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
499 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 | 2955 ms |
|---|---|
| p95 TTFT | 5637 ms |
| Effective throughput | 113 tok/s n=1 |
| Uptime | 99.80% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemini-2.5-flash | 643 ms | — | 100.00% | — | 4 |
| google/gemini-3.8-flash | 1840 ms | — | 100.00% | — | 7 |
| google/gemini-3.5-flash | 1843 ms | — | 100.00% | — | 1 |
| google/gemini-3.5-flash-lite | 2330 ms | — | 100.00% | — | 3 |
| google/gemini-3.7-flash | 2955 ms | — | 100.00% | — | 1 |
| google/gemini-3.1-pro-preview | 3321 ms | — | 100.00% | — | 8 |
| google/gemini-2.5-pro | 5637 ms | — | 87.50% | — | 8 |
| google/gemini-2.5-flash-lite | — | — | 100.00% | — | 467 |
| google/gemini-3.6-flash | — | 113 tok/s n=1 | — | — | 0 |