Skip to main content
To use Microsoft Foundry (Azure AI Foundry) as the inference provider, set inferenceProvider to foundry and supply the resource name and credentials (API key, credential helper, or Entra ID sign-in) described below.
In this preview platform integration, Claude models on Microsoft Foundry run on Anthropic’s infrastructure. This is a commercial integration for billing and access through Azure. The data-residency and “no conversation data sent to Anthropic” statements elsewhere in these pages do not apply when using Microsoft Foundry. See the Overview for details.

​
Configuration keys

SettingRequiredDescription
Azure AI Foundry resource name
inferenceFoundryResource		YesAzure AI Foundry resource name used to construct the endpoint URL (<resource>.services.ai.azure.com). Two to sixty-four characters, lowercase alphanumeric and hyphens.
Azure AI Foundry API key
inferenceFoundryApiKey		For static authAPI key for the Foundry resource. May be supplied dynamically by an inferenceCredentialHelper executable instead.
Entra ID tenant ID
inferenceFoundryTenantId		For interactive sign-inDirectory (tenant) ID of the Entra ID app registration that has the Cognitive Services scope. Use with inferenceCredentialKind: "interactive" for per-user device-code sign-in instead of a shared API key.
Entra ID client ID
inferenceFoundryClientId		For interactive sign-inApplication (client) ID of the Entra ID app registration. The app must allow public client flows for device code.
You must also set inferenceModels to a list of Foundry deployment names. See the Configuration reference.

​
Configure in the app

Open the in-app configuration window (Developer → Configure third-party inference). In the Connection section, set Inference provider to Foundry, then fill in the Foundry credentials card:
FieldValue
Azure AI Foundry resource nameyour-foundry-resource
Azure AI Foundry API keyyour API key
Under Models, add at least one Model list entry using the Foundry deployment name. Then click Export to produce a .mobileconfig (macOS) or .reg (Windows) file for your MDM. See Installation and setup for the export and deployment workflow.