LiteLLM · Rust vs Helicone

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.

Requested cell: OpenAI → OpenAI. Metric: Added latency p99 (µs).

Comparability: Comparable. Ratios require an identical protocol pair, hardware, architecture, metric definition, clean harness commit, recorded mock digest, and metric-specific workload. Missing evidence never matches missing evidence. These are observed gateway measurements against a local mock, not a claim about model latency or statistical significance.

Ratio (Helicone ÷ LiteLLM · Rust): 0.982. No statistical significance is asserted.

Comparison JSON · All LiteLLM · Rust evidence · All Helicone evidence

LiteLLM · Rust

Build src/litellm-rust/target/release/litellm-gateway. Measured . Run evidence

Ingress → upstreamMetricValueState / reasonp99 bound (ms)
OpenAI → OpenAIAdded latency p50 (µs)249Valid · n=22,021 gateway / 267,021 direct—
OpenAI → OpenAIAdded latency p99 (µs)279Valid · n=22,021 gateway / 267,021 direct—
OpenAI → OpenAIGateway p99 at concurrency 1 (µs)306Valid · n=22,021—
OpenAI → OpenAIDirect-to-mock p99 at concurrency 1 (µs)27Valid · n=267,021—
OpenAI → OpenAICPU per request (µs)272.6Valid—
OpenAI → OpenAIRequests per CPU-second3,668.4Valid—
OpenAI → OpenAICost window concurrency8Valid—
OpenAI → OpenAICost window core utilisation0.679Valid—
OpenAI → OpenAICost window successful requests59,941Valid—
OpenAI → OpenAICost window throughput (req/s)9,989Valid—
OpenAI → OpenAICost window threads5Valid—
OpenAI → OpenAINon-voluntary context switches per request0Valid—
OpenAI → OpenAICost window major page faults0Valid—
OpenAI → OpenAIAdded time to first event p50 (µs)—Not measured—
OpenAI → OpenAIAdded time to first event p99 (µs)—Not measured—
OpenAI → OpenAIAdded inter-frame gap p50 (µs)—Not measured—
OpenAI → OpenAIAdded inter-frame gap p99 (µs)—Not measured—
OpenAI → OpenAIStreams sustained (frames/s)0Valid — measured failure: the gateway was offered stream load and sustained none of it—
OpenAI → OpenAIStreams sustained0Valid — measured failure: the gateway was offered stream load and sustained none of it—
OpenAI → OpenAIIdle RSS (MiB)12.74Valid—
OpenAI → OpenAISteady-state RSS (MiB)18.99Valid—
OpenAI → OpenAIRecovered RSS (MiB)19Valid—
OpenAI → OpenAIPeak RSS (MiB)19.88Valid—
OpenAI → OpenAIPeak RSS high-water mark (MiB)19.48Valid—
OpenAI → OpenAITime to plateau (s)—Not measured—
OpenAI → OpenAIMemory growth (MiB/min)-0.179Valid—
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)0Valid—
OpenAI → OpenAIThroughput (req/s)8,404concurrency 4; n=50,4351 ms
OpenAI → OpenAIThroughput (req/s)10,049concurrency 16; n=60,3065 ms
OpenAI → OpenAIThroughput (req/s)10,049concurrency 16; n=60,30610 ms
OpenAI → OpenAIThroughput (req/s)10,049concurrency 16; n=60,30650 ms
OpenAI → OpenAIThroughput (req/s)10,049concurrency 16; n=60,306100 ms
OpenAI → OpenAIThroughput (req/s)10,049concurrency 16; n=60,306Unbounded

Helicone

Build target/release/ai-gateway. Measured . Run evidence

Ingress → upstreamMetricValueState / reasonp99 bound (ms)
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