Google Vertex AI
Explore Google Vertex AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Google Vertex AIgoogle-vertex
ZDR
These privacy labels describe Google Vertex AI, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Google Vertex AI |
|---|---|
| Routing status | Active |
| Provider website | https://cloud.google.com/vertex-ai |
| Models | 11 public models |
| Credits routes | 11 |
| Zero data retention | yes TR-funded routes |
| Verified confidential inference | Not verified |
| Policy note | TrustedRouter's managed Vertex AI account is covered by contractual Zero Data Retention. This guarantee applies only to TrustedRouter-funded routes. TrustedRouter does not invoke Google Search or Maps grounding or Gemini Live session resumption on these routes. Google AI Studio is classified separately. Policy source |
Measured performance
40 samplesContinuously sampled across Google Vertex AI's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1566 ms |
|---|---|
| Effective throughput | 67 tok/s n=4 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemini-2.5-flash-lite | 815 ms | — | 100.00% | — | 1 |
| google/gemini-3.6-flash | 890 ms | 96 tok/s n=1 | 100.00% | — | 4 |
| google/gemini-3.5-flash | 1372 ms | 58 tok/s n=2 | 100.00% | — | 5 |
| google/gemini-3.1-flash-lite | 1472 ms | — | 100.00% | — | 3 |
| google/gemini-3-flash-preview | 1561 ms | — | 100.00% | — | 3 |
| google/gemini-3.5-flash-lite | 1566 ms | — | 100.00% | — | 4 |
| google/gemini-2.5-flash | 3215 ms | — | 100.00% | — | 3 |
| google/gemini-3.7-flash | 3216 ms | — | 100.00% | — | 3 |
| google/gemini-2.5-pro | 3357 ms | — | 100.00% | — | 5 |
| google/gemini-3.1-pro-preview | 3665 ms | 76 tok/s n=1 | 100.00% | — | 6 |
| google/gemini-3.8-flash | 3754 ms | — | 100.00% | — | 3 |
Google Vertex AI performance history · Full provider & model leaderboard.
Models served by Google Vertex AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
google/gemini-2.5-flashGoogle: Gemini 2.5 Flash |
— | 1,048,576 | $0.3165/1M | $0.03165/1M | $2.6375/1M |
google/gemini-2.5-flash-liteGoogle: Gemini 2.5 Flash Lite |
— | 1,048,576 | $0.1055/1M | $0.01055/1M | $0.422/1M |
google/gemini-2.5-proGoogle: Gemini 2.5 Pro |
IQ 100#88 | 1,048,576 | $1.31875/1M | $0.131875/1M to $0.26375/1M | $10.55/1M |
google/gemini-3-flash-previewGoogle: Gemini 3 Flash Preview |
IQ 116#39 | 1,048,576 | $0.5275/1M | $0.05275/1M | $3.165/1M |
google/gemini-3.1-flash-liteGoogle: Gemini 3.1 Flash Lite |
IQ 103#78 | 1,048,576 | $0.26375/1M | $0.026375/1M | $1.5825/1M |
google/gemini-3.1-pro-previewGoogle: Gemini 3.1 Pro Preview |
IQ 129#8 | 1,048,576 | $2.11/1M | $0.211/1M to $0.422/1M | $12.66/1M |
google/gemini-3.5-flashGoogle: Gemini 3.5 Flash |
IQ 124#14 | 1,048,576 | $1.5825/1M | $0.15825/1M | $9.495/1M |
google/gemini-3.5-flash-liteGoogle: Gemini 3.5 Flash Lite |
IQ 103#79 | 1,048,576 | $0.3165/1M | $0.03165/1M | $2.6375/1M |
google/gemini-3.6-flashGoogle: Gemini 3.6 Flash |
IQ 122#21 | 1,048,576 | $0.79125/1M | $0.079125/1M | $3.95625/1M |
google/gemini-3.7-flashGoogle: Gemini 3.7 Flash |
IQ 124#15 | 1,048,576 | $0.79125/1M | $0.079125/1M | $3.95625/1M |
google/gemini-3.8-flashGoogle: Gemini 3.8 Flash |
IQ 124#16 | 1,048,576 | $0.79125/1M | $0.079125/1M | $3.95625/1M |
Questions
Does Google Vertex AI have zero data retention?
TrustedRouter records its managed Google Vertex AI routes as zero data retention. That classification does not automatically cover every direct or BYOK account. Use provider.min_privacy=zdr to require an eligible route.
Is Google Vertex AI end-to-end encrypted?
TrustedRouter does not currently mark Google Vertex AI as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Google Vertex AI models are available through TrustedRouter?
This page currently lists 11 public Google Vertex AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.