Error 715-123420 blocks all Azure OpenAI model deployments across two separate subscriptions and a brand-new resource - requesting moderator help for a collaboration ticket

Filip B 0 Reputation points
2026-08-19T15:20:05.47+00:00

Every Azure OpenAI model deployment operation on our account fails with:

(715-123420) Our system has detected this request as unusual activity for your account.

This affects new deployments and capacity increases alike, on every model, in both Azure CLI and the portal. Every other Azure operation on the account works normally.

I have isolated it as far as I can from our side, and the result is why I am asking for moderator help rather than filing another case:

The block follows the tenant, not the subscription. I created a brand-new Azure OpenAI resource on a second, separate subscription. Resource creation succeeded (provisioningState: Succeeded). The very first deployment call against that brand-new resource failed with the identical 715-123420.

Also established:

  • Quota is not the constraint. OpenAI.GlobalStandard.gpt-5.4-nano shows 500 used against a limit of 675,000. The existing deployment is sized at 250 and cannot be scaled.
  • Both subscriptions are offer PayAsYouGo_2014-09-01. Billing is current, no failed payments.
  • Region: swedencentral.
  • We are on a Developer support plan.

We are a Finnish company running a public-sector employment pilot that begins on 1 September, and this blocks the production model configuration for it. A support request filed around 11 August has had no response.

Could a moderator please open a collaboration ticket, or route this to the team that handles account-level security and fraud reviews for Azure OpenAI (RTFP)?

I can provide subscription IDs, tenant ID, resource IDs, exact UTC timestamps and correlation IDs by private message.

Azure OpenAI in Foundry Models

2 answers

Sort by: Oldest
  1. Vinodh247-1375 44,476 Reputation points Volunteer Moderator
    2026-08-19T16:32:46.86+00:00

    based on the information provided, this does not appear to be a quota, billing, subscription, regional capacity, or deployment configuration issue.

    The key indicator is that the same 715-123420 error occurs:

    • Across two separate subscriptions
    • On a newly created Azure OpenAI resource
    • For both new deployments and scaling operations
    • Through both the Azure portal and Azure CLI
    • While resource creation continues to succeed

    Because the behavior follows the tenant rather than a specific subscription or resource, it suggests that the block may be related to an account-level review or restriction associated with Azure OpenAI services.

    Why further self-troubleshooting is unlikely to help?

    You've already verified several of the most common causes:

    • Quota is available (500 used of 675,000)
    • Billing is current
    • Resource provisioning succeeds
    • The issue reproduces on a newly created Azure OpenAI resource
    • Other Azure services continue to function normally

    Was this answer helpful?


  2. Karnam Venkata Rajeswari 5,255 Reputation points Microsoft External Staff Moderator
    2026-08-25T22:24:52.4433333+00:00

    Hello @Filip B ,

    Welcome to Microsoft Q&A .Thank you for reaching out to us.

    The current behavior suggests that the deployment request may be failing during an earlier validation stage before the model provisioning process begins. The error message itself does not expose the exact validation reason, so confirmation requires additional backend investigation.

    Possible areas that may require review include:

    • Subscription eligibility validation
    • Subscription-level authorization checks
    • Automated risk or trust validation controls
    • Model deployment access validation

    Regarding the request for an RTFP review, the available information does not conclusively confirm that an RTFP restriction is present. However, the observed pattern is consistent with scenarios where additional backend validation may be required to determine whether a subscription-level condition is preventing deployments from completing.

    The following checks can help rule out common deployment blockers before backend investigation.

    1. Confirming Model Availability Verify that the selected models are supported in the intended region and deployment type. Checks:
      • Confirm model availability for the selected Azure region.
      • Confirm that the selected deployment type (for example, Global Standard) is supported for the model.
    2. Validating Quota and Capacity Availability Confirm that sufficient quota is available for:
      • Subscription
      • Region
      • Selected model deployment
      Quota or capacity issues normally return more specific quota-related messages. However, validating quota helps eliminate standard deployment limitations.
    3. Verifying Resource Provider Registration Confirm that the required resource providers are registered and in a healthy state:
      • Microsoft.CognitiveServices
      • Microsoft.MachineLearningServices
      Expected status: Registered
    4. Reviewing Governance and Policy Restrictions Review Azure Policy assignments that may restrict:
      • AI model deployments
      • Allowed regions
      • Resource types
      • Deployment configurations
    5. Performing Additional Deployment Validation To determine whether the issue is limited to a specific deployment method or occurs at the service level:
      • Retry after a short interval to rule out temporary service behavior.
      • Attempt a deployment with a new deployment name to exclude deployment-specific inconsistencies.
      • Test deployment through Azure AI Foundry portal.
      • If possible, test through Azure CLI or ARM/Bicep to confirm whether the failure occurs at the service layer.

    As an additional verification , please note that

    For sponsored subscriptions, it may also be useful to confirm that the selected models appear under the appropriate model collection in Azure AI Foundry, as model eligibility and billing behavior can vary depending on the model source.

    The following references might be helpful , please check them out

    We have reached out to you on private messenger for further assistance

     

    Thank you

     

    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.