Networking
For network administrators (or anyone else who needs to dive deeper intoVertex AI and generative AI networking),Vertex AI networking documentationshows you how to configure and work with networking and traffic managementfeatures for your generative AI models and data, including the followingtopics:
Accessing the Vertex AI API
Learn about the different ways to access the Vertex AI API, such as available deployment endpoints, when to use a Shared VPC, and more.
Network access with Vertex AI
Information on the ways that you can use enterprise networking options to access the Vertex AI platform.
Accessing Vertex AI services through PSC endpoints
Information on how to access Vertex AI services through Private Service Connect endpoints.
Set up a PSC interface for Vertex AI resources
Learn how to set up a Private Service Connect interface for Vertex AI resources.
VPC Service Controls with Vertex AI
Learn how to mitigate the risk of data exfiltration by creating a service perimeter around your models, training data, and other critical resources.
Use Private Service Connect to access Generative AI on Vertex AI from on-premises
Learn to use High-Availability VPN (HA VPN) to access Generative AI on Vertex AI both publicly, through Cloud NAT; and privately, between two Virtual Private Cloud (VPC) networks that can serve as a basis for multi-cloud and on-premises private connectivity.
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-02-19 UTC.