Sovereign Inference DirectoryAbout made. ↗
← Back to directory

Google Cloud / Service profile

Managed generative AI APIs

AU processing unverified

Evaluate the model’s processing commitment separately from its endpoint location.

The important distinction:A regional endpoint alone does not guarantee in-region ML processing.

Source review: 09 Nov 2026 · Exact model configuration not yet verified

Model coverage

Model/endpoint selection pending

API access

Google Cloud project and model quota

Billing

Model-specific; pricing review pending

Capacity commitment

Not yet verified.

Storage

Storage location and inference processing are separate controls.

Retention and training

Feature-specific logging, caching and retention not yet reviewed.

Ownership and control

Google Cloud; Australian endpoint availability does not establish local ownership.

What to check before using it

  1. Select the exact model, version and endpoint.
  2. Read the processing commitment applicable to that model.
  3. Check features such as grounding and caching separately.

Still to verify

Sources and supported claims

Documentation

Deployments and endpoints ↗

Endpoint location alone does not guarantee data residency or in-region ML processing.

Checked 2026-11-09 · Scope: this service profile
Documentation

Data residency ↗

Storage and model computation have distinct location controls.

Checked 2026-11-09 · Scope: this service profile

Add to comparison →Suggest a correction