OpenAI compatible API · Attested · Public status
Google AI Studio performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Google AI Studio on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Google AI Studiogoogle-ai-studio
38 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1294 ms |
|---|---|
| p95 TTFT | 6332 ms |
| Effective throughput | 65 tok/s n=2 |
| Uptime | 78.95% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemini-3.1-flash-lite | 864 ms | — | 100.00% | — | 4 |
| google/gemini-3.6-flash | 1174 ms | — | 100.00% | — | 6 |
| google/gemini-2.5-flash | 1200 ms | — | 12.50% | 11 provider_error |
8 |
| google/gemini-3.1-flash-image-preview | 1294 ms | — | 100.00% | 14 client_error |
3 |
| google/gemini-3-flash-preview | 1403 ms | — | 100.00% | — | 2 |
| google/gemini-3.5-flash-lite | 1417 ms | — | 100.00% | — | 3 |
| google/gemini-3.1-pro-preview | 2990 ms | 65 tok/s n=2 | 100.00% | — | 2 |
| google/gemini-4-argon | 3340 ms | — | 100.00% | — | 4 |
| google/gemini-3.8-flash | 3673 ms | — | 100.00% | 1 provider_error |
5 |
| google/gemini-embedding-001 | — | — | 0.00% | — | 1 |