LiteLLM · Python 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.
- Load-generator binary digests were not recorded; instrument equivalence is based on the identical clean harness source commit and mock digest.
- Measurements were made at different times on independently provisioned machines.
Ratio (Helicone ÷ LiteLLM · Python): 0.029. No statistical significance is asserted.
Comparison JSON · All LiteLLM · Python evidence · All Helicone evidence
LiteLLM · Python
Build ghcr.io/berriai/litellm:v1.108.3. Measured . Run evidence
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → OpenAI | Added latency p50 (µs) | 8,512 | Valid · n=701 gateway / 267,297 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 9,522 | Valid · n=701 gateway / 267,297 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 9,549 | Valid · n=701 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 27 | Valid · n=267,297 | — |
| OpenAI → OpenAI | CPU per request (µs) | 8,644.8 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 115.7 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.25 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 701 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 116 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 32 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0.029 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 11,154 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 11,974 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | 9 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 1,208 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 62 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 593 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 628.6 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 628.6 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 628.6 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 628.6 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 61 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 302 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | — | Not measured | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 117 | concurrency 1; n=708 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 119 | concurrency 2; n=718 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 119 | concurrency 2; n=718 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 119 | concurrency 2; n=718 | Unbounded |
Helicone
Build target/release/ai-gateway. Measured . Run evidence
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → OpenAI | Added latency p50 (µs) | 256 | Valid · n=21,418 gateway / 260,967 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 274 | Valid · n=21,418 gateway / 260,967 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 302 | Valid · n=21,418 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=260,967 | — |
| OpenAI → OpenAI | CPU per request (µs) | 259.4 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 3,855.3 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.984 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 91,294 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 15,213 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 24 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 0 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 399 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 493 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | 0 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 21,883.1 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 463 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 42.97 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 56.18 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 53.69 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 56.95 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 56.61 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 126 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.5 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | — | Not measured | — |
| OpenAI → OpenAI | Idle memory shape | — | Not measured | — |
| OpenAI → OpenAI | Idle memory static | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.124 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 15,405 | concurrency 8; n=92,444 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 16,288 | concurrency 32; n=97,741 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 16,376 | concurrency 64; n=98,266 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 16,376 | concurrency 64; n=98,266 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 16,376 | concurrency 64; n=98,266 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 16,376 | concurrency 64; n=98,266 | Unbounded |