Helicone benchmark measurements

Operated by the Busbar team; Busbar is also an entrant. Gateway overhead against a local mock is not end-to-end model latency. Methodology and limitations.

Rust · recorded build: built from source; recorded binary target/release/ai-gateway. 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)
Bedrock → Cohere——Not declared: recorded note 1—
Anthropic → Cohere——Not declared: recorded note 1—
Gemini → Cohere——Not declared: recorded note 1—
Cohere → Cohere——Not declared: recorded note 1—
OpenAI → Cohere——Not declared: recorded note 1—
OpenAI Responses → Cohere——Not declared: recorded note 1—
Anthropic → OpenAI——Not declared: recorded note 1—
OpenAI Responses → OpenAI——Not declared: recorded note 1—
OpenAI → OpenAIAdded latency p50 (µs)256Valid · n=21,418 gateway / 260,967 direct—
OpenAI → OpenAIAdded latency p99 (µs)274Valid · n=21,418 gateway / 260,967 direct—
OpenAI → OpenAIGateway p99 at concurrency 1 (µs)302Valid · n=21,418—
OpenAI → OpenAIDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=260,967—
OpenAI → OpenAICPU per request (µs)259.4Valid—
OpenAI → OpenAIRequests per CPU-second3,855.3Valid—
OpenAI → OpenAICost window concurrency8Valid—
OpenAI → OpenAICost window core utilisation0.984Valid—
OpenAI → OpenAICost window successful requests91,294Valid—
OpenAI → OpenAICost window throughput (req/s)15,213Valid—
OpenAI → OpenAICost window threads24Valid—
OpenAI → OpenAINon-voluntary context switches per request0Valid—
OpenAI → OpenAICost window major page faults0Valid—
OpenAI → OpenAIAdded time to first event p50 (µs)399Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded time to first event p99 (µs)493Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded inter-frame gap p50 (µs)0Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIAdded inter-frame gap p99 (µs)—Below resolution · n=63 gateway / 63 direct—
OpenAI → OpenAIStreams sustained (frames/s)21,883.1Valid—
OpenAI → OpenAIStreams sustained463Valid—
OpenAI → OpenAIIdle RSS (MiB)42.97Valid—
OpenAI → OpenAISteady-state RSS (MiB)56.18Valid—
OpenAI → OpenAIRecovered RSS (MiB)53.69Valid—
OpenAI → OpenAIPeak RSS (MiB)56.95Valid—
OpenAI → OpenAIPeak RSS high-water mark (MiB)56.61Valid—
OpenAI → OpenAITime to plateau (s)126Valid—
OpenAI → OpenAIMemory growth (MiB/min)0.5Valid—
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)0.124Valid—
OpenAI → OpenAIThroughput (req/s)15,405concurrency 8; n=92,4441 ms
OpenAI → OpenAIThroughput (req/s)16,288concurrency 32; n=97,7415 ms
OpenAI → OpenAIThroughput (req/s)16,376concurrency 64; n=98,26610 ms
OpenAI → OpenAIThroughput (req/s)16,376concurrency 64; n=98,26650 ms
OpenAI → OpenAIThroughput (req/s)16,376concurrency 64; n=98,266100 ms
OpenAI → OpenAIThroughput (req/s)16,376concurrency 64; n=98,266Unbounded
Cohere → OpenAI——Not declared: recorded note 1—
Bedrock → OpenAI——Not declared: recorded note 1—
Gemini → OpenAI——Not declared: recorded note 1—
OpenAI Responses → Anthropic——Not declared: recorded note 1—
Cohere → Anthropic——Not declared: recorded note 1—
OpenAI → AnthropicAdded latency p50 (µs)259Valid · n=21,200 gateway / 264,063 direct—
OpenAI → AnthropicAdded latency p99 (µs)278Valid · n=21,200 gateway / 264,063 direct—
OpenAI → AnthropicGateway p99 at concurrency 1 (µs)305Valid · n=21,200—
OpenAI → AnthropicDirect-to-mock p99 at concurrency 1 (µs)27Valid · n=264,063—
OpenAI → AnthropicCPU per request (µs)260.9Valid—
OpenAI → AnthropicRequests per CPU-second3,833.2Valid—
OpenAI → AnthropicCost window concurrency8Valid—
OpenAI → AnthropicCost window core utilisation0.983Valid—
OpenAI → AnthropicCost window successful requests90,694Valid—
OpenAI → AnthropicCost window throughput (req/s)15,114Valid—
OpenAI → AnthropicCost window threads26Valid—
OpenAI → AnthropicNon-voluntary context switches per request0Valid—
OpenAI → AnthropicCost window major page faults0Valid—
OpenAI → AnthropicAdded time to first event p50 (µs)400Valid · n=100 gateway / 100 direct—
OpenAI → AnthropicAdded time to first event p99 (µs)515Valid · n=100 gateway / 100 direct—
OpenAI → AnthropicAdded inter-frame gap p50 (µs)15Valid · n=63 gateway / 63 direct—
OpenAI → AnthropicAdded inter-frame gap p99 (µs)20Valid · n=63 gateway / 63 direct—
OpenAI → AnthropicStreams sustained (frames/s)22,502.4Valid—
OpenAI → AnthropicStreams sustained477Valid—
OpenAI → AnthropicIdle RSS (MiB)42.85Valid—
OpenAI → AnthropicSteady-state RSS (MiB)56.48Valid—
OpenAI → AnthropicRecovered RSS (MiB)53.44Valid—
OpenAI → AnthropicPeak RSS (MiB)57.04Valid—
OpenAI → AnthropicPeak RSS high-water mark (MiB)56.79Valid—
OpenAI → AnthropicTime to plateau (s)168Valid—
OpenAI → AnthropicMemory growth (MiB/min)0.11Valid—
OpenAI → AnthropicMemory load duration (s)300Valid—
OpenAI → AnthropicMemory shape under load—Not measured—
OpenAI → AnthropicIdle memory shape—Not measured—
OpenAI → AnthropicIdle memory static1Valid—
OpenAI → AnthropicIdle memory growth (MiB/min)0.124Valid—
OpenAI → AnthropicThroughput (req/s)15,212concurrency 8; n=91,2911 ms
OpenAI → AnthropicThroughput (req/s)16,081concurrency 32; n=96,4985 ms
OpenAI → AnthropicThroughput (req/s)16,164concurrency 64; n=97,00310 ms
OpenAI → AnthropicThroughput (req/s)16,164concurrency 64; n=97,00350 ms
OpenAI → AnthropicThroughput (req/s)16,164concurrency 64; n=97,003100 ms
OpenAI → AnthropicThroughput (req/s)16,164concurrency 64; n=97,003Unbounded
Bedrock → Anthropic——Not declared: recorded note 1—
Anthropic → AnthropicAdded latency p50 (µs)175Valid · n=30,620 gateway / 260,783 direct—
Anthropic → AnthropicAdded latency p99 (µs)192Valid · n=30,620 gateway / 260,783 direct—
Anthropic → AnthropicGateway p99 at concurrency 1 (µs)220Valid · n=30,620—
Anthropic → AnthropicDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=260,783—
Anthropic → AnthropicCPU per request (µs)166.8Valid—
Anthropic → AnthropicRequests per CPU-second5,995.3Valid—
Anthropic → AnthropicCost window concurrency8Valid—
Anthropic → AnthropicCost window core utilisation0.983Valid—
Anthropic → AnthropicCost window successful requests141,788Valid—
Anthropic → AnthropicCost window throughput (req/s)23,628Valid—
Anthropic → AnthropicCost window threads5Valid—
Anthropic → AnthropicNon-voluntary context switches per request0Valid—
Anthropic → AnthropicCost window major page faults0Valid—
Anthropic → AnthropicAdded time to first event p50 (µs)270Valid · n=100 gateway / 100 direct—
Anthropic → AnthropicAdded time to first event p99 (µs)404Valid · 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)51,526.6Valid—
Anthropic → AnthropicStreams sustained1,142Valid—
Anthropic → AnthropicIdle RSS (MiB)42.95Valid—
Anthropic → AnthropicSteady-state RSS (MiB)50.8Valid—
Anthropic → AnthropicRecovered RSS (MiB)50.79Valid—
Anthropic → AnthropicPeak RSS (MiB)51.33Valid—
Anthropic → AnthropicPeak RSS high-water mark (MiB)51.13Valid—
Anthropic → AnthropicTime to plateau (s)—Not measured—
Anthropic → AnthropicMemory growth (MiB/min)-0.215Valid—
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)0.124Valid—
Anthropic → AnthropicThroughput (req/s)24,452concurrency 16; n=146,7291 ms
Anthropic → AnthropicThroughput (req/s)25,909concurrency 64; n=155,4815 ms
Anthropic → AnthropicThroughput (req/s)26,217concurrency 128; n=157,32810 ms
Anthropic → AnthropicThroughput (req/s)26,320concurrency 256; n=157,94150 ms
Anthropic → AnthropicThroughput (req/s)26,320concurrency 256; n=157,941100 ms
Anthropic → AnthropicThroughput (req/s)26,320concurrency 256; n=157,941Unbounded
Gemini → Anthropic——Not declared: recorded note 1—
OpenAI → BedrockAdded latency p50 (µs)293Valid · n=18,960 gateway / 263,027 direct—
OpenAI → BedrockAdded latency p99 (µs)311Valid · n=18,960 gateway / 263,027 direct—
OpenAI → BedrockGateway p99 at concurrency 1 (µs)338Valid · n=18,960—
OpenAI → BedrockDirect-to-mock p99 at concurrency 1 (µs)27Valid · n=263,027—
OpenAI → BedrockCPU per request (µs)295.1Valid—
OpenAI → BedrockRequests per CPU-second3,388.6Valid—
OpenAI → BedrockCost window concurrency8Valid—
OpenAI → BedrockCost window core utilisation0.989Valid—
OpenAI → BedrockCost window successful requests80,614Valid—
OpenAI → BedrockCost window throughput (req/s)13,433Valid—
OpenAI → BedrockCost window threads19Valid—
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)42.97Valid—
OpenAI → BedrockSteady-state RSS (MiB)56.49Valid—
OpenAI → BedrockRecovered RSS (MiB)53.67Valid—
OpenAI → BedrockPeak RSS (MiB)56.91Valid—
OpenAI → BedrockPeak RSS high-water mark (MiB)56.73Valid—
OpenAI → BedrockTime to plateau (s)138Valid—
OpenAI → BedrockMemory growth (MiB/min)0.042Valid—
OpenAI → BedrockMemory load duration (s)300Valid—
OpenAI → BedrockMemory shape under load—Not measured—
OpenAI → BedrockIdle memory shape—Not measured—
OpenAI → BedrockIdle memory static1Valid—
OpenAI → BedrockIdle memory growth (MiB/min)0.124Valid—
OpenAI → BedrockThroughput (req/s)13,411concurrency 8; n=80,4771 ms
OpenAI → BedrockThroughput (req/s)14,128concurrency 32; n=84,7795 ms
OpenAI → BedrockThroughput (req/s)14,164concurrency 64; n=84,98510 ms
OpenAI → BedrockThroughput (req/s)14,164concurrency 64; n=84,98550 ms
OpenAI → BedrockThroughput (req/s)14,164concurrency 64; n=84,985100 ms
OpenAI → BedrockThroughput (req/s)14,164concurrency 64; n=84,985Unbounded
Gemini → Bedrock——Not declared: recorded note 1—
OpenAI Responses → Bedrock——Not declared: recorded note 1—
Cohere → Bedrock——Not declared: recorded note 1—
Anthropic → Bedrock——Not declared: recorded note 1—
Bedrock → BedrockAdded latency p50 (µs)203Valid · n=26,758 gateway / 262,304 direct—
Bedrock → BedrockAdded latency p99 (µs)220Valid · n=26,758 gateway / 262,304 direct—
Bedrock → BedrockGateway p99 at concurrency 1 (µs)247Valid · n=26,758—
Bedrock → BedrockDirect-to-mock p99 at concurrency 1 (µs)27Valid · n=262,304—
Bedrock → BedrockCPU per request (µs)191.5Valid—
Bedrock → BedrockRequests per CPU-second5,222.2Valid—
Bedrock → BedrockCost window concurrency8Valid—
Bedrock → BedrockCost window core utilisation0.987Valid—
Bedrock → BedrockCost window successful requests124,080Valid—
Bedrock → BedrockCost window throughput (req/s)20,677Valid—
Bedrock → BedrockCost window threads5Valid—
Bedrock → BedrockNon-voluntary context switches per request0.00000806Valid—
Bedrock → BedrockCost window major page faults0Valid—
Bedrock → BedrockAdded time to first event p50 (µs)—Untestable—
Bedrock → BedrockAdded time to first event p99 (µs)—Untestable—
Bedrock → BedrockAdded inter-frame gap p50 (µs)—Untestable—
Bedrock → BedrockAdded inter-frame gap p99 (µs)—Untestable—
Bedrock → BedrockStreams sustained (frames/s)—Untestable—
Bedrock → BedrockStreams sustained—Untestable—
Bedrock → BedrockIdle RSS (MiB)42.96Valid—
Bedrock → BedrockSteady-state RSS (MiB)50.83Valid—
Bedrock → BedrockRecovered RSS (MiB)51.14Valid—
Bedrock → BedrockPeak RSS (MiB)51.44Valid—
Bedrock → BedrockPeak RSS high-water mark (MiB)51.44Valid—
Bedrock → BedrockTime to plateau (s)—Not measured—
Bedrock → BedrockMemory growth (MiB/min)-0.008Valid—
Bedrock → BedrockMemory load duration (s)300Valid—
Bedrock → BedrockMemory shape under load0Valid—
Bedrock → BedrockIdle memory shape—Not measured—
Bedrock → BedrockIdle memory static1Valid—
Bedrock → BedrockIdle memory growth (MiB/min)0.124Valid—
Bedrock → BedrockThroughput (req/s)20,749concurrency 8; n=124,5131 ms
Bedrock → BedrockThroughput (req/s)22,637concurrency 64; n=135,8255 ms
Bedrock → BedrockThroughput (req/s)22,807concurrency 128; n=136,86710 ms
Bedrock → BedrockThroughput (req/s)22,894concurrency 256; n=137,38950 ms
Bedrock → BedrockThroughput (req/s)22,894concurrency 256; n=137,389100 ms
Bedrock → BedrockThroughput (req/s)22,894concurrency 256; n=137,389Unbounded
OpenAI → Gemini——Not declared: recorded note 1—
Anthropic → Gemini——Not declared: recorded note 1—
Gemini → Gemini——Not declared: recorded note 1—
Cohere → Gemini——Not declared: recorded note 1—
Bedrock → Gemini——Not declared: recorded note 1—
OpenAI Responses → Gemini——Not declared: recorded note 1—
Cohere → OpenAI Responses——Not declared: recorded note 1—
Bedrock → OpenAI Responses——Not declared: recorded note 1—
Anthropic → OpenAI Responses——Not declared: recorded note 1—
OpenAI → OpenAI Responses——Not declared: recorded note 1—
OpenAI Responses → OpenAI Responses——Not declared: recorded note 1—
Gemini → 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
Bedrock → CohereNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Anthropic → CohereNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Gemini → CohereNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Cohere → CohereNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI → CohereNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI Responses → CohereNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Anthropic → OpenAINot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI Responses → OpenAINot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI → OpenAIServed———Recorded run evidence—built from source; recorded binary target/release/ai-gateway
Cohere → OpenAINot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Bedrock → OpenAINot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Gemini → OpenAINot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI Responses → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Cohere → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI → AnthropicServed———Recorded run evidence—built from source; recorded binary target/release/ai-gateway
Bedrock → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Anthropic → AnthropicServed———Recorded run evidence—built from source; recorded binary target/release/ai-gateway
Gemini → AnthropicNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI → BedrockServed———Recorded run evidence—built from source; recorded binary target/release/ai-gateway
Gemini → BedrockNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI Responses → BedrockNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Cohere → BedrockNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Anthropic → BedrockNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Bedrock → BedrockServed———Recorded run evidence—built from source; recorded binary target/release/ai-gateway
OpenAI → GeminiNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Anthropic → GeminiNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Gemini → GeminiNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Cohere → GeminiNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Bedrock → GeminiNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI Responses → GeminiNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Cohere → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Bedrock → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Anthropic → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
OpenAI Responses → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
Gemini → OpenAI ResponsesNot declared—recorded note 1recorded note 1recorded note 2—built from source; recorded binary target/release/ai-gateway
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
Gateway build receipt
Binary name
ai-gateway
Binary sha256
f401a719a6341a95be9d1f0b7a63ce385241583ee632f5724df3bf54b04a22f1
Cargo lock sha256
d70600602afa1fa8a054251da84622cd764c920e110bf0e3266f0a562473de88
Compiler
rustc 1.99.1 (58cf8f9c3 2026-10-13) binary: rustc commit-hash: 58cf8f9c35b355199727627d07ae34a4e2846d67 commit-date: 2026-10-13 host: aarch64-unknown-linux-gnu release: 1.99.1 LLVM version: 23.1.1
Source commit
081f310be779f27122e6038e81e2359c44db4ecb
Source dirty
No

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 → 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: 460, HTTP 404: 520
OpenAI → OpenAI384HTTP 200: 3840
OpenAI → OpenAI448HTTP 200: 4480
OpenAI → OpenAI480HTTP 200: 391, HTTP 404: 890
OpenAI → OpenAI464HTTP 200: 463, HTTP 404: 10
OpenAI → OpenAI456HTTP 200: 4560
OpenAI → OpenAI460HTTP 200: 4600
OpenAI → OpenAI462HTTP 200: 4620
OpenAI → OpenAI463HTTP 200: 4630
OpenAI → OpenAI463HTTP 200: 4630
OpenAI → OpenAI463HTTP 200: 4630
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: 511, HTTP 404: 10
OpenAI → Anthropic384HTTP 200: 3840
OpenAI → Anthropic448HTTP 200: 4480
OpenAI → Anthropic480HTTP 200: 463, HTTP 404: 170
OpenAI → Anthropic464HTTP 200: 4640
OpenAI → Anthropic472HTTP 200: 4720
OpenAI → Anthropic476HTTP 200: 4760
OpenAI → Anthropic478HTTP 200: 378, HTTP 404: 1000
OpenAI → Anthropic477HTTP 200: 4770
OpenAI → Anthropic477HTTP 200: 4770
OpenAI → Anthropic477HTTP 200: 4770
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 → Anthropic1,280HTTP 200: 1,2800
Anthropic → Anthropic1,152HTTP 200: 1,1520
Anthropic → Anthropic1,088HTTP 200: 1,0880
Anthropic → Anthropic1,120HTTP 200: 1,1200
Anthropic → Anthropic1,136HTTP 200: 1,1360
Anthropic → Anthropic1,144HTTP 200: 1,1440
Anthropic → Anthropic1,140HTTP 200: 1,1400
Anthropic → Anthropic1,142HTTP 200: 1,1420
Anthropic → Anthropic1,143HTTP 200: 1,1430
Anthropic → Anthropic1,142HTTP 200: 1,1420
Anthropic → Anthropic1,142HTTP 200: 1,1420

Recorded notes

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

  1. Pinned v0.2.0-beta.30 source 081f310be779f27122e6038e81e2359c44db4ecb: ai-gateway/src/endpoints defines OpenAI Chat, Anthropic Messages and Bedrock Converse. Google uses v1beta/openai/chat/completions, not native Gemini. router/router_details.rs exposes OpenAI router ingress plus provider-prefixed direct proxy paths. No Responses, native Gemini or Cohere interface is registered; direct proxy does not imply cross-protocol conversion. Five supported exact-wire pairs pass the 36-cell correctness check. Evidence: results/diagnostics/refresh-configuration/helicone-final-config-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

server:
  port: 8787
providers:
  openai:
    base-url: "http://127.0.0.1:8000/"
  anthropic:
    base-url: "http://127.0.0.1:8000/"
  bedrock:
    base-url: "http://127.0.0.1:8000/"
routers:
  openai:
    load-balance:
      chat:
        strategy: latency
        providers:
          - openai
  anthropic:
    load-balance:
      chat:
        strategy: latency
        providers:
          - anthropic
  bedrock:
    load-balance:
      chat:
        strategy: latency
        providers:
          - bedrock

Compare a shared protocol cell

Historical measurements