OpenAI compatible API · Attested · Public status
Google Vertex AI performance
Review measured TTFT, TTFB, 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
55 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 | 1384 ms |
|---|---|
| p95 TTFT | 5027 ms |
| p50 TTFB | 2471 ms |
| Effective throughput | 58 tok/s n=5 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemini-3.6-flash | 1150 ms | 1150 ms | 47 tok/s n=1 | 100.00% | — | 10 |
| google/gemini-2.5-flash-lite | 1304 ms | 1304 ms | — | 100.00% | — | 5 |
| google/gemini-3.5-flash-lite | 1327 ms | 1327 ms | 93 tok/s n=1 | 100.00% | — | 8 |
| google/gemini-2.5-flash | 1384 ms | 1384 ms | — | 100.00% | — | 5 |
| google/gemini-3-flash-preview | 1591 ms | 1591 ms | — | 100.00% | — | 5 |
| google/gemini-3.1-flash-lite | 2049 ms | 2049 ms | — | 100.00% | — | 5 |
| google/gemini-3.5-flash | 3014 ms | 3013 ms | 58 tok/s n=2 | 100.00% | — | 3 |
| google/gemini-3.1-pro-preview | 3321 ms | 3321 ms | 82 tok/s n=1 | 100.00% | — | 7 |
| google/gemini-2.5-pro | 4474 ms | 4474 ms | — | 100.00% | — | 7 |