Plano vs LiteLLM · Python
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 (LiteLLM · Python ÷ Plano): 0.046. No statistical significance is asserted.
Comparison JSON · All Plano evidence · All LiteLLM · Python evidence
Plano
Build katanemo/plano:0.4.39. Measured . Run evidence
| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
|---|---|---|---|---|
| OpenAI → OpenAI | Added latency p50 (µs) | 198,988 | Valid · n=30 gateway / 266,566 direct | — |
| OpenAI → OpenAI | Added latency p99 (µs) | 205,966 | Valid · n=30 gateway / 266,566 direct | — |
| OpenAI → OpenAI | Gateway p99 at concurrency 1 (µs) | 205,993 | Valid · n=30 | — |
| OpenAI → OpenAI | Direct-to-mock p99 at concurrency 1 (µs) | 27 | Valid · n=266,566 | — |
| OpenAI → OpenAI | CPU per request (µs) | 182,230.8 | Valid | — |
| OpenAI → OpenAI | Requests per CPU-second | 5.49 | Valid | — |
| OpenAI → OpenAI | Cost window concurrency | 8 | Valid | — |
| OpenAI → OpenAI | Cost window core utilisation | 0.965 | Valid | — |
| OpenAI → OpenAI | Cost window successful requests | 130 | Valid | — |
| OpenAI → OpenAI | Cost window throughput (req/s) | 21 | Valid | — |
| OpenAI → OpenAI | Cost window threads | 68 | Valid | — |
| OpenAI → OpenAI | Non-voluntary context switches per request | 6.28 | Valid | — |
| OpenAI → OpenAI | Cost window major page faults | 0 | Valid | — |
| OpenAI → OpenAI | Added time to first event p50 (µs) | 158,773 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added time to first event p99 (µs) | 170,494 | Valid · n=100 gateway / 100 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p50 (µs) | 1 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Added inter-frame gap p99 (µs) | 38 | Valid · n=63 gateway / 63 direct | — |
| OpenAI → OpenAI | Streams sustained (frames/s) | 669.7 | Valid | — |
| OpenAI → OpenAI | Streams sustained | 29 | Valid | — |
| OpenAI → OpenAI | Idle RSS (MiB) | 617.2 | Valid | — |
| OpenAI → OpenAI | Steady-state RSS (MiB) | 971.8 | Valid | — |
| OpenAI → OpenAI | Recovered RSS (MiB) | 972.3 | Valid | — |
| OpenAI → OpenAI | Peak RSS (MiB) | 972.4 | Valid | — |
| OpenAI → OpenAI | Peak RSS high-water mark (MiB) | 972.3 | Valid | — |
| OpenAI → OpenAI | Time to plateau (s) | 61 | Valid | — |
| OpenAI → OpenAI | Memory growth (MiB/min) | 0.129 | Valid | — |
| OpenAI → OpenAI | Memory load duration (s) | 305 | 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) | 0.052 | 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) | — | Bound not met; concurrency not recorded: every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 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 50ms, so this gateway carried no measurable throughput under that bound | 50 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 100ms, so this gateway carried no measurable throughput under that bound | 100 ms |
| OpenAI → OpenAI | Throughput (req/s) | 19 | concurrency 8; n=118 | Unbounded |
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 |