OpenAI compatible API. Attested gateway. Public status.
Google: Gemma 4 26B A4B Performance
TrustedRouter performance signals and provider route posture for Google: Gemma 4 26B A4B .
1 URLbase_url migration
100smodels and routes
0prompt logs by default
google/gemma-4-26b-a4b-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 26B A4B — 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 | 749 ms | 1646 ms | 747 ms | — | 47.62% | — | 21 |
| deepinfra | 792 ms | 10120 ms | 724 ms | — | 57.14% | — | 49 |
| novita | 1354 ms | 1385 ms | 1250 ms | — | 66.67% | — | 3 |
| gmi | 3889 ms | 24589 ms | 3887 ms | — | 50.85% | — | 59 |
Full provider & model leaderboard.
Provider diversity
9 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.