> ## Documentation Index
> Fetch the complete documentation index at: https://hobbyist-e43fa225.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart: Set up Microsoft Foundry resources
> Learn how to create a Microsoft Foundry project, deploy a model, and grant access to team members so they can build AI applications.
In this quickstart, you create a [Microsoft Foundry](https://ai.azure.com) project and deploy a model. If you're managing a team, you also grant access to team members. After you complete these steps, you or your team can start building AI applications using the deployed model.
This quickstart shows you how to create resources to build an agent with a basic setup. For more advanced scenarios that use your own resources, see [Set up your environment for agent development](../agents/environment-setup).
## Prerequisites
* An Azure account with an active subscription. If you don't have one, create a [free Azure account, which includes a free trial subscription](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* If you're creating the project for yourself:
* Access to a role that allows you to create a Foundry resource, such as **Foundry Account Owner** or **Foundry Owner** on the subscription or resource group. For more information about permissions, see [Role-based access control for Microsoft Foundry](../concepts/rbac-foundry#permissions-for-each-built-in-role).
The Foundry RBAC roles were recently renamed. **Foundry User**, **Foundry Owner**, **Foundry Account Owner**, and **Foundry Project Manager** were previously named Azure AI User, Azure AI Owner, Azure AI Account Owner, and Azure AI Project Manager. You might still see the previous names in some places while the rename rolls out. The role IDs and core permissions are unchanged by the rename.
* If you're creating the project for a team:
* Access to a role that allows you to complete role assignments, such as **Owner**. For more information about permissions, see [Role-based access control for Microsoft Foundry](../concepts/rbac-foundry#permissions-for-each-built-in-role).
* A list of user email addresses or Microsoft Entra security group IDs for team members who need access.
Select your preferred method by using the following tabs:
* Install the [Azure CLI](https://learn.microsoft.com/cli/azure/install-azure-cli) version 2.67.0 or later (check with `az version`).
* Sign in to Azure:
```azurecli theme={null}
az login
```
* Access to the [Microsoft Foundry portal](https://ai.azure.com).
## Create a project
Create a Foundry project to organize your work. The project contains models, agents, and other resources your team uses.
Create your project in the **West US 3** region if you want to try an [instant model (preview)](/models/instant-models).
These steps require Azure CLI and **Contributor** or **Owner** role on the resource group. Run `az login` to sign in before you start. For supported regions, see [Region support](/models/region-support).
1. Create a resource group or use an existing one. For example, create `my-foundry-rg` in `eastus`:
```azurecli theme={null}
az group create --name my-foundry-rg --location eastus
```
2. Create the Foundry resource with project management enabled. For example, create `my-foundry-resource` in the `my-foundry-rg` resource group:
```azurecli theme={null}
az cognitiveservices account create \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--kind AIServices \
--sku S0 \
--location eastus \
--custom-domain my-foundry-resource \
--allow-project-management
```
Set the `--allow-project-management` flag to enable project management. You can't change this flag after resource creation. The `--custom-domain` value must be globally unique - if `my-foundry-resource` is already taken, choose a different name.
3. Create a project. For example, create `my-foundry-project` in the `my-foundry-resource`:
```azurecli theme={null}
az cognitiveservices account project create \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--project-name my-foundry-project \
--location eastus
```
4. Verify that the resource is provisioned:
```azurecli theme={null}
az cognitiveservices account show \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--query properties.provisioningState --output tsv
```
The output should show `Succeeded`. If the output shows a different state, check your permissions, region availability, and resource quotas. For more help, see [Create a multi-service resource](../../ai-services/multi-service-resource).
5. Verify the project was created:
```azurecli theme={null}
az cognitiveservices account project show \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--project-name my-foundry-project \
--query properties.provisioningState --output tsv
```
The output should show `Succeeded`.
1. Sign in to [Microsoft Foundry](https://ai.azure.com/?cid=learnDocs). Make sure the **New Foundry** toggle is on. These steps refer to **Foundry (new)**.
1. Create a project.
* If this is your first use of Foundry, you'll be asked to create or search for a project to continue. Select **Create a new project** in the dropdown.
* If you already have a project loaded, select its name in the upper-left corner, and then select **Create new project**.
1. Enter a project name, such as `my-foundry-project`.
2. Select **Advanced options** to configure the resource group and location:
* **Resource group**: Create a new resource group or select an existing one. If you create a new resource group, you can more easily manage the project and all its resources together.
* **Location**: Select the region closest to your team.
3. Select **Create project**.
Wait for the project to be created. When the project overview page appears, your project is ready.
## Deploy a model
Deploy a model that you can use. This example uses **gpt-5.1-mini**, but you can choose any available model.
To try an [instant access model (preview)](/models/instant-models), you can skip this step.
```azurecli theme={null}
az cognitiveservices account deployment create \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--deployment-name gpt-5.1-mini \
--model-name gpt-5.1-mini \
--model-version "2025-04-14" \
--model-format OpenAI \
--sku-capacity 10 \
--sku-name Standard
```
Verify the deployment succeeded:
```azurecli theme={null}
az cognitiveservices account deployment show \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--deployment-name gpt-5.1-mini
```
When the deployment is ready, the output shows `"provisioningState": "Succeeded"`.
Reference: [az cognitiveservices account deployment](https://learn.microsoft.com/cli/azure/cognitiveservices/account/deployment)
1. Select **Discover** in the upper-right navigation, then **Models** in the left pane.
2. Search for **gpt-5.1-mini**.
3. Select **Deploy** > **Default settings** to add it to your project.
4. Note the deployment name (for example, `gpt-5.1-mini`). Your team needs this name to use the model.
## Get your project connection details
You need your project endpoint to connect from code. If you're administering this project for others, send them this endpoint along with the deployment name.
1. Sign in to [Microsoft Foundry](https://ai.azure.com/?cid=learnDocs) by using your Azure account.
2. Select your project.
3. Find your project endpoint on the welcome screen of the project.
1. Copy the endpoint value. You use this value in other quickstarts and tutorials.
## For administrators - grant access
If you're administering a team, assign the **Foundry User** role to team members so they can use the project and deployed models. This role provides the minimum permissions needed to build and test AI applications. For other roles you might need to assign, see [Role-based access control for Microsoft Foundry](../concepts/rbac-foundry)
The Foundry RBAC roles were recently renamed. **Foundry User**, **Foundry Owner**, **Foundry Account Owner**, and **Foundry Project Manager** were previously named Azure AI User, Azure AI Owner, Azure AI Account Owner, and Azure AI Project Manager. You might still see the previous names in some places while the rename rolls out. The role IDs and core permissions are unchanged by the rename.
1. Get the project's resource ID:
```azurecli theme={null}
PROJECT_ID=$(az cognitiveservices account project show \
--name my-foundry-resource \
--resource-group my-foundry-rg \
--project-name my-foundry-project \
--query id -o tsv)
```
2. Assign the **Foundry User** role to a team member:
> The Foundry RBAC roles were recently renamed. **Foundry User**, **Foundry Owner**, **Foundry Account Owner**, and **Foundry Project Manager** were previously named Azure AI User, Azure AI Owner, Azure AI Account Owner, and Azure AI Project Manager. You might still see the previous names in some places while the rename rolls out. The role IDs and core permissions are unchanged by the rename.
```azurecli theme={null}
az role assignment create \
--role "53ca6127-db72-4b80-b1b0-d745d6d5456d" \
--assignee "user@contoso.com" \
--scope $PROJECT_ID
```
Because the Foundry RBAC roles were recently renamed, use the role definition ID (GUID) instead of the role name in your code to avoid issues during the rename rollout:
* **Foundry User**: `53ca6127-db72-4b80-b1b0-d745d6d5456d`
* **Foundry Owner**: `c883944f-8b7b-4483-af10-35834be79c4a`
* **Foundry Account Owner**: `e47c6f54-e4a2-4754-9501-8e0985b135e1`
* **Foundry Project Manager**: `eadc314b-1a2d-4efa-be10-5d325db5065e`
To add a security group instead of an individual user:
```azurecli theme={null}
az role assignment create \
--role "53ca6127-db72-4b80-b1b0-d745d6d5456d" \
--assignee-object-id "" \
--assignee-principal-type Group \
--scope $PROJECT_ID
```
1. Verify the role assignment:
```azurecli theme={null}
az role assignment list \
--scope $PROJECT_ID \
--role "53ca6127-db72-4b80-b1b0-d745d6d5456d" \
--output table
```
Reference: [az role assignment](https://learn.microsoft.com/cli/azure/role/assignment)
1. In the Foundry portal, select **Operate** in the upper-right navigation.
2. Select **Admin** in the left pane.
3. Select your project name in the table.
4. Select **Add user** in the upper right.
5. Enter the email address of the team member.
6. Select **Add**.
Repeat these steps for each team member or security group.
To add multiple users at once, use a Microsoft Entra security group instead of individual email addresses.
### Verify team member access
Ask a team member to verify their access by signing in to [Microsoft Foundry](https://ai.azure.com) and selecting the project from the project list.
If the team member can't access the project, verify that the role assignment completed successfully. Check that you used the correct email address or security group ID. Make sure the team member's Azure account is in the same Microsoft Entra tenant.
To confirm the deployed model is available, ask the team member to select **Build** in the upper-right navigation, then **Models** in the left pane.
## Clean up resources
When you no longer want this project, delete the resource group to delete all resources associated with it.
```azurecli theme={null}
az group delete --name my-foundry-rg --yes --no-wait
```
In the [Azure portal](https://portal.azure.com), find and select your resource group. Select **Delete** and confirm to delete the resource group and all its associated resources.
## Next step