Azure Foundry - Error deploying model

Hi Sebastian,

Sorry you're running into this issue.

The error message "Failed to create deployment. An error occurred. Please reach out to support for additional assistance." is fairly generic and doesn't identify the root cause on its own.

A few common things to check are:

1. Verify model availability

Ensure the model you're trying to deploy is available in your selected region and is supported for your subscription.

2. Check quota availability

Insufficient quota is a common reason for deployment failures. In Azure AI Foundry, navigate to Quota and verify that you have sufficient capacity available for the model and region you're deploying to.

3. Review deployment settings

Confirm that the selected model version, deployment type, and other configuration settings are valid for your scenario.

4. Check deployment details and logs

If available, review the deployment operation details in Azure AI Foundry or Azure Portal for a more specific error message. The generic banner often hides the underlying cause.

5. Retry the deployment

Occasionally, transient service issues can cause deployment failures. Refresh the portal and try the deployment again.

To help narrow this down, could you provide:

• The model you're trying to deploy
• The Azure region
• Whether you're deploying through Azure AI Foundry, SDK, CLI, or REST API
• Any additional error details shown in the deployment operation logs

With those details, the community may be able to identify the exact cause more quickly.

Reference:

Create model deployments in Azure AI Foundry

How to deploy and infer with a managed compute deployment (classic)

I Hope this helps. Do let me know if you have any further queries.

Thankyou!