Use Private Endpoints in OCI Generative AI

You can now access pretrained models through OCI Generative AI private endpoints.

An OCI Generative AI private endpoint is a private IP address within an OCI virtual cloud network (VCN). You use this private endpoint to access a model that's hosted on a Generative AI dedicated AI cluster. Generative AI service sets up the private endpoint in a private subnet of the VCN. Think of the private endpoint as another VNIC within the VCN. You control access to it similar to any other VNIC, using security rules. The service creates this VNIC, and you manage the subnet and its security rules.

To access a Generative AI model through a private endpoint, host the model on a dedicated AI cluster and attach the cluster's endpoint to a Generative AI private endpoint.

Learn about Private Endpoints in Generative AI. For information about the service, see the Generative AI documentation.