Google: Gemini 3.5 Flash Performance
Compare measured TTFT, TTFB, throughput, uptime, and route health for Google: Gemini 3.5 Flash across TrustedRouter providers using metadata-only production probes.
google/gemini-3.5-flash
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for Google: Gemini 3.5 Flash. Effective throughput uses provider-reported output tokens over complete request time. 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| google-ai-studio | 1997 ms | 3148 ms | 1997 ms | — | 100.00% | — | 5 |
| lightning | 2249 ms | 2421 ms | 2248 ms | 50 tok/s n=2 | 100.00% | — | 5 |
| google-vertex | 3014 ms | 3297 ms | 3013 ms | 58 tok/s n=2 | 100.00% | — | 3 |
| atlas-cloud | 14038 ms | 15679 ms | 14038 ms | 29 tok/s n=2 | 100.00% | — | 2 |
Full provider & model leaderboard.
7 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.