715-123420 error in foundry model deployment

Welcome to Microsoft Q&A!

Hello @Mahiraa kansal I hope you are doing well,

The error 715-123420:

"Our system has detected this request as unusual activity for your account."

This error as a service-side security/fraud protection signal that can block model deployments and requires review by the appropriate internal team.

Dont repeatedly retrying the deployment, as this is unlikely to clear the restriction.

Confirm that your Azure subscription is active and has a valid billing profile.

1. If you are using a VPN, proxy, or automated environment, try once from the Azure/Foundry portal using a normal network.
2. Microsoft's documentation confirms that normal model deployment failures can be caused by quota, availability, or permissions, but this particular error message points to a different service-side restriction. https://learn.microsoft.com/is-is/azure/foundry/foundry-models/how-to/deploy-foundry-models

·       Deploy Microsoft Foundry Models

• Role-based access control for Microsoft Foundry

·       Microsoft Q&A: 715-123420 service-side issue

If this answer helped clarify the platform capabilities and save you troubleshooting time, please consider marking it as Accepted. This helps others in the community find similar solutions.

Hi @Mahiraa kansal

Error 715-123420, “Our system has detected this request as unusual activity,” is not normally caused by model quota, region availability, RBAC, or deployment configuration. Recent Microsoft Q&A cases confirm that this error can indicate an account- or subscription-level risk or fraud-protection block that requires backend review.

Since you've confirmed that all models are failing with the same error, I would avoid repeatedly changing models, regions, quotas, or recreating the Foundry resource. Those actions generally won't clear this type of restriction.

There is also a very recent case where Microsoft reviewed the same 715-123420 condition and subsequently confirmed that the subscription had been unblocked from the backend.

I recommend opening an Azure Support request for Microsoft Foundry/model deployment and providing the error code, subscription ID, Foundry resource ID, UTC timestamp, and the Trace/Correlation/Service Request ID from a failed deployment. If you cannot open a technical support request, ask a Microsoft moderator here to assist with an internal escalation, as has been done for other cases with this exact error.

Also, I suggest removing the Subscription ID from the public post and providing it privately to Microsoft Support/moderators instead.

At this point, Microsoft needs to review the backend restriction rather than continue deployment troubleshooting.

Help make this community better for everyone: if this answer resolved your issue, please accept it or upvote it. If not, share more details in a comment so we can continue the discussion and find the right solution.