Model deployment blocked by error 715-123420 (Real-Time Fraud Protection)

Zachary Fincham 20 Reputation points
2026-06-25T17:49:53.4133333+00:00

Summary:

Anthropic Claude model deployments on my Azure AI Foundry (AIServices) resource are being blocked at the platform level with error 715-123420 ("An error occurred. Please reach out to support for additional assistance."). This code corresponds to a Real-Time Fraud Protection (RTFP) hold. I am requesting that the RTFP/security team review this subscription and lift the deployment block so model deployments can proceed.

This is NOT a configuration, quota, region, or permissions issue — I have already ruled those out:

  • I am Owner on the subscription and Global Administrator on the tenant.
  • Quota for the target model is approved and visible.
  • The model (claude-sonnet-4-6) is confirmed available in East US 2 via "az cognitiveservices model list".
  • I cleared the earlier InvalidModelProviderData error by submitting the required modelProviderData fields (organizationName, countryCode, industry) via the ARM REST API (api-version 2025-10-01-preview). The request now fails immediately with 715-123420, before model provisioning begins.
  • The deployment fails identically via both REST/CLI and the portal, confirming it is platform-side, not a UI or template issue.

I have the same issue for text-embedding-large and gpt-chat-latest as well

Azure OpenAI in Foundry Models
Answer accepted by question author
Anshika Varshney 15,625 Reputation points Microsoft External Staff Moderator
2026-06-25T18:16:23.12+00:00

Hello @Zachary Fincham

When this error occurs (Error Code 715-123420 or 555420), it indicates that Azure AI Foundry has blocked GPT model deployment due to a fraud signal, and the request requires review by the appropriate internal team.

To proceed with further investigation and escalation, could you please share the details requested in private message for the same.

Thankyou!

Was this answer helpful?

1 person found this answer helpful.
0 comments

1 additional answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Sina Salam 31,456 Reputation points Volunteer Moderator
    2026-07-13T15:59:19.7433333+00:00

    Hello Zachary Fincham,

    Welcome to the Microsoft Q&A and thank you for posting your questions here.

    I understand that your Model deployment blocked by error 715-123420 (Real-Time Fraud Protection).

    Microsoft internal backend has to review and remove the subscription/resource-level deployment block, then validate deployment of both an Azure-sold model and the Anthropic Claude model. Foundry model deployment requires a valid Foundry project/resource, Cognitive Services Contributor or equivalent permission, and supported model deployment settings; partner/community models also require Azure Marketplace subscription capability, while Azure-sold models do not. - https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models, and https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners

    I will suggest you reopen or continue the Azure support incident and explicitly request routing to Azure AI Foundry Product Group and the Fraud Protection / RTFP / subscription trust validation team.

    I hope this is helpful. Please! Do not hesitate to let me know if you have any other questions, steps or clarifications.

    Please do not close the thread by upvoting and accepting the answer if any part of it is helpful.

    Was this answer helpful?

    0 comments

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.