Vertex AI implements Google Cloud security controls to help secure your models and training data.
The following table lists the security controls available for Generative AI features:
Gemini 3.1 Flash-Lite
Online prediction
Batch prediction
Context caching
Gemini 2.5 Pro
Online prediction
Batch prediction
Tuning
Context caching
RAG Engine
Grounding with Google Search and Grounding with Google Maps
Gemini 2.5 Flash Image
Online prediction
Batch prediction
Gemini 2.5 Flash
Online prediction
Batch prediction
Tuning
Context caching
RAG Engine
Grounding with Google Search and Grounding with Google Maps
Gemini 2.5 Flash-Lite
Online prediction
Batch prediction
Tuning
Context caching
RAG Engine
Grounding with Google Search and Grounding with Google Maps
Gemini 2.5 Flash with Gemini Live API native audio
Online prediction
Gemini 2.0 Flash
Online prediction
Batch prediction
Tuning
Context caching
RAG Engine
Grounding with Google Search and Grounding with Google Maps
Gemini 2.0 Flash-Lite
Online prediction
Batch prediction
Tuning
RAG Engine
Context caching
Grounding with Google Search and Grounding with Google Maps
gemini-embedding-2-preview
Online prediction
Embeddings for Multimodal
Online prediction
Batch prediction
Tuning
Embeddings for Text
Online prediction
Batch prediction
Tuning
RAG Engine
Imagen for Image Generation
Online prediction
Tuning
Veo for Video Generation
Online prediction
Online prediction
Prompt logging for Partner and Open Models (MaaS) is turned off by default and adheres to the Vertex AI Zero Data Retention policy.
