Quotas and limits for Microsoft Foundry Agent Service

Review default limits for Foundry Agent Service, including file sizes, vector stores, messages, tools, error handling, supported regions, and compatible models.

Foundry Agent Service enforces quotas and limits on agent artifacts, file uploads, messages, and tool registrations. Understanding these limits helps you design applications that scale without hitting service boundaries. This article lists default limits, supported regions, compatible models, and guidance for handling limit errors.

Foundry Agent Service is generally available (GA). Some sub-features are in public preview and might have different constraints.

Prerequisites

• An Azure subscription.
• A Microsoft Foundry project.
• A deployed model compatible with Agent Service. Model and region availability can vary.

Supported regions

The following table shows regional support for the Responses API, Agents, and private class A IP address ranges.

Region	Responses API	Agents	Class A*
Australia East	Yes	Yes	Yes
Brazil South	Yes	Yes	Yes
Canada Central	Yes	Yes	No
Canada East	Yes	Yes	Yes
Central US	Yes	Yes	Yes
East US	Yes	Yes	Yes
East US 2	Yes	Yes	Yes
France Central	Yes	Yes	Yes
Germany West Central	Yes	Yes	Yes
Italy North	Yes	Yes	Yes
Japan East	Yes	Yes	Yes
Japan West	Yes	Yes	No
Korea Central	Yes	Yes	Yes
North Central US	Yes	Yes	Yes
Norway East	Yes	Yes	No
Poland Central	Yes	Yes	No
South Africa North	Yes	Yes	Yes
South Central US	Yes	Yes	Yes
Southeast Asia	Yes	Yes	Yes
South India	Yes	Yes	Yes
Spain Central	Yes	Yes	Yes
Sweden Central	Yes	Yes	Yes
Switzerland North	Yes	Yes	No
Switzerland West	Yes	Yes	No
UAE North	Yes	Yes	Yes
UK South	Yes	Yes	Yes
West Central US	Yes	Yes	No
West Europe	Yes	Yes	Yes
West US	Yes	Yes	Yes
West US 3	Yes	Yes	Yes

* Class A refers to support for private Class A IP address ranges (10.x.x.x). For related networking requirements, see Regional support for private networking.

Some Azure OpenAI models aren’t available in every region. For details, see Region availability for Foundry Models sold by Azure.

Not all tools are available in every region. For example, file search isn’t available in Italy North and Brazil South. For the full tool-by-region matrix, see Tool support by region and model.

Regional support for private networking

When you use a private network configuration, such as a network-secured standard agent, the following regional requirements apply:

• Foundry resource and virtual network region. You must deploy the Foundry resource in the same region as its virtual network. You can deploy other Azure resources, such as Azure Cosmos DB, Azure AI Search, and Azure Storage, in different regions. Consider the cost implications of cross-region deployments.
• Grounding with Bing Search. Only the following regions are supported: West Europe, Canada East, Switzerland North, Spain Central, UAE North, Korea Central, Poland Central, Southeast Asia, West US, West US 2, West US 3, East US, East US 2, Central US, South India, Japan East, UK South, France Central, Norway East, Australia East, Canada Central, Sweden Central, South Africa North, Italy North, Brazil South.

For more information, see Use a virtual network with Foundry Agent Service.

Supported models

Agent Service supports Azure OpenAI models and several Foundry models sold by Azure. Model availability can change over time and varies by region. To see the full list of models you can deploy for your project and region, use the Foundry portal model experience.

Sovereign clouds

Foundry Agent Service is also available in Azure Government (US Gov Virginia and US Gov Arizona) with a subset of agent types and tools. For the full list of supported features, see Foundry Agent Service feature availability in Azure Government.

Tool support by region and model

Region and model determine which tools are available to your agent. In the following tables, Yes means fully supported, No means not supported, and Limited means partial support that varies by tool configuration. Check individual tool documentation for details.

The following table shows which tools are available in each supported region. This table only accounts for service availability, so make sure the model you want to use is also available in the same region.

The following table shows which tools each model supports. For the image generation tool, you need both the gpt-image-1 model and a large language model (LLM) as the orchestrator in the same Microsoft Foundry project.

Troubleshooting

A model or version isn’t available in your region

• Confirm you selected the right tab for your deployment type (global standard vs. provisioned).
• Try a different region that supports the model and Responses API.
• If you’re using gpt-5 models, registration is required. Access is granted according to Microsoft’s eligibility criteria.

A tool isn’t available in your region

• Not all tools are supported in every region. For example, file search isn’t available in Italy North and Brazil South.
• Check the tool support by region and model table to confirm availability before you deploy.
• If a tool isn’t available, choose a supported region or use a different tool.

Provisioned throughput deployment fails

• Confirm you have enough PTUs available in the region.
• Review Provisioned throughput and Spillover traffic management.

Agent receives rate-limit (429) errors

• Implement exponential backoff with jitter in your application retry logic.
• For sustained high-throughput workloads, consider provisioned throughput deployments.
• Review Azure OpenAI quotas and limits for your deployment’s tokens-per-minute and requests-per-minute caps.

How Agent Service enforces limits

Foundry Agent Service enforces limits in two places:

• Agent Service limits. Limits for agent and thread artifacts, such as file uploads, vector store attachments, message counts, and tool registration.
• Model limits. Quotas and rate limits for the model deployments your agents call.

The artifacts these limits govern are stored in either Microsoft-managed storage or your own Azure resources, depending on your setup.

Where Agent Service stores your data

Where your agent data lives depends on which setup option you choose. The setup option also determines which resources the quotas and limits in this article apply to.

• Basic setup stores agent state in secure, Microsoft-managed storage that’s logically separated. This is the default when you don’t configure your own resources.
• Standard setup stores agent state in customer-managed, single-tenant Azure resources in your own subscription, which gives you full control over data residency and access.

Data type	Basic setup	Standard setup
Files, uploads, and attachments	Microsoft-managed storage	Azure Storage (Blob Storage)
Vector stores, embeddings, and retrieval indexes	Microsoft-managed vector search	Azure AI Search
Threads, conversation history, messages, and agent definitions	Microsoft-managed storage	Azure Cosmos DB

Capability hosts tell Agent Service where to store and process file uploads, vector stores, and conversation history. To store agent data in your own resources, see Standard agent setup.

Foundry Agent Service endpoints are regional, and data is stored in the same region as the endpoint. For more information, see the Azure data residency documentation.

Default service limits

The following table lists default limits enforced by the Agent Service. These limits apply to all Foundry projects regardless of subscription type or region.

Limit name	Limit value
Maximum number of files per agent/thread	10,000
Maximum file size for agents	512 MB
Maximum size for all uploaded files for agents	300 GB
Maximum file size in tokens for attaching to a vector store	2,000,000 tokens
Maximum number of messages per thread	100,000
Maximum size of text content per message	1,500,000 characters
Maximum number of tools registered per agent	128
Maximum number of valid agent revisions per agent	1,000

The Agent Service limits in this table are fixed and apply uniformly across all subscription types. Rate limiting for model calls is applied at the model deployment level; see Azure OpenAI quotas and limits for model-specific rate limits.

Limit error reference

When you exceed a limit, the Agent Service returns an error. Handle these errors gracefully in your application.

Error scenario	HTTP status	Error code	Recommended action
File too large	400	file_size_exceeded	Split content into smaller files
Vector store token limit	400	token_limit_exceeded	Reduce file content or split files
Thread message cap	400	message_limit_exceeded	Create a new thread
Message content too large	400	content_size_exceeded	Use file search for large content
Too many tools	400	tool_limit_exceeded	Remove unused tools
Rate limit exceeded	429	rate_limit_exceeded	Implement exponential backoff
Too many valid agent revisions	400	UserError	Delete older versions before creating new ones

For example:

• File exceeds the maximum size. Uploading the file fails. Split the content into smaller files or reduce file size before you upload.
• Vector store token limit. Attaching a file to a vector store fails if the file exceeds the token limit. Reduce the file content or split it into multiple files.
• Thread message cap. Adding messages can fail after a thread reaches the message limit. Create a new thread for a new conversation session, or archive and rotate threads as part of your application design.
• Message content size. Creating a message can fail if the text content is too large. Send smaller messages, or move large content into files and use file search.
• Tool registration cap. Creating or updating an agent can fail if you register too many tools. Register only the tools you need, and prefer fewer, reusable tools.
• Rate limit exceeded. API calls to the model deployment are throttled. Implement exponential backoff with jitter.
• Valid agent revision cap. Creating a version fails once an agent reaches 1,000 valid revisions. Delete versions you no longer need to free capacity immediately, then create new versions.

For file search scenarios, see Vector stores for file search for guidance on managing vector store growth.

Best practices to stay within limits

Use the following practices to reduce limit-related failures:

• Keep files small and focused. Prefer multiple smaller documents over a single large document.
• Avoid very large messages. Put long content in uploaded files and query it by using file search.
• Plan for long conversations. Treat threads as session state and rotate to new threads when conversations become very long.
• Register only required tools. Remove unused tools from agent definitions.
• Monitor usage trends. Track agent activity by using Foundry Agent Service metrics to identify growth before you hit limits.

Model quotas and rate limits

Agents follow the quotas and rate limits for the model deployments they use.

For current model quotas and limits, see:

• Azure OpenAI quotas and limits.
• Microsoft Foundry Models quotas and limits.

To view or request more model quota, see Manage and increase quotas for resources with Microsoft Foundry (Foundry projects).

Request a limit increase

The limits in this article are default values for Foundry Agent Service. If your workload requires higher limits:

• Model quotas. You can request increases for model deployment quotas. See Manage and increase quotas for resources with Microsoft Foundry.
• Agent Service limits. The file, message, and tool limits listed in this article are fixed service limits and can’t be increased. Design your application to work within these constraints by using the best practices described earlier.

Related content

• Threads, runs, and messages in Foundry Agent Service
• Capability hosts
• Standard agent setup
• Tool support by region and model
• Vector stores for file search
• Monitor Foundry Agent Service
• Azure OpenAI quotas and limits
• Manage and increase quotas for resources with Microsoft Foundry