Unable to deploy gpt-5.5 mini models - fraud block

Chris LJ (Sealjay) 0 Reputation points MVP
2026-07-21T18:20:33.3233333+00:00

{ "error": { "code": "715-123420", "message": "Our system has detected this request as unusual activity for your account. If you are confident this is in error, please contact support." } }

Foundry Models
Foundry Models

A catalog of AI models in Microsoft Foundry that you can discover, compare, and deploy using Azure’s built‑in tools for evaluation, fine‑tuning, and inference


1 answer

Sort by: Most helpful
  1. Alex Burlachenko 24,870 Reputation points MVP Volunteer Moderator
    2026-07-23T09:03:13.4233333+00:00

    hi Chris LJ (Sealjay) & thx for sharing urs issue here at Q&A portal,

    Error 715-123420 indicates the request has been blocked by Microsoft's fraud/risk detection system rather than by the model deployment process itself.

    If this happens consistently when deploying gpt-5.5-mini and there are no quota, region, or permission errors, there's nothing you can change in the Foundry project to bypass it. This isn't a deployment configuration issue.

    I'd verify whether the same subscription can deploy other models, and whether the problem reproduces across different regions or Foundry projects. If only gpt-5.5-mini is affected, include that in the report.

    At this point, open an Azure AI Foundry support case and provide the subscription ID, tenant ID, project name, region, exact UTC timestamp, correlation/request ID (if available), and the full 715-123420 error. The engineering team will need to review the backend fraud evaluation and determine whether the block is a false positive or whether there's an account-level restriction that needs to be cleared.

    rgds,

    Alex

    &

    If my answer was helpful pls mark it and additional thx if u follow me at Q&A portal

    and at my blog https://ctrlaltdel.blog/

     

    Was this answer helpful?


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.