OpenAI compatible API · Attested · Public status
Google: Gemini 2.5 Flash Performance
TrustedRouter performance signals and provider route posture for Google: Gemini 2.5 Flash.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
google/gemini-2.5-flash
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Google: Gemini 2.5 Flash — 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 |
|---|---|---|---|---|---|---|---|
| google-vertex | 2220 ms | 9920 ms | 2220 ms | 165 tok/s | 100.00% | — | 21 |
| google-ai-studio | 3654 ms | 12681 ms | 3654 ms | 7 tok/s | 100.00% | — | 16 |
| deepinfra | 3863 ms | 11121 ms | 3863 ms | — | 100.00% | — | 9 |
| atlas-cloud | 4613 ms | 11752 ms | 4612 ms | — | 100.00% | — | 7 |
| lightning | 5413 ms | 18817 ms | 5413 ms | — | 100.00% | — | 17 |
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.