Claude Code on Microsoft Foundry
Learn about configuring Claude Code through Microsoft Foundry, including setup, configuration, and troubleshooting.
Prerequisites
Before configuring Claude Code with Microsoft Foundry, ensure you have:
- An Azure subscription with access to Microsoft Foundry
- RBAC permissions to create Microsoft Foundry resources and deployments
- Azure CLI installed and configured (optional - only needed if you don't have another mechanism for getting credentials)
Setup
1. Provision Microsoft Foundry resource
First, create a Claude resource in Azure:
- Navigate to the Microsoft Foundry portal
- Create a new resource, noting your resource name
- Create deployments for the Claude models:
- Claude Opus
- Claude Sonnet
- Claude Haiku
2. Configure Azure credentials
Claude Code supports two authentication methods for Microsoft Foundry. Choose the method that best fits your security requirements.
Option A: API key authentication
- Navigate to your resource in the Microsoft Foundry portal
- Go to the Endpoints and keys section
- Copy API Key
- Set the environment variable:
export ANTHROPIC_FOUNDRY_API_KEY=your-azure-api-key
Option B: Microsoft Entra ID authentication
When ANTHROPIC_FOUNDRY_API_KEY is not set, Claude Code automatically uses the Azure SDK default credential chain.
This supports a variety of methods for authenticating local and remote workloads.
On local environments, you commonly may use the Azure CLI:
az login
3. Configure Claude Code
Set the following environment variables to enable Microsoft Foundry:
# Enable Microsoft Foundry integration
export CLAUDE_CODE_USE_FOUNDRY=1
# Azure resource name (replace {resource} with your resource name)
export ANTHROPIC_FOUNDRY_RESOURCE={resource}
# Or provide the full base URL:
# export ANTHROPIC_FOUNDRY_BASE_URL=https://{resource}.services.ai.azure.com/anthropic
4. Pin model versions
Set the model variables to match the deployment names you created in step 1.
Without ANTHROPIC_DEFAULT_OPUS_MODEL, the opus alias on Foundry resolves to Opus 4.6. Set it to the Opus 4.8 ID to use the latest model:
export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'
export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5'
Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Foundry, Claude Code defaults this to the primary model because not every account has a Haiku deployment. To use Haiku for background tasks, set ANTHROPIC_DEFAULT_HAIKU_MODEL to a Haiku deployment that is available in your account, as shown above.
For current and legacy model IDs, see Models overview. See Model configuration for the full list of environment variables.
Prompt caching is enabled automatically. To request a 1-hour cache TTL instead of the 5-minute default, set the following variable; cache writes with a 1-hour TTL are billed at a higher rate:
export ENABLE_PROMPT_CACHING_1H=1
5. Run Claude Code
With the environment variables set, start Claude Code from your project directory:
claude
Claude Code reads CLAUDE_CODE_USE_FOUNDRY and the other Foundry variables from the environment and connects to your Azure resource on the first prompt. Unlike Bedrock and Vertex AI, Foundry has no interactive setup wizard, so the environment variables in steps 3 and 4 are the only configuration path.
Azure RBAC configuration
The Azure AI User and Cognitive Services User default roles include all required permissions for invoking Claude models.
For more restrictive permissions, create a custom role with the following:
{
"permissions": [
{
"dataActions": [
"Microsoft.CognitiveServices/accounts/providers/*"
]
}
]
}
For details, see Microsoft Foundry RBAC documentation.
Troubleshooting
If you receive an error "Failed to get token from azureADTokenProvider: ChainedTokenCredential authentication failed":
- Configure Entra ID on the environment, or set
ANTHROPIC_FOUNDRY_API_KEY.