LiteLLM · Python vs Busbar
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 (Busbar ÷ LiteLLM · Python): 0.009. No statistical significance is asserted.
Comparison JSON · All LiteLLM · Python evidence · All Busbar 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 |
Busbar
Build getbusbar/busbar:1.5.5. Measured . Run evidence
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → OpenAI | Added latency p50 (µs) | 78 | Valid · n=59,266 gateway / 266,330 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 89 | Valid · n=59,266 gateway / 266,330 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 117 | Valid · n=59,266 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 28 | Valid · n=266,330 | — |
| OpenAI → OpenAI | CPU per request (µs) | 68.74 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 14,547.2 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.957 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 335,167 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 55,854 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 10 | 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) | 118 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 254 | 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) | — | Below resolution · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 39,240.2 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 1,452 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 7.43 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 21.49 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 15.7 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 22.35 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 22.27 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | — | Not measured | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.391 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 300 | Valid | — |
| OpenAI → OpenAI | Memory shape under load | 1 | Valid | — |
| OpenAI → OpenAI | Idle memory shape | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory static | 0 | Valid | — |
| OpenAI → OpenAI | Idle memory growth (MiB/min) | 0.004 | Valid | — |
| OpenAI → OpenAI | Throughput (req/s) | 62,231 | concurrency 32; n=373,417 | 1 ms |
| OpenAI → OpenAI | Throughput (req/s) | 62,587 | concurrency 128; n=375,578 | 5 ms |
| OpenAI → OpenAI | Throughput (req/s) | 62,587 | concurrency 128; n=375,578 | 10 ms |
| OpenAI → OpenAI | Throughput (req/s) | 62,587 | concurrency 128; n=375,578 | 50 ms |
| OpenAI → OpenAI | Throughput (req/s) | 62,587 | concurrency 128; n=375,578 | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 62,587 | concurrency 128; n=375,578 | Unbounded |