OpenAI compatible API · Attested · Public status
Google: Gemma 3 27B Performance
TrustedRouter performance signals and provider route posture for Google: Gemma 3 27B.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
google/gemma-3-27b-it
open weights
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Google: Gemma 3 27B — unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| parasail | 2398 ms | 17466 ms | 2397 ms | — | 100.00% | — | 15 |
| nebius | 5017 ms | 10566 ms | 5016 ms | — | 100.00% | — | 7 |
| deepinfra | 5934 ms | 7434 ms | 5933 ms | — | 100.00% | — | 5 |
| novita | 9494 ms | 25222 ms | 9494 ms | — | 66.67% | — | 3 |
Full provider & model leaderboard.
Provider diversity
8 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Streaming
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Status
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.