Title: 715-123420 blocking all model deployments on Azure OpenAI subscription

Gourav Salottra 20 Reputation points
2026-06-01T01:04:50.55+00:00

Subscription ID: 4289c1d1-43f4-4f42-904d-3405d11eb42f

Resource group: thrivarc

Resources: thrivarc (Azure OpenAI), thrivarc-foundry (AIServices)

Error: 715-123420 on ALL deployment attempts including gpt-5.4, DeepSeek-R1-0528

Existing deployments (gpt-4o, gpt-4o-mini) were created before the block.

No new deployments succeed. Quota shows available capacity.

Requesting RTFP review and subscription unblock.

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


Answer accepted by question author
Anshika Varshney 15,625 Reputation points Microsoft External Staff Moderator
2026-06-08T17:10:40.4233333+00:00

Hi @Gourav Salottra

Hope you are doing well.

We have received an update from the PG team that the issue has been rectified. Analysis and adjustments completed, please try again within 1-2hours.

Could you please check from your end and confirm whether the issue is now resolved?

If the updated response resolves your query, kindly consider clicking Upvote and Accept Answer so it can help others as well.

Looking forward to your response.

Thankyou!

Was this answer helpful?

1 person found this answer helpful.
0 comments No comments

1 additional answer

Sort by: Most helpful
  1. Jerald Felix 18,760 Reputation points Volunteer Moderator
    2026-06-01T01:47:16.8833333+00:00

    Hello Gourav Salottra,

    Greetings! Thanks for raising this question in the Q&A forum.

    The error code 715-123420 typically indicates that your Azure subscription has been flagged or temporarily blocked by Microsoft's automated abuse/fraud prevention system (also called the RTFP Real-Time Fraud Prevention system). This can happen even when quota appears available, and it blocks all new deployments at the subscription level. Your existing deployments (like gpt-4o and gpt-4o-mini) remain unaffected because they were created before the block was applied.

    Here's what you can do to get this resolved:

    Step 1: Raise an Azure Support Request

    1. Go to the Azure Portal at portal.azure.com and sign in.
    2. In the left menu, click on "Help + Support."
    3. Click "Create a support request."
    4. Set Issue type as "Technical" and select your subscription.
    5. Under Service, search for and select "Azure OpenAI."
    6. Describe the issue clearly mention error code 715-123420, that all new deployments are blocked, and that you are requesting an RTFP review and subscription unblock.
    7. Include your Subscription ID, Resource Group name (thrivarc), and the specific models you tried to deploy (gpt-5.4, DeepSeek-R1-0528).

    Step 2: Set Severity Appropriately

    1. Choose severity "B – Moderate" or higher if this is blocking your business operations.
    2. This ensures faster routing to the Azure backend team who can review and lift the RTFP flag.

    Step 3: While You Wait

    1. Try deploying in a different Azure region if you haven't already sometimes the block may be region-specific.
    2. Check the Azure Service Health dashboard at status.azure.com to rule out any ongoing platform-level issues.
    3. Verify that your subscription has no unpaid invoices or policy violations under "Cost Management + Billing," as these can sometimes trigger deployment blocks.

    Step 4: Follow Up if Needed

    1. If you don't hear back within 24–48 hours, follow up on the support ticket with your tracking number.
    2. You can also reach out via the Azure Community forums or your Microsoft account manager (if you're on an enterprise plan) to escalate.

    Unfortunately, RTFP unblocks cannot be done through the portal self-service they require manual review by the Microsoft support team, so raising a support ticket is the right and only path forward here.

    If this answer helps you kindly accept the answer which will help others who have similar questions.

    Best Regards,

    Jerald Felix.

    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.