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
28 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 | 2358 ms |
|---|---|
| p95 TTFT | 6077 ms |
| Effective throughput | 66 tok/s n=5 |
| Uptime | 96.43% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemini-3.1-flash-lite | 1124 ms | — | 100.00% | — | 3 |
| google/gemini-3.5-flash-lite | 1463 ms | — | 100.00% | — | 1 |
| anthropic/claude-sonnet-4.6 | 1599 ms | — | 100.00% | — | 4 |
| google/gemini-3.5-flash | 1600 ms | 66 tok/s n=1 | 100.00% | — | 3 |
| google/gemini-2.5-flash | 2297 ms | — | 100.00% | — | 1 |
| google/gemini-3.7-flash | 2358 ms | — | 100.00% | — | 3 |
| google/gemini-3.6-flash | 3074 ms | 69 tok/s n=2 | 50.00% | — | 2 |
| google/gemini-2.5-pro | 3206 ms | — | 100.00% | — | 3 |
| google/gemini-3.8-flash | 3258 ms | — | 100.00% | — | 2 |
| google/gemini-3.1-pro-preview | 3539 ms | 61 tok/s n=2 | 100.00% | — | 3 |
| google/gemini-4-argon | 4602 ms | — | 100.00% | — | 3 |