Vertex AI networking overview

Vertex AI supports enterprise networking options for accessing Vertex AI endpoints and services that help you:

  • Safely access your Vertex AI resources from an on-premises or multicloud environment.
  • Protect your Vertex AI artifacts from exfiltration.
  • Configure network traffic for your Vertex AI resources.

This page is intended for enterprise networking architects and administrators who are already familiar with Google Cloud networking concepts.

Public access for Vertex AI

Vertex AI services that are accessible from the internet have a checkmark in the Public internet column of the Private access options for Vertex AI table. The APIs for these services resolve to the fully qualified domain name REGION-aiplatform.googleapis.com, which returns publicly routable IP addresses.

Private access options for Vertex AI

Vertex AI supports the following options for accessing Vertex AI endpoints and services privately, without assigning external IP addresses to your Google Cloud resources:

  • Private Service Connect endpoints for Google APIs let your Google Cloud resources or on-premises systems connect to an endpoint in your VPC network, which forwards requests to Google APIs and services.
  • Private Google Access:
  • Private services access:
    • Lets your Google Cloud VM instances connect to Google-managed Infrastructure-as-a-Service (IaaS) in the service producer's VPC network through an endpoint.
    • Lets your on-premises hosts connect to the service producer through hybrid networking, for example, by using a Cloud VPN tunnel or VLAN attachment once the private service access subnet is advertised from the Cloud Router.
    • Lets your Google Cloud VM instances connect to a Google or third-party managed VPC network through a VPC Network Peering connection.
  • Private Service Connect lets your Google Cloud consumer projects and VPC networks connect to services in other VPC networks through a forwarding rule that deploys an endpoint.

Accessing Vertex AI from on-premises and multicloud

The following table shows the supported access methods for connecting from on-premises and multicloud environments to Vertex AI services. In this table, a checkmark indicates that an access method is supported. For more information about using an access method with a specific Vertex AI service, click the Learn more link.

Vertex AI product Public internet Private Service Connect for Google APIs Private Google Access Private services access Private Service Connect
Batch predictions
Datasets
Vertex AI Feature Store (Bigtable online serving)
Vertex AI Feature Store (optimized online serving)
Learn more
Generative AI on Vertex AI (Gemini)
Model Registry
Online prediction Learn more
Vector Search (index creation)
Vector Search (index query)
Learn more
Custom training (control plane)
Custom training (data plane)
Learn more
Vertex AI Pipelines
Private online prediction endpoints
Learn more

Securing your Vertex AI resources

To reduce the risk of data exfiltration for your Vertex AI resources, you can place them within a service perimeter using VPC Service Controls.

What's next