Claude in Microsoft Foundry

This guide walks you through the process of setting up and making API calls to Claude in Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you can access Claude in Foundry, you are billed for Claude usage in the Microsoft Marketplace, allowing you to access Claude's latest capabilities while managing costs through your Azure subscription.

Regional availability: At launch, Claude is available as a Global Standard deployment type in Foundry resources. Pricing for Claude in the Microsoft Marketplace uses Anthropic's standard API pricing. Visit Pricing for details.

Preview

In this preview platform integration, Claude models run on Anthropic's infrastructure. This is a commercial integration for billing and access through Azure. As an independent processor for Microsoft, customers using Claude through Microsoft Foundry are subject to Anthropic's data use terms. Anthropic continues to provide its industry-leading safety and data commitments, including zero data retention availability.

Prerequisites

Before you begin, ensure you have:

• An active Azure subscription
• Access to Foundry
• The Azure CLI installed (optional, for resource management)

Install an SDK

Anthropic's client SDKs support Foundry through a platform-specific package or client class.

Provisioning

Foundry uses a two-level hierarchy: resources contain your security and billing configuration, while deployments are the model instances you call via API. You'll first create a Foundry resource, then create one or more Claude deployments within it.

Provisioning Foundry resources

Create a Foundry resource, which is required to use and manage services in Azure. You can follow these instructions to create a Foundry resource. Alternatively, you can start by creating a Foundry project, which involves creating a Foundry resource.

To provision your resource:

1. Navigate to the Foundry portal
2. Create a new Foundry resource or select an existing one
3. Configure access management using Azure-issued API keys or Entra ID (formerly Azure Active Directory) for role-based access control
4. Optionally configure the resource to be part of a private network (Azure Virtual Network) for enhanced security
5. Note your resource name. You'll use this as {resource} in API endpoints (for example, https://{resource}.services.ai.azure.com/anthropic/v1/*)

Creating Foundry deployments

After creating your resource, deploy a Claude model to make it available for API calls:

1. In the Foundry portal, navigate to your resource
2. Go to Models + endpoints and select + Deploy model > Deploy base model
3. Search for and select a Claude model (for example, claude-sonnet-4-6)
4. Configure deployment settings:
   • Deployment name: Defaults to the model ID, but you can customize it (for example, my-claude-deployment). The deployment name cannot be changed after it has been created.
   • Deployment type: Select Global Standard (recommended for Claude)
5. Select Deploy and wait for provisioning to complete
6. Once deployed, you can find your endpoint URL and keys under Keys and Endpoint

Authentication

Claude in Foundry supports two authentication methods: API keys and Entra ID tokens. Both methods use Azure-hosted endpoints in the format https://{resource}.services.ai.azure.com/anthropic/v1/*.

API key authentication

After provisioning your Foundry Claude resource, you can obtain an API key from the Foundry portal:

1. Navigate to your resource in the Foundry portal
2. Go to Keys and Endpoint section
3. Copy one of the provided API keys
4. Use either the api-key or x-api-key header in your requests, or provide it to the SDK

The Foundry SDKs require an API key and either a resource name or base URL. The C#, Java, PHP, Python, and TypeScript SDKs automatically read these from the following environment variables if they are defined:

• ANTHROPIC_FOUNDRY_API_KEY - Your API key
• ANTHROPIC_FOUNDRY_RESOURCE - Your resource name (for example, example-resource)
• ANTHROPIC_FOUNDRY_BASE_URL - Alternative to resource name; the full base URL (for example, https://example-resource.services.ai.azure.com/anthropic/)

Example using API key:

Microsoft Entra authentication

For enhanced security and centralized access management, you can use Entra ID tokens:

1. Enable Entra authentication for your Foundry resource
2. Obtain an access token from Entra ID
3. Use the token in the Authorization: Bearer {TOKEN} header

Example using Entra ID:

Correlation request IDs

Foundry includes request identifiers in HTTP response headers for debugging and tracing. When contacting support, provide both the request-id and apim-request-id values to help teams quickly locate and investigate your request across both Anthropic and Azure systems.

Feature support

Claude in Foundry supports most of Claude's powerful features. You can find all the features currently supported in Features overview.

Context window

Claude Fable 5, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 have a 1M-token context window on Microsoft Foundry. Other Claude models, including Claude Opus 4.8 and Sonnet 4.5, have a 200k-token context window.

Features not supported

• Admin API
• Compliance API
• Models API
• Message Batches API
• Server-side fallback (the fallbacks parameter; use the client-side fallback pattern instead)

API responses

API responses from Claude in Foundry follow the standard Claude API response format. This includes the usage object in response bodies, which provides detailed token consumption information for your requests. The usage object is consistent across all platforms (Claude API, Foundry, Claude Platform on AWS, Amazon Bedrock, and Vertex AI).

For details on response headers specific to Foundry, see Correlation request IDs.

API model IDs and deployments

Lifecycle terms (Deprecated, Retired) are defined in Model deprecations. Microsoft Foundry follows the Claude API lifecycle schedule.

The following Claude models are available through Foundry. The latest generation models (Claude Fable 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, and Haiku 4.5) offer the most advanced capabilities:

By default, deployment names match the model IDs shown in the preceding table. However, you can create custom deployments with different names in the Foundry portal to manage different configurations, versions, or rate limits. Use the deployment name (not necessarily the model ID) in your API requests.

Monitoring and logging

Azure provides comprehensive monitoring and logging capabilities for your Claude usage through standard Azure patterns:

• Azure Monitor: Track API usage, latency, and error rates
• Azure Log Analytics: Query and analyze request/response logs
• Cost Management: Monitor and forecast costs associated with Claude usage

Anthropic recommends logging your activity on at least a 30-day rolling basis to understand usage patterns and investigate any potential issues.

Troubleshooting

Authentication errors

Error: 401 Unauthorized or Invalid API key

• Solution: Verify your API key is correct. You can obtain a new API key from the Foundry portal under Keys and Endpoint for your Foundry resource.
• Solution: If using Microsoft Entra ID, ensure your access token is valid and hasn't expired. Tokens typically expire after 1 hour.

Error: 403 Forbidden

• Solution: Your Azure account may lack the necessary permissions. Ensure you have the appropriate Azure RBAC role assigned (for example, "Cognitive Services OpenAI User").

Rate limiting

Error: 429 Too Many Requests

• Solution: You've exceeded your rate limit. Implement exponential backoff and retry logic in your application.
• Solution: Consider requesting rate limit increases through the Azure portal or Azure support.

Rate limit headers

Foundry does not include Anthropic's standard rate limit headers (anthropic-ratelimit-tokens-limit, anthropic-ratelimit-tokens-remaining, anthropic-ratelimit-tokens-reset, anthropic-ratelimit-input-tokens-limit, anthropic-ratelimit-input-tokens-remaining, anthropic-ratelimit-input-tokens-reset, anthropic-ratelimit-output-tokens-limit, anthropic-ratelimit-output-tokens-remaining, and anthropic-ratelimit-output-tokens-reset) in responses. Manage rate limiting through Azure's monitoring tools instead.

Model and deployment errors

Error: Model not found or Deployment not found

• Solution: Verify you're using the correct deployment name. If you haven't created a custom deployment, use the default model ID (for example, claude-sonnet-4-6).
• Solution: Ensure the model/deployment is available in your Azure region.

Error: Invalid model parameter

• Solution: The model parameter should contain your deployment name, which can be customized in the Foundry portal. Verify the deployment exists and is properly configured.

Additional resources

• Foundry documentation: ai.azure.com/catalog
• Azure pricing: azure.microsoft.com/en-us/pricing/details/ai-foundry
• Anthropic pricing details: Model pricing
• Authentication guide: See Authentication
• Azure portal: portal.azure.com