OpenAI compatible API. Attested gateway. Public status.
Google: Gemma 4 31B Performance
TrustedRouter performance signals and provider route posture for Google: Gemma 4 31B.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
google/gemma-4-31b-it
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Google: Gemma 4 31B — 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 | 644 ms | 1460 ms | 643 ms | — | 30.77% | — | 13 |
| deepinfra | 876 ms | 2623 ms | 846 ms | 12 tok/s | 71.70% | — | 53 |
| lightning | 877 ms | 1313 ms | 807 ms | — | 51.30% | — | 308 |
| novita | 2138 ms | 2138 ms | 2036 ms | — | 100.00% | — | 1 |
| gmi | 3015 ms | 15219 ms | 2913 ms | — | 43.75% | — | 64 |
Full provider & model leaderboard.
Provider diversity
11 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.