128; n=36,811100 ms
Anthropic → BedrockThroughput (req/s)6,134concurrency 128; n=36,811Unbounded
Cohere → Bedrock——Not declared: recorded note 1—
Gemini → Bedrock——Not declared: recorded note 1—
Bedrock → Bedrock——Not declared: recorded note 1—
OpenAI Responses → BedrockAdded latency p50 (µs)471Valid · n=11,671 gateway / 247,559 direct—
OpenAI Responses → BedrockAdded latency p99 (µs)809Valid · n=11,671 gateway / 247,559 direct—
OpenAI Responses → BedrockGateway p99 at concurrency 1 (µs)839Valid · n=11,671—
OpenAI Responses → BedrockDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=247,559—
OpenAI Responses → BedrockCPU per request (µs)674.7Valid—
OpenAI Responses → BedrockRequests per CPU-second1,482.2Valid—
OpenAI Responses → BedrockCost window concurrency8Valid—
OpenAI Responses → BedrockCost window core utilisation0.87Valid—
OpenAI Responses → BedrockCost window successful requests31,052Valid—
OpenAI Responses → BedrockCost window throughput (req/s)5,174Valid—
OpenAI Responses → BedrockCost window threads13Valid—
OpenAI Responses → BedrockNon-voluntary context switches per request0.024Valid—
OpenAI Responses → BedrockCost window major page faults0Valid—
OpenAI Responses → BedrockAdded time to first event p50 (µs)—Untestable—
OpenAI Responses → BedrockAdded time to first event p99 (µs)—Untestable—
OpenAI Responses → BedrockAdded inter-frame gap p50 (µs)—Untestable—
OpenAI Responses → BedrockAdded inter-frame gap p99 (µs)—Untestable—
OpenAI Responses → BedrockStreams sustained (frames/s)—Untestable—
OpenAI Responses → BedrockStreams sustained—Untestable—
OpenAI Responses → BedrockIdle RSS (MiB)53.07Valid—
OpenAI Responses → BedrockSteady-state RSS (MiB)193.3Valid—
OpenAI Responses → BedrockRecovered RSS (MiB)130.7Valid—
OpenAI Responses → BedrockPeak RSS (MiB)276.3Valid—
OpenAI Responses → BedrockPeak RSS high-water mark (MiB)276Valid—
OpenAI Responses → BedrockTime to plateau (s)—Not measured—
OpenAI Responses → BedrockMemory growth (MiB/min)-105.1Valid—
OpenAI Responses → BedrockMemory load duration (s)300Valid—
OpenAI Responses → BedrockMemory shape under load-1Valid—
OpenAI Responses → BedrockIdle memory shape—Not measured—
OpenAI Responses → BedrockIdle memory static1Valid—
OpenAI Responses → BedrockIdle memory growth (MiB/min)0.277Valid—
OpenAI Responses → BedrockThroughput (req/s)1,945concurrency 1; n=11,6721 ms
OpenAI Responses → BedrockThroughput (req/s)4,809concurrency 4; n=28,8605 ms
OpenAI Responses → BedrockThroughput (req/s)5,149concurrency 8; n=30,90210 ms
OpenAI Responses → BedrockThroughput (req/s)5,409concurrency 64; n=32,45950 ms
OpenAI Responses → BedrockThroughput (req/s)5,409concurrency 64; n=32,459100 ms
OpenAI Responses → BedrockThroughput (req/s)5,409concurrency 64; n=32,459Unbounded
OpenAI → BedrockAdded latency p50 (µs)450Valid · n=12,265 gateway / 239,336 direct—
OpenAI → BedrockAdded latency p99 (µs)756Valid · n=12,265 gateway / 239,336 direct—
OpenAI → BedrockGateway p99 at concurrency 1 (µs)787Valid · n=12,265—
OpenAI → BedrockDirect-to-mock p99 at concurrency 1 (µs)31Valid · n=239,336—
OpenAI → BedrockCPU per request (µs)545.4Valid—
OpenAI → BedrockRequests per CPU-second1,833.4Valid—
OpenAI → BedrockCost window concurrency8Valid—
OpenAI → BedrockCost window core utilisation0.799Valid—
OpenAI → BedrockCost window successful requests35,275Valid—
OpenAI → BedrockCost window throughput (req/s)5,878Valid—
OpenAI → BedrockCost window threads12Valid—
OpenAI → BedrockNon-voluntary context switches per request0Valid—
OpenAI → BedrockCost window major page faults0Valid—
OpenAI → BedrockAdded time to first event p50 (µs)—Untestable—
OpenAI → BedrockAdded time to first event p99 (µs)—Untestable—
OpenAI → BedrockAdded inter-frame gap p50 (µs)—Untestable—
OpenAI → BedrockAdded inter-frame gap p99 (µs)—Untestable—
OpenAI → BedrockStreams sustained (frames/s)—Untestable—
OpenAI → BedrockStreams sustained—Untestable—
OpenAI → BedrockIdle RSS (MiB)52.4Valid—
OpenAI → BedrockSteady-state RSS (MiB)91.29Valid—
OpenAI → BedrockRecovered RSS (MiB)88.52Valid—
OpenAI → BedrockPeak RSS (MiB)92.88Valid—
OpenAI → BedrockPeak RSS high-water mark (MiB)92.66Valid—
OpenAI → BedrockTime to plateau (s)—Not measured—
OpenAI → BedrockMemory growth (MiB/min)0.289Valid—
OpenAI → BedrockMemory load duration (s)300Valid—
OpenAI → BedrockMemory shape under load0Valid—
OpenAI → BedrockIdle memory shape—Not measured—
OpenAI → BedrockIdle memory static1Valid—
OpenAI → BedrockIdle memory growth (MiB/min)0.29Valid—
OpenAI → BedrockThroughput (req/s)2,045concurrency 1; n=12,2741 ms
OpenAI → BedrockThroughput (req/s)5,862concurrency 8; n=35,1775 ms
OpenAI → BedrockThroughput (req/s)5,862concurrency 8; n=35,17710 ms
OpenAI → BedrockThroughput (req/s)6,347concurrency 64; n=38,08750 ms
OpenAI → BedrockThroughput (req/s)6,361concurrency 128; n=38,177100 ms
OpenAI → BedrockThroughput (req/s)6,361concurrency 128; n=38,177Unbounded
Cohere → Gemini——Not declared: recorded note 1—
Bedrock → Gemini——Not declared: recorded note 1—
Gemini → Gemini——Not declared: recorded note 1—
Anthropic → GeminiAdded latency p50 (µs)336Valid · n=16,147 gateway / 237,693 direct—
Anthropic → GeminiAdded latency p99 (µs)499Valid · n=16,147 gateway / 237,693 direct—
Anthropic → GeminiGateway p99 at concurrency 1 (µs)530Valid · n=16,147—
Anthropic → GeminiDirect-to-mock p99 at concurrency 1 (µs)31Valid · n=237,693—
Anthropic → GeminiCPU per request (µs)432.5Valid—
Anthropic → GeminiRequests per CPU-second2,312.2Valid—
Anthropic → GeminiCost window concurrency8Valid—
Anthropic → GeminiCost window core utilisation0.683Valid—
Anthropic → GeminiCost window successful requests38,012Valid—
Anthropic → GeminiCost window throughput (req/s)6,334Valid—
Anthropic → GeminiCost window threads12Valid—
Anthropic → GeminiNon-voluntary context switches per request0Valid—
Anthropic → GeminiCost window major page faults0Valid—
Anthropic → GeminiAdded time to first event p50 (µs)—Untestable—
Anthropic → GeminiAdded time to first event p99 (µs)—Untestable—
Anthropic → GeminiAdded inter-frame gap p50 (µs)—Untestable—
Anthropic → GeminiAdded inter-frame gap p99 (µs)—Untestable—
Anthropic → GeminiStreams sustained (frames/s)—Untestable—
Anthropic → GeminiStreams sustained—Untestable—
Anthropic → GeminiIdle RSS (MiB)53.18Valid—
Anthropic → GeminiSteady-state RSS (MiB)88.14Valid—
Anthropic → GeminiRecovered RSS (MiB)88.41Valid—
Anthropic → GeminiPeak RSS (MiB)90Valid—
Anthropic → GeminiPeak RSS high-water mark (MiB)89.93Valid—
Anthropic → GeminiTime to plateau (s)—Not measured—
Anthropic → GeminiMemory growth (MiB/min)0.25Valid—
Anthropic → GeminiMemory load duration (s)300Valid—
Anthropic → GeminiMemory shape under load0Valid—
Anthropic → GeminiIdle memory shape0Valid—
Anthropic → GeminiIdle memory static0Valid—
Anthropic → GeminiIdle memory growth (MiB/min)0.558Valid—
Anthropic → GeminiThroughput (req/s)4,493concurrency 2; n=26,9621 ms
Anthropic → GeminiThroughput (req/s)6,289concurrency 8; n=37,7435 ms
Anthropic → GeminiThroughput (req/s)6,450concurrency 16; n=38,70810 ms
Anthropic → GeminiThroughput (req/s)7,092concurrency 64; n=42,55850 ms
Anthropic → GeminiThroughput (req/s)7,137concurrency 128; n=42,837100 ms
Anthropic → GeminiThroughput (req/s)7,137concurrency 128; n=42,837Unbounded
OpenAI Responses → GeminiAdded latency p50 (µs)353Valid · n=15,337 gateway / 250,993 direct—
OpenAI Responses → GeminiAdded latency p99 (µs)599Valid · n=15,337 gateway / 250,993 direct—
OpenAI Responses → GeminiGateway p99 at concurrency 1 (µs)629Valid · n=15,337—
OpenAI Responses → GeminiDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=250,993—
OpenAI Responses → GeminiCPU per request (µs)571.8Valid—
OpenAI Responses → GeminiRequests per CPU-second1,749Valid—
OpenAI Responses → GeminiCost window concurrency8Valid—
OpenAI Responses → GeminiCost window core utilisation0.855Valid—
OpenAI Responses → GeminiCost window successful requests36,012Valid—
OpenAI Responses → GeminiCost window throughput (req/s)6,001Valid—
OpenAI Responses → GeminiCost window threads12Valid—
OpenAI Responses → GeminiNon-voluntary context switches per request0.017Valid—
OpenAI Responses → GeminiCost window major page faults0Valid—
OpenAI Responses → GeminiAdded time to first event p50 (µs)—Untestable—
OpenAI Responses → GeminiAdded time to first event p99 (µs)—Untestable—
OpenAI Responses → GeminiAdded inter-frame gap p50 (µs)—Untestable—
OpenAI Responses → GeminiAdded inter-frame gap p99 (µs)—Untestable—
OpenAI Responses → GeminiStreams sustained (frames/s)—Untestable—
OpenAI Responses → GeminiStreams sustained—Untestable—
OpenAI Responses → GeminiIdle RSS (MiB)53.45Valid—
OpenAI Responses → GeminiSteady-state RSS (MiB)280.7Valid—
OpenAI Responses → GeminiRecovered RSS (MiB)149.6Valid—
OpenAI Responses → GeminiPeak RSS (MiB)371.7Valid—
OpenAI Responses → GeminiPeak RSS high-water mark (MiB)371.3Valid—
OpenAI Responses → GeminiTime to plateau (s)—Not measured—
OpenAI Responses → GeminiMemory growth (MiB/min)70.65Valid—
OpenAI Responses → GeminiMemory load duration (s)300Valid—
OpenAI Responses → GeminiMemory shape under load1Valid—
OpenAI Responses → GeminiIdle memory shape0Valid—
OpenAI Responses → GeminiIdle memory static0Valid—
OpenAI Responses → GeminiIdle memory growth (MiB/min)0.665Valid—
OpenAI Responses → GeminiThroughput (req/s)4,292concurrency 2; n=25,7581 ms
OpenAI Responses → GeminiThroughput (req/s)5,944concurrency 8; n=35,6705 ms
OpenAI Responses → GeminiThroughput (req/s)5,944concurrency 8; n=35,67010 ms
OpenAI Responses → GeminiThroughput (req/s)6,212concurrency 64; n=37,27750 ms
OpenAI Responses → GeminiThroughput (req/s)6,215concurrency 128; n=37,303100 ms
OpenAI Responses → GeminiThroughput (req/s)6,215concurrency 128; n=37,303Unbounded
OpenAI → GeminiAdded latency p50 (µs)336Valid · n=16,158 gateway / 241,090 direct—
OpenAI → GeminiAdded latency p99 (µs)508Valid · n=16,158 gateway / 241,090 direct—
OpenAI → GeminiGateway p99 at concurrency 1 (µs)539Valid · n=16,158—
OpenAI → GeminiDirect-to-mock p99 at concurrency 1 (µs)31Valid · n=241,090—
OpenAI → GeminiCPU per request (µs)424.6Valid—
OpenAI → GeminiRequests per CPU-second2,355.2Valid—
OpenAI → GeminiCost window concurrency8Valid—
OpenAI → GeminiCost window core utilisation0.707Valid—
OpenAI → GeminiCost window successful requests40,086Valid—
OpenAI → GeminiCost window throughput (req/s)6,680Valid—
OpenAI → GeminiCost window threads12Valid—
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)53.06Valid—
OpenAI → GeminiSteady-state RSS (MiB)87.94Valid—
OpenAI → GeminiRecovered RSS (MiB)91.47Valid—
OpenAI → GeminiPeak RSS (MiB)91.51Valid—
OpenAI → GeminiPeak RSS high-water mark (MiB)89.38Valid—
OpenAI → GeminiTime to plateau (s)—Not measured—
OpenAI → GeminiMemory growth (MiB/min)0.081Valid—
OpenAI → GeminiMemory load duration (s)300Valid—
OpenAI → GeminiMemory shape under load0Valid—
OpenAI → GeminiIdle memory shape0Valid—
OpenAI → GeminiIdle memory static0Valid—
OpenAI → GeminiIdle memory growth (MiB/min)0.486Valid—
OpenAI → GeminiThroughput (req/s)4,561concurrency 2; n=27,3721 ms
OpenAI → GeminiThroughput (req/s)6,538concurrency 8; n=39,2365 ms
OpenAI → GeminiThroughput (req/s)6,721concurrency 16; n=40,33310 ms
OpenAI → GeminiThroughput (req/s)7,332concurrency 64; n=43,99650 ms
OpenAI → GeminiThroughput (req/s)7,393concurrency 128; n=44,369100 ms
OpenAI → GeminiThroughput (req/s)7,393concurrency 128; n=44,369Unbounded
Anthropic → OpenAI Responses——Not declared: recorded note 1—
OpenAI → OpenAI Responses——Not declared: recorded note 1—
OpenAI Responses → OpenAI ResponsesAdded latency p50 (µs)363Valid · n=15,015 gateway / 246,146 direct—
OpenAI Responses → OpenAI ResponsesAdded latency p99 (µs)591Valid · n=15,015 gateway / 246,146 direct—
OpenAI Responses → OpenAI ResponsesGateway p99 at concurrency 1 (µs)621Valid · n=15,015—
OpenAI Responses → OpenAI ResponsesDirect-to-mock p99 at concurrency 1 (µs)30Valid · n=246,146—
OpenAI Responses → OpenAI ResponsesCPU per request (µs)577.7Valid—
OpenAI Responses → OpenAI ResponsesRequests per CPU-second1,731Valid—
OpenAI Responses → OpenAI ResponsesCost window concurrency8Valid—
OpenAI Responses → OpenAI ResponsesCost window core utilisation0.856Valid—
OpenAI Responses → OpenAI ResponsesCost window successful requests35,675Valid—
OpenAI Responses → OpenAI ResponsesCost window throughput (req/s)5,945Valid—
OpenAI Responses → OpenAI ResponsesCost window threads12Valid—
OpenAI Responses → OpenAI ResponsesNon-voluntary context switches per request0Valid—
OpenAI Responses → OpenAI ResponsesCost window major page faults0Valid—
OpenAI Responses → OpenAI ResponsesAdded time to first event p50 (µs)—Untestable—
OpenAI Responses → OpenAI ResponsesAdded time to first event p99 (µs)—Untestable—
OpenAI Responses → OpenAI ResponsesAdded inter-frame gap p50 (µs)—Untestable—
OpenAI Responses → OpenAI ResponsesAdded inter-frame gap p99 (µs)—Untestable—
OpenAI Responses → OpenAI ResponsesStreams sustained (frames/s)—Untestable—
OpenAI Responses → OpenAI ResponsesStreams sustained—Untestable—
OpenAI Responses → OpenAI ResponsesIdle RSS (MiB)52.82Valid—
OpenAI Responses → OpenAI ResponsesSteady-state RSS (MiB)224.9Valid—
OpenAI Responses → OpenAI ResponsesRecovered RSS (MiB)125.7Valid—
OpenAI Responses → OpenAI ResponsesPeak RSS (MiB)326.3Valid—
OpenAI Responses → OpenAI ResponsesPeak RSS high-water mark (MiB)326Valid—
OpenAI Responses → OpenAI ResponsesTime to plateau (s)—Not measured—
OpenAI Responses → OpenAI ResponsesMemory growth (MiB/min)27.23Valid—
OpenAI Responses → OpenAI ResponsesMemory load duration (s)300Valid—
OpenAI Responses → OpenAI ResponsesMemory shape under load1Valid—
OpenAI Responses → OpenAI ResponsesIdle memory shape—Not measured—
OpenAI Responses → OpenAI ResponsesIdle memory static1Valid—
OpenAI Responses → OpenAI ResponsesIdle memory growth (MiB/min)0.309Valid—
OpenAI Responses → OpenAI ResponsesThroughput (req/s)2,485concurrency 1; n=14,9181 ms
OpenAI Responses → OpenAI ResponsesThroughput (req/s)5,918concurrency 8; n=35,5195 ms
OpenAI Responses → OpenAI ResponsesThroughput (req/s)5,918concurrency 8; n=35,51910 ms
OpenAI Responses → OpenAI ResponsesThroughput (req/s)6,295concurrency 64; n=37,77550 ms
OpenAI Responses → OpenAI ResponsesThroughput (req/s)6,295concurrency 64; n=37,775100 ms
OpenAI Responses → OpenAI ResponsesThroughput (req/s)6,295concurrency 64; n=37,775Unbounded
Gemini → OpenAI Responses——Not declared: recorded note 1—
Cohere → OpenAI Responses——Not declared: recorded note 1—
Bedrock → OpenAI Responses——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
Cohere → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI → AnthropicServed———Recorded run evidence—enterpilot/gomodel:0.2.3
OpenAI Responses → AnthropicServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Bedrock → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Gemini → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Anthropic → AnthropicServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Bedrock → OpenAINot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Cohere → OpenAINot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI Responses → OpenAINot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Gemini → OpenAINot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Anthropic → OpenAIServed———Recorded run evidence—enterpilot/gomodel:0.2.3
OpenAI → OpenAIServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Gemini → CohereNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI Responses → CohereServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Anthropic → CohereServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Cohere → CohereNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Bedrock → CohereNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI → CohereServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Anthropic → BedrockServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Cohere → BedrockNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Gemini → BedrockNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Bedrock → BedrockNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI Responses → BedrockServed———Recorded run evidence—enterpilot/gomodel:0.2.3
OpenAI → BedrockServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Cohere → GeminiNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Bedrock → GeminiNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Gemini → GeminiNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Anthropic → GeminiServed———Recorded run evidence—enterpilot/gomodel:0.2.3
OpenAI Responses → GeminiServed———Recorded run evidence—enterpilot/gomodel:0.2.3
OpenAI → GeminiServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Anthropic → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
OpenAI Responses → OpenAI ResponsesServed———Recorded run evidence—enterpilot/gomodel:0.2.3
Gemini → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Cohere → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
Bedrock → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—enterpilot/gomodel:0.2.3
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: 1280
OpenAI → Anthropic256HTTP 200: 2560
OpenAI → Anthropic512HTTP 200: 5120
OpenAI → Anthropic1,024HTTP 200: 1,0240
OpenAI → Anthropic2,048HTTP 200: 2,0480
OpenAI → Anthropic1,536HTTP 200: 1,5360
OpenAI → Anthropic1,280HTTP 200: 1,2800
OpenAI → Anthropic1,152HTTP 200: 1,1520
OpenAI → Anthropic1,088HTTP 200: 1,0880
OpenAI → Anthropic1,120HTTP 200: 1,1200
OpenAI → Anthropic1,136HTTP 200: 1,1360
OpenAI → Anthropic1,144HTTP 200: 1,1440
OpenAI → Anthropic1,140HTTP 200: 1,1400
OpenAI → Anthropic1,142HTTP 200: 1,1420
OpenAI → Anthropic1,141HTTP 200: 1,1410
OpenAI → Anthropic1,140HTTP 200: 1,1400
OpenAI → Anthropic1,140HTTP 200: 1,1400
Anthropic → Anthropic1HTTP 200: 10
Anthropic → Anthropic2HTTP 200: 20
Anthropic → Anthropic4HTTP 200: 40
Anthropic → Anthropic8HTTP 200: 80
Anthropic → Anthropic16HTTP 200: 160
Anthropic → Anthropic32HTTP 200: 320
Anthropic → Anthropic64HTTP 200: 640
Anthropic → Anthropic128HTTP 200: 1280
Anthropic → Anthropic256HTTP 200: 2560
Anthropic → Anthropic512HTTP 200: 5120
Anthropic → Anthropic1,024HTTP 200: 1,0240
Anthropic → Anthropic2,048HTTP 200: 2,0480
Anthropic → Anthropic1,536HTTP 200: 1,5360
Anthropic → Anthropic1,792HTTP 200: 1,7920
Anthropic → Anthropic1,664HTTP 200: 1,6640
Anthropic → Anthropic1,600HTTP 200: 1,6000
Anthropic → Anthropic1,568HTTP 200: 1,5680
Anthropic → Anthropic1,552HTTP 200: 1,5520
Anthropic → Anthropic1,560HTTP 200: 1,5600
Anthropic → Anthropic1,556HTTP 200: 1,5560
Anthropic → Anthropic1,558HTTP 200: 1,5580
Anthropic → Anthropic1,559HTTP 200: 1,5590
Anthropic → Anthropic1,559HTTP 200: 1,5590
Anthropic → Anthropic1,559HTTP 200: 1,5590
Anthropic → OpenAI1HTTP 200: 10
Anthropic → OpenAI2HTTP 200: 20
Anthropic → OpenAI4HTTP 200: 40
Anthropic → OpenAI8HTTP 200: 80
Anthropic → OpenAI16HTTP 200: 160
Anthropic → OpenAI32HTTP 200: 320
Anthropic → OpenAI64HTTP 200: 640
Anthropic → OpenAI128HTTP 200: 1280
Anthropic → OpenAI256HTTP 200: 2560
Anthropic → OpenAI512HTTP 200: 5120
Anthropic → OpenAI1,024HTTP 200: 1,0240
Anthropic → OpenAI2,048HTTP 200: 2,0480
Anthropic → OpenAI1,536HTTP 200: 1,5360
Anthropic → OpenAI1,792HTTP 200: 1,7920
Anthropic → OpenAI1,664HTTP 200: 1,6640
Anthropic → OpenAI1,600HTTP 200: 1,6000
Anthropic → OpenAI1,568HTTP 200: 1,5680
Anthropic → OpenAI1,552HTTP 200: 1,5520
Anthropic → OpenAI1,544HTTP 200: 1,5440
Anthropic → OpenAI1,540HTTP 200: 1,5400
Anthropic → OpenAI1,538HTTP 200: 1,5380
Anthropic → OpenAI1,537HTTP 200: 1,5370
Anthropic → OpenAI1,536HTTP 200: 1,5360
Anthropic → OpenAI1,536HTTP 200: 1,5360
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: 2560
OpenAI → OpenAI512HTTP 200: 5120
OpenAI → OpenAI1,024HTTP 200: 1,0240
OpenAI → OpenAI2,048HTTP 200: 2,0480
OpenAI → OpenAI1,536HTTP 200: 1,5360
OpenAI → OpenAI1,280HTTP 200: 1,2800
OpenAI → OpenAI1,152HTTP 200: 1,1520
OpenAI → OpenAI1,216HTTP 200: 1,2160
OpenAI → OpenAI1,184HTTP 200: 1,1840
OpenAI → OpenAI1,200HTTP 200: 1,2000
OpenAI → OpenAI1,208HTTP 200: 1,2080
OpenAI → OpenAI1,212HTTP 200: 1,2120
OpenAI → OpenAI1,210HTTP 200: 1,2100
OpenAI → OpenAI1,209HTTP 200: 1,2090
OpenAI → OpenAI1,208HTTP 200: 1,2080
OpenAI → OpenAI1,208HTTP 200: 1,2080

Recorded notes

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

  1. GoModel v0.2.3 source 86dbeffc254e0166367d72e0404f5a27aceeeaaa: local single-request checks using the engine's request bodies and authentication headers establish 16 exact protocol pairs; 15 are enabled on the pinned image. The 0.2.3 default configured-model allowlist remains enabled; no legacy fallback override is applied. OpenAI CompatibleProvider uses Chat Completions for chat/messages ingress and native Responses for responses ingress; the other OpenAI cross-operation cells do not select the requested upstream wire. Cohere supports translated chat/responses/messages. Native Cohere passthrough is opt-in (not in the default ENABLED_PASSTHROUGH_PROVIDERS), so cohere>cohere is not configured under the benchmark's out-of-the-box rule. Gemini and Bedrock implement upstream adapters but no native ingress/passthrough interface. These checks verify protocol routing only, not performance. Evidence: results/diagnostics/refresh-configuration/gomodel-0.2.3-correctness-preflight.json
  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