Claude models in Microsoft Foundry

Discover Claude models in Microsoft Foundry. Compare available models, capabilities, quotas, and supported regions to choose the right one for your AI use case.

Anthropic’s Claude models bring advanced conversational AI capabilities to Microsoft Foundry, providing state-of-the-art language understanding and generation for intelligent applications. Claude models excel at complex reasoning, code generation, and multimodal tasks including image analysis. This article describes the available Claude models, how they’re hosted and billed, supported APIs, capabilities, quotas, and best practices.

To deploy and call a Claude model, see Deploy and use Claude models in Microsoft Foundry.

Items marked (preview) in this article are currently in public preview. This preview is provided without a service-level agreement, and we don’t recommend it for production workloads. Certain features might not be supported or might have constrained capabilities. For more information, see Supplemental Terms of Use for Microsoft Azure Previews.

How Claude models are hosted and billed

Microsoft Foundry offers Claude models in two versions:

• Version 1: Hosted on Anthropic infrastructure; these models run on Anthropic’s infrastructure (outside of Azure).
• Version 2: Hosted on Azure; these models run on Azure infrastructure end-to-end and are all Generally available (GA).

Not all models are available in both versions. A model’s lifecycle stage, such as Preview or Generally available, can differ between the two versions. For per-model availability and lifecycle status, see Available Claude models.

To compare both hosting options across data residency, SLAs, support paths, compliance, and purchasing flow, see Compare Azure-hosted and Anthropic-hosted Claude models.

You access Claude models in Microsoft Foundry through Foundry Models from partners and community. Models from partners and community that Anthropic sells and operates are Non-Microsoft Products under the Product Terms.

Claude models in Foundry require an Azure Marketplace subscription and bill through Claude Consumption Units (CCU). Ensure that you have the permissions required to subscribe to model offerings before you deploy. For pricing details, see Claude Consumption Units (CCU) billing in Microsoft Foundry.

Available Claude models

The following table compares model availability for both versions of Claude models in Foundry. For details on the features referenced in the table, see the Capabilities section.

1M context beta on Claude Sonnet 4.5 was retired on April 30, 2026.

Starting May 1, 2026:

• Requests greater than 200K tokens that include the context-1m-2025-08-07 beta header on Sonnet 4.5 return an error.
• Requests 200K tokens or fewer remain unaffected, even with the header present.

To migrate, remove the context-1m-2025-08-07 beta header from your requests. For workloads that require 1M context, migrate to Claude Sonnet 4.6 (where 1M context is generally available) or to Claude Opus 4.6 or Claude Opus 4.7 for higher-intelligence workloads.

Model	Availability	Context window / Max output	Key capabilities	Best for
claude-mythos-51	- Hosted on Anthropic infrastructure: Gated research preview	1M / 128K	- Adaptive thinking - Image and text input - Microsoft Entra ID authentication only - See Introducing Claude Fable 5 and Claude Mythos 5	- Biology and life sciences - Cybersecurity (defensive use cases prioritized): vulnerability discovery, attack-surface auditing, red teaming, threat intelligence - Autonomous coding - Long-running agents
claude-fable-5	- Hosted on Anthropic infrastructure: Preview	1M / 128K	- Adaptive thinking - Reasoning over entire codebases and multi-day project context - Longer independent work than any prior Claude model - Self verification - Sub-agent orchestration - Refusal stop_reason on dual-use safeguard policies2 - See See Introducing Claude Fable 5 and Claude Mythos 5	- Cybersecurity - Autonomous coding - Long-running agents - Coding and agents, with deeper reasoning for enterprise workflows
claude-mythos-preview1	- Hosted on Anthropic infrastructure: Gated research preview	1M / 128K	- Adaptive thinking - Image and text input - Microsoft Entra ID authentication only - See Migrating to Claude Mythos 5 and Claude Fable 5 from Claude Mythos Preview	- Cybersecurity (defensive use cases prioritized) - Autonomous coding - Long-running agents
claude-opus-5	- Hosted on Azure: GA - Hosted on Anthropic infrastructure: GA	1M / 128K	- Adaptive thinking with xhigh and max effort levels - Reasoning over entire codebases and multi-day project context - Per-turn effort controls3 - Mid-conversation3 role:"system" - Token budgets3 (task_budget) - See What’s new in Claude Opus 5	- Near-Fable intelligence for long-horizon coding and complex agentic orchestration. - Long-running agents - Enterprise workflows - Financial analysis - Computer use
claude-opus-4-8	- Hosted on Azure: GA - Hosted on Anthropic infrastructure: GA	1M / 128K	- Adaptive thinking with xhigh effort level - Reasoning over entire codebases and multi-day project context - High-resolution image input (up to 2576px / 3.75MP) - See Migrating to Claude Opus 5	- Coding - Long-running agents - Financial analysis - Cybersecurity - Computer use
claude-opus-4-7	- Hosted on Anthropic infrastructure: GA	1M / 128K	- Adaptive thinking - Reasoning over entire codebases- High-resolution image input (up to 2576px / 3.75MP) - See Migrating to Claude Opus 5	- Coding - Enterprise workflows - Long-running agents - Multimodal reasoning - Financial analysis - Cybersecurity
claude-opus-4-6	- Hosted on Anthropic infrastructure: GA	1M / 128K	- Adaptive thinking - Image and text input - Computer use - Advanced tool use (search, programmatic calling, examples) - See Migrating to Claude Opus 5	- Coding - Enterprise agents
claude-opus-4-5	- Hosted on Anthropic infrastructure: GA	200K / 64K	- Extended thinking - Image and text input - Computer use - Advanced tool use (search, programmatic calling, examples) - See Migrating to Claude Opus 5	- Coding - Agents - Computer use - Enterprise workflows
claude-opus-4-1	- Hosted on Anthropic infrastructure: GA	200K / 32K	- Extended thinking - Image and text input - See Migrating to Claude Opus 5	- Coding - Long-running tasks
claude-sonnet-5	- Hosted on Azure: GA - Hosted on Anthropic infrastructure: GA	1M / 128K	- Adaptive thinking - xhigh effort level - Reasoning over entire codebases and multi-day project context - High-res image input (up to 2576px / 3.75MP) are on by default - Mid-conversation3 role:"system" - Token budgets3 (task_budget) - See What’s new in Claude Sonnet 5	- Coding - Long-running agents - Financial analysis - Cybersecurity - Computer use
claude-sonnet-4-6	- Hosted on Anthropic infrastructure: GA	1M / 128K	- Adaptive thinking - Image and text input - Computer use - Advanced tool use (search, programmatic calling, examples) - See Migrating to Claude Sonnet 5	- Coding - Agents - Enterprise workflows
claude-sonnet-4-5	- Hosted on Anthropic infrastructure: GA	200K / 64K	- Extended thinking - Image and text input - Computer use - See Migrating to Claude Sonnet 5	- Agents and complex, long-horizon tasks - High-volume workloads
claude-haiku-4-5	- Hosted on Azure: GA - Hosted on Anthropic infrastructure: GA	200K / 64K	- Extended thinking - Image and text input	- Coding - Agents

¹ Claude Mythos 5 and Claude Mythos Preview are only available as gated research preview. Access to the models is granted solely at Anthropic’s discretion and prioritized for defensive cybersecurity use cases. See the Claude Mythos Preview system card and Claude Mythos 5 system card for responsible use guidance.

² Claude Fable 5 applies additional input/output classifiers that might refuse requests whose content triggers dual-use safeguard policies. When a refusal occurs, the request returns a successful (200) response with a refusal indicator stop_reason: "refusal" instead of model-generated content. You’re not billed for input tokens that are refused.

³ Per-turn effort controls, Mid-conversation, and Token budgets are currently in Beta state.

API overview

The following table lists the APIs that you can use to interact with both the Hosted on Azure and Hosted on Anthropic infrastructure versions of Claude models in Foundry.

Use the Anthropic SDKs and the following Claude APIs:

The Hosted on Anthropic infrastructure version of Claude models in Foundry supports more APIs than the ones listed in this table. You can see them on the Claude API docs: API overview page.

API	Description
Messages1 (POST /v1/messages)	Core Messages API: Send a structured list of input messages with text or image content, including streaming responses. The model generates the next message in the conversation.
Token counting (POST /v1/messages/count_tokens)	Token Count API: Count the number of tokens in a message before sending it to Claude.

¹You can call the Messages API from the anthropic Python package, the @anthropic-ai/foundry-sdk JavaScript package, or directly through REST. The deployment endpoint follows the shape https://<resource-name>.services.ai.azure.com/anthropic/v1/messages, and REST and JavaScript clients use the anthropic-version: 2023-06-01 header.

Capabilities

Claude models in Foundry expose core capabilities for processing, analyzing, and generating content, and tools that let Claude interact with external systems, execute code, and perform automated tasks.

The following table summarizes capabilities available for both the Hosted on Azure and Hosted on Anthropic infrastructure versions of Claude models in Foundry, including core capabilities and tools.

The Hosted on Anthropic infrastructure version of Claude models in Foundry supports more capabilities than the ones listed in this table. You can see them on the Claude API docs: Features overview page.

Feature	Description
Streaming responses	Server-sent event streaming.
Fine-grained tool streaming	Stream tool use parameters without buffering or JSON validation, reducing latency for large parameters. Requires the anthropic-beta header fine-grained-tool-streaming-2025-05-14.
Prompt caching	Cache context to reduce cost and latency.
Tool use with client-executed tools	Custom tools plus Anthropic-defined bash, text editor, computer use, and memory.
Context editing	Automatically manage conversation context with configurable strategies, including clearing tool results and managing thinking blocks. Requires the anthropic-beta header context-management-2025-06-27.
Extended thinking	Step-by-step reasoning for complex tasks.
Effort	Control how many tokens Claude uses when responding, trading off between response thoroughness and token efficiency.
Citations	Ground Claude’s responses in sources, including search_result content blocks.
Image support	Process and analyze content from images (provided as base64 or URL).
PDF support	Process and analyze text and visual content from PDF documents. Provided as base64 or URL.
1M context window	Up to 1M tokens for processing large documents, extensive codebases, and long conversations. Support is subject to model eligibility.

Model-specific parameter values

Extended thinking

The Extended thinking feature allows specific values for the thinking parameter type, depending on the model, as described in the following table. The adaptive type allows the model to decide whether to think, based on query complexity and effort level.

Model	adaptive	enabled	disabled
claude-mythos-5	Yes	No	No
claude-fable-5	Yes	No	No
claude-mythos-preview	Yes	Yes	No
claude-opus-5	Yes	No	Yes1
claude-opus-4-8	Yes	No	Yes
claude-opus-4-7	Yes	No	Yes
claude-opus-4-6	Yes	Yes	Yes
claude-sonnet-5	Yes	No	Yes
claude-sonnet-4-6	Yes	Yes	Yes

¹ Thinking can be disabled only at effort high or below

Effort

The Effort feature allows specific effort levels for each model, as described in the following table. The xhigh level produces the same result as max.

Model	low	medium	high	xhigh	max
claude-mythos-5	Yes	Yes	Yes	Yes	No
claude-fable-5	Yes	Yes	Yes	Yes	No
claude-opus-5	Yes	Yes	Yes	Yes	Yes
claude-opus-4-8	Yes	Yes	Yes	Yes	Yes
claude-opus-4-7	Yes	Yes	Yes	Yes	Yes
claude-opus-4-6	Yes	Yes	Yes	No	Yes
claude-sonnet-5	Yes	Yes	Yes	Yes	Yes
claude-sonnet-4-6	Yes	Yes	Yes	No	Yes

Agent support

• Microsoft Agent Framework supports creating agents that use Claude models.
• Build custom AI agents with the Claude Agent SDK.

Quotas, rate limits, and regions

Use this section to understand where you can deploy Claude models, how quota is shared, and what rate limits apply to your deployments.

Deployment types

Claude models in Foundry are available for the following deployment types in specific Azure regions:

• Global Standard: All Claude models (Hosted on Azure and Hosted on Anthropic infrastructure).
• Data Zone Standard (US): Hosted on Azure versions of claude-opus-5, claude-opus-4-8, and claude-sonnet-5.

For the exact Azure regions where Claude models are available for deployment, see Region availability by deployment type.

Quotas and rate limits

Subscription-level management handles the deployment quota. Resources and regions share the quota instead of allocating it separately for each resource or region.

• All Global Standard deployments of the same model and version in a subscription draw from one shared quota pool across all regions.
• All Data Zone Standard deployments of the same model and version in a subscription draw from a shared quota pool within each data zone (for example, US).

For more information about quota management for Foundry Models, see Microsoft Foundry Models quotas and limits.

Claude models in Foundry measure rate limits in Requests Per Minute (RPM) and uncached input Tokens Per Minute (ITPM).

What counts towards ITPM?

• Input TPM — tokens in the request after the last cache breakpoint (uncached input).
• Cache write 5m TPM — tokens being written to the 5-minute prompt cache.
• Cache write 1h TPM — tokens being written to the 1-hour prompt cache.

What doesn’t count towards ITPM?

• Output tokens (including tokens read from cache) don’t count towards uiTPM.

For more information about rate limits and cache, see Claude API Docs: Rate limits.

Rate limits by subscription type

Your Azure subscription type determines your rate limits. The Version 2: Hosted on Azure and Version 1: Hosted on Anthropic infrastructure columns indicate whether quota is available for that model and deployment type combination. Yes means quota is available. N/A means the model and version combination don’t have quota for that deployment type.

As listed in the following table, to increase your quota beyond the default limits, submit a request through the quota increase request form.

Pay-as-you-go

Pay-as-you-go

Model	Deployment type	Version 2: Hosted on Azure	Version 1: Hosted on Anthropic infrastructure	RPM	ITPM
claude-fable-5	Global Standard	N/A	Yes	0	0
claude-opus-5	Global Standard	Yes	Yes	40	40,000
claude-opus-5	Data Zone Standard (US)	Yes	N/A	40	40,000
claude-opus-4-8	Global Standard	Yes	Yes	40	40,000
claude-opus-4-8	Data Zone Standard (US)	Yes	N/A	40	40,000
claude-opus-4-7	Global Standard	N/A	Yes	40	40,000
claude-opus-4-6	Global Standard	N/A	Yes	40	40,000
claude-opus-4-5	Global Standard	N/A	Yes	40	40,000
claude-opus-4-1	Global Standard	N/A	Yes	40	40,000
claude-sonnet-5	Global Standard	Yes	Yes	40	40,000
claude-sonnet-5	Data Zone Standard (US)	Yes	N/A	40	40,000
claude-sonnet-4-6	Global Standard	N/A	Yes	80	80,000
claude-sonnet-4-5	Global Standard	N/A	Yes	80	80,000
claude-haiku-4-5	Global Standard	Yes	Yes	80	80,000

Enterprise and MCA-E

Enterprise and MCA-E

Model	Deployment type	Version 2: Hosted on Azure	Version 1: Hosted on Anthropic infrastructure	RPM	ITPM
claude-fable-5	Global Standard	N/A	Yes	2,000	2,000,000
claude-opus-5	Global Standard	Yes	Yes	2,000	2,000,000
claude-opus-5	Data Zone Standard (US)	Yes	N/A	2,000	2,000,000
claude-opus-4-8	Global Standard	Yes	Yes	2,000	2,000,000
claude-opus-4-8	Data Zone Standard (US)	Yes	N/A	2,000	2,000,000
claude-opus-4-7	Global Standard	N/A	Yes	2,000	2,000,000
claude-opus-4-6	Global Standard	N/A	Yes	2,000	2,000,000
claude-opus-4-5	Global Standard	N/A	Yes	2,000	2,000,000
claude-opus-4-1	Global Standard	N/A	Yes	2,000	2,000,000
claude-sonnet-5	Global Standard	Yes	Yes	2,000	2,000,000
claude-sonnet-5	Data Zone Standard (US)	Yes	N/A	2,000	2,000,000
claude-sonnet-4-6	Global Standard	N/A	Yes	4,000	4,000,000
claude-sonnet-4-5	Global Standard	N/A	Yes	4,000	4,000,000
claude-haiku-4-5	Global Standard	Yes	Yes	4,000	4,000,000

Free Trial

Free Trial

Model	Deployment type	Version 2: Hosted on Azure	Version 1: Hosted on Anthropic infrastructure	RPM	ITPM
claude-fable-5	Global Standard	N/A	Yes	0	0
claude-opus-5	Global Standard	Yes	Yes	0	0
claude-opus-5	Data Zone Standard (US)	Yes	N/A	0	0
claude-opus-4-8	Global Standard	Yes	Yes	0	0
claude-opus-4-8	Data Zone Standard (US)	Yes	N/A	0	0
claude-opus-4-7	Global Standard	N/A	Yes	0	0
claude-opus-4-6	Global Standard	N/A	Yes	0	0
claude-opus-4-5	Global Standard	N/A	Yes	0	0
claude-opus-4-1	Global Standard	N/A	Yes	0	0
claude-sonnet-5	Global Standard	Yes	Yes	0	0
claude-sonnet-5	Data Zone Standard (US)	Yes	N/A	0	0
claude-sonnet-4-6	Global Standard	N/A	Yes	0	0
claude-sonnet-4-5	Global Standard	N/A	Yes	0	0
claude-haiku-4-5	Global Standard	Yes	Yes	0	0

Responsible AI considerations

When using Claude models in Foundry, consider these responsible AI practices:

• Review Data, privacy, and security for Claude models in Microsoft Foundry to understand how your data is processed and retained when you deploy Claude models.

• Configure AI content safety during model inference, because Foundry doesn’t provide built-in content filtering for Claude models at deployment time.

• Ensure your applications comply with Anthropic’s Acceptable Use Policy. Also, see details of safety evaluations for Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Opus 4.5, Claude Opus 4.1, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5.

Best practices

Follow these best practices when working with Claude models in Foundry:

Prompt engineering

• Clear instructions: Provide specific and detailed prompts.
• Context management: Use the available context window effectively.
• Role definitions: Use system messages to define the assistant’s role and behavior.
• Structured prompts: Use consistent formatting for better results.

Cost optimization

To optimize your usage and avoid rate limiting:

• Implement retry logic: Handle 429 responses with exponential backoff.
• Batch requests: Combine multiple prompts when possible.
• Monitor token usage: Track your token consumption and request patterns.
• Use appropriate models: Use the most cost-effective model for your use case. See Available Claude models.

Related content

• Deploy and use Claude models in Microsoft Foundry
• Deploy Claude models in Microsoft Foundry using Bicep or Terraform
• Foundry Models from partners and community
• Claude Consumption Units (CCU) billing in Microsoft Foundry
• Data, privacy, and security for Claude models in Microsoft Foundry