Does Vertex AI store your API prompts?

“If automated safety classifiers detect suspicious activity that requires further investigation into whether a customer has violated our policies, then Google may log customer prompts solely for the purpose of examining whether a violation of the AUP or Prohibited Use Policy has occurred. This data won't be used to train or fine-tune any AI/ML models. This data is stored securely for up to 90 days in the same region or multi-region selected by the customer for their project and adheres to Google Cloud assurances, such as Data Residency, Access Transparency and VPC Service Controls.”

“This means that customers with a Google Cloud Master Agreement are exempt from prompt logging for this abuse monitoring by default.”

“These logs are stored securely inside the customer's environment for up to 30 days.”

“All prompts and responses will be logged and securely stored for up to 30 days for the sole purpose of monitoring for abuse.”

“If you are in scope for prompt logging for abuse monitoring and want zero data retention, you can request an exception for abuse monitoring.”

“Zero data retention may not be possible when using some Advanced AI features. Please contact your account team for clarification.”

“If your organization's policy does not permit Customer Data to be stored at rest, you can disable durable caching on a per-project basis and maintain in-memory caching. Alternatively, you can disable caching entirely.”

“Data stored at rest in the customer selected location remains at rest in that location, independent of the Agent Platform endpoint called by that customer's request.”

“Requests submitted to a global endpoint may be processed in any Google Cloud location around the world, and therefore don't provide any data residency guarantees.”

“Jurisdictional multi-region endpoints: When you use jurisdictional endpoints, ML processing stays within that specific geographical region (such as the United States or the European Union).”

“Locational endpoints: These endpoints (like us-central1, europe-west1) ensure that ML processing remains entirely within the broader multi-regional or country jurisdiction associated with that region (for example, requests to us-central1 are processed within the United States).”

“For European regions, local in-country processing varies by model type (for example, specific models may have local processing in France or Germany, while others are processed within the broader EU multi-region boundary).”