Where is my data processed?

By default, Baseten Cloud runs workloads on a managed, multi-cloud, multi-region fleet. Unless regional constraints are configured, workloads may be placed across available Baseten Cloud capacity to keep models fast and available.

If your architecture requires region-specific processing — for example, EU-only or US-only — use regional environments. Regional environments constrain replicas to a designated geographic region and provide a region-specific inference endpoint. They require initial configuration by Baseten.

For self-hosted and single-tenant options where workloads run in dedicated or customer-controlled infrastructure, see hosting options.