APISIX vs One-API

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 (One-API ÷ APISIX): 1,734.1. No statistical significance is asserted.

Comparison JSON · All APISIX evidence · All One-API evidence

APISIX

Build apache/apisix:3.19.0-debian. Measured . Run evidence

Ingress → upstreamMetricValueState / reasonp99 bound (ms)
OpenAI → OpenAIAdded latency p50 (µs)179Valid · n=28,247 gateway / 260,315 direct—
OpenAI → OpenAIAdded latency p99 (µs)340Valid · n=28,247 gateway / 260,315 direct—
OpenAI → OpenAIGateway p99 at concurrency 1 (µs)368Valid · n=28,247—
OpenAI → OpenAIDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=260,315—
OpenAI → OpenAICPU per request (µs)185.7Valid—
OpenAI → OpenAIRequests per CPU-second5,386.2Valid—
OpenAI → OpenAICost window concurrency8Valid—
OpenAI → OpenAICost window core utilisation0.711Valid—
OpenAI → OpenAICost window successful requests92,266Valid—
OpenAI → OpenAICost window throughput (req/s)15,375Valid—
OpenAI → OpenAICost window threads12Valid—
OpenAI → OpenAINon-voluntary context switches per request0.000455Valid—
OpenAI → OpenAICost window major page faults0Valid—
OpenAI → OpenAIAdded time to first event p50 (µs)10,584Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded time to first event p99 (µs)11,228Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded inter-frame gap p50 (µs)—Below resolution · n=63 gateway / 63 direct—
OpenAI → OpenAIAdded inter-frame gap p99 (µs)8,877Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIStreams sustained (frames/s)63,882.4Valid—
OpenAI → OpenAIStreams sustained1,470Valid—
OpenAI → OpenAIIdle RSS (MiB)191.2Valid—
OpenAI → OpenAISteady-state RSS (MiB)228.2Valid—
OpenAI → OpenAIRecovered RSS (MiB)228.4Valid—
OpenAI → OpenAIPeak RSS (MiB)228.4Valid—
OpenAI → OpenAIPeak RSS high-water mark (MiB)233.2Valid—
OpenAI → OpenAITime to plateau (s)66Valid—
OpenAI → OpenAIMemory growth (MiB/min)0.05Valid—
OpenAI → OpenAIMemory load duration (s)300Valid—
OpenAI → OpenAIMemory shape under load—Not measured—
OpenAI → OpenAIIdle memory shape0Valid—
OpenAI → OpenAIIdle memory static0Valid—
OpenAI → OpenAIIdle memory growth (MiB/min)-0.464Valid—
OpenAI → OpenAIThroughput (req/s)12,187concurrency 4; n=73,1361 ms
OpenAI → OpenAIThroughput (req/s)23,089concurrency 32; n=138,5505 ms
OpenAI → OpenAIThroughput (req/s)25,474concurrency 64; n=152,85110 ms
OpenAI → OpenAIThroughput (req/s)26,590concurrency 256; n=159,56050 ms
OpenAI → OpenAIThroughput (req/s)26,590concurrency 256; n=159,560100 ms
OpenAI → OpenAIThroughput (req/s)26,590concurrency 256; n=159,560Unbounded

One-API

Build justsong/one-api:v0.6.10. Measured . Run evidence

Ingress → upstreamMetricValueState / reasonp99 bound (ms)
OpenAI → OpenAIAdded latency p50 (µs)34,017Valid · n=102 gateway / 263,027 direct—
OpenAI → OpenAIAdded latency p99 (µs)589,609Valid · n=102 gateway / 263,027 direct—
OpenAI → OpenAIGateway p99 at concurrency 1 (µs)589,637Valid · n=102—
OpenAI → OpenAIDirect-to-mock p99 at concurrency 1 (µs)28Valid · n=263,027—
OpenAI → OpenAICPU per request (µs)—Not measured—
OpenAI → OpenAIRequests per CPU-second—Not measured—
OpenAI → OpenAICost window concurrency—Not measured—
OpenAI → OpenAICost window core utilisation—Not measured—
OpenAI → OpenAICost window successful requests—Not measured—
OpenAI → OpenAICost window throughput (req/s)—Not measured—
OpenAI → OpenAICost window threads—Not measured—
OpenAI → OpenAINon-voluntary context switches per request—Not measured—
OpenAI → OpenAICost window major page faults—Not measured—
OpenAI → OpenAIAdded time to first event p50 (µs)728Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded time to first event p99 (µs)770Valid · n=100 gateway / 100 direct—
OpenAI → OpenAIAdded inter-frame gap p50 (µs)12Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIAdded inter-frame gap p99 (µs)27Valid · n=63 gateway / 63 direct—
OpenAI → OpenAIStreams sustained (frames/s)7,497.8Valid—
OpenAI → OpenAIStreams sustained213Valid—
OpenAI → OpenAIIdle RSS (MiB)87.16Valid—
OpenAI → OpenAISteady-state RSS (MiB)141.9Valid—
OpenAI → OpenAIRecovered RSS (MiB)136.6Valid—
OpenAI → OpenAIPeak RSS (MiB)142.5Valid—
OpenAI → OpenAIPeak RSS high-water mark (MiB)142.5Valid—
OpenAI → OpenAITime to plateau (s)134Valid—
OpenAI → OpenAIMemory growth (MiB/min)0.116Valid—
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)-0.115Valid—
OpenAI → OpenAIThroughput (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 bound1 ms
OpenAI → OpenAIThroughput (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 bound5 ms
OpenAI → OpenAIThroughput (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 bound10 ms
OpenAI → OpenAIThroughput (req/s)32concurrency 1; n=19650 ms
OpenAI → OpenAIThroughput (req/s)32concurrency 1; n=196100 ms
OpenAI → OpenAIThroughput (req/s)38concurrency 16; n=229Unbounded