A healthcare provider operating only within the European Union must ensure that inference requests sent to a Foundry-hosted model, along with the patient data in those requests, are processed exclusively within EU-based Azure datacenters to satisfy local regulatory requirements. What should the team configure when creating the model deployment to meet this requirement?
Select an answer to reveal the explanation.
Short Explanation
You need to deploy the model to an Azure region inside the EU and confirm the deployment's data processing region matches that region. Content filters only control what the model can say, private endpoints only protect the network path, and global routing for lowest cost gives up control over where the data is processed.
Full Explanation
Selecting an Azure region physically located in the EU and confirming that the deployment's data processing region matches that location is what actually controls where inference requests are processed and where the associated data resides, which is the specific regulatory requirement the provider must satisfy. Turning on a custom content filter category for personal health information is incorrect because it governs what the model flags or blocks in its output; it says nothing about which physical datacenter processes the request, so it does not address data residency. Configuring a private endpoint so traffic stays on the virtual network is incorrect because it secures the network path between the client and the deployment, keeping traffic off the public internet, but it does not by itself pin the deployment to a particular geographic region or guarantee EU-only processing. Choosing the global standard deployment option for the lowest per-token price is incorrect because global standard deployments are explicitly designed to route requests to whichever region has available capacity, which is the opposite of the geographic guarantee this scenario requires; choosing it for cost would directly undermine the residency requirement.