OpenAI compatible API · Attested · Public status
Google Vertex AI performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Google Vertex AI on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Google Vertex AIgoogle-vertex
31 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 | 1535 ms |
|---|---|
| p95 TTFT | 4099 ms |
| Effective throughput | 70 tok/s n=5 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemini-2.5-flash-lite | 567 ms | — | 100.00% | — | 2 |
| google/gemini-2.5-flash | 832 ms | — | 100.00% | — | 2 |
| google/gemini-3.6-flash | 874 ms | 69 tok/s n=2 | 100.00% | — | 2 |
| google/gemini-3.5-flash | 1208 ms | 83 tok/s n=1 | 100.00% | — | 4 |
| google/gemini-3.5-flash-lite | 1277 ms | — | 100.00% | — | 5 |
| google/gemini-3-flash-preview | 1535 ms | — | 100.00% | — | 7 |
| google/gemini-3.8-flash | 1871 ms | — | 100.00% | — | 3 |
| google/gemini-3.1-flash-lite | 1955 ms | — | 100.00% | — | 1 |
| google/gemini-3.1-pro-preview | 3204 ms | 70 tok/s n=2 | 100.00% | — | 4 |
| google/gemini-2.5-pro | 4840 ms | — | 100.00% | — | 1 |