Skip to main content
Single-tenant runs your inference workloads in an isolated VPC in Baseten Cloud. Baseten provisions and operates compute and networking dedicated to your organization. You get a dedicated workload plane without running infrastructure in your own cloud account. Single-tenant architecture: a dedicated workload plane isolated to one organization
Single-tenant is available with custom pricing on the Enterprise plan.

​
Data security

Single-tenant adds dedicated, tenant-level isolation on top of Baseten Cloud’s data security controls:
  • Dedicated isolation: Compute and scheduling are restricted to your organization. Requests still authenticate against the shared control plane, but no other customer’s workloads run on your infrastructure.
  • Secure weights: Models can pull weights from a private source, and weights can be cached in-cluster to accelerate cold starts.
  • Payload retention: Baseten doesn’t store synchronous inference inputs or outputs. Async inference stores inputs until the request runs; see Async inference.
  • Restricted egress: On request, model replicas and supporting services can run without direct internet access, with outbound traffic limited to an approved allow-list.
Single-tenant supports the same compliance programs as Baseten Cloud (SOC 2 Type II, HIPAA, and GDPR) in a dedicated environment. See Secure model inference and the Baseten Trust Center for more information.

​
Private networking

Inference requests route directly from your application to your dedicated environment and can remain off the public internet. Expose endpoints through a provider-native private networking service, such as AWS PrivateLink or Google Cloud Private Service Connect, so traffic from your VPC reaches your environment over the cloud provider’s private backbone. You can also restrict inference to a specific IP range or to traffic originating within your VPC.

​
Capacity

Baseten procures and operates capacity for your dedicated workload plane. Work with the Baseten team to select regions, GPU types, and capacity commitments that meet your workload requirements.

​
Get started

Single-tenant is available with custom pricing on the Enterprise plan. Talk to us to discuss your isolation, connectivity, and capacity requirements.