Azure OpenAI deployment blocked by unusual activity - Basic Support Plan prevents resolution

Parth Yadav 0 Reputation points
2026-11-05T05:21:57.5966667+00:00

Hello Microsoft Support Team,

I am developing an AI-powered Investor Intelligence Platform as a personal learning project using Microsoft Foundry, Azure OpenAI, FastAPI, and Azure Database for PostgreSQL.

I successfully created a Microsoft Foundry project and resource. However, when I attempted to deploy my first Azure OpenAI embedding model, the deployment failed immediately.

Error message:

"Failed to create deployment. Our system has detected this request as unusual activity for your account. If you are confident this is in error, please contact support."

Deployment details:

Service: Microsoft Foundry / Azure OpenAI

Model: text-embedding-3-small

Model version: 1

Region: Southeast Asia

Deployment type: Global Standard

Tokens per minute: 10,000

Subscription support plan: Basic

The Foundry project was created successfully, and the model appeared as available in the model catalog. The error occurred when I attempted to create the model deployment.

Support request issue:

Following the error message, I opened an Azure support request under Subscription Management.

Unfortunately, I received an automated email stating that the issue requires technical support, which is unavailable under my Basic Support Plan, and that I must purchase a paid support plan.

This leaves me unable to resolve the restriction through the standard support process.

I have also found Microsoft Q&A discussions reporting the same unusual-activity error and similar Basic Support Plan limitations.

Request for assistance:

Could a Microsoft moderator help determine whether my subscription or Foundry resource is subject to an account-security, risk-validation, or deployment-eligibility restriction?

Could this issue be escalated internally to the appropriate Azure OpenAI / Microsoft Foundry account-security or service-protection team?

Is there a way to request this account-level review without purchasing a paid technical support plan?

I am not requesting assistance with application code. I need Microsoft to investigate why my legitimate Azure subscription is being prevented from deploying an embedding model.

I can provide the following details privately to an authorized Microsoft representative:

Azure subscription ID

Tenant ID

Foundry resource ID

Previous Azure support request number

Deployment failure timestamp

Relevant diagnostic or correlation IDs, if available

Screenshots showing the deployment error

For security reasons, I have not included these identifiers publicly.

I would appreciate it if a Microsoft moderator could contact me through a private message and help initiate the appropriate review.

Thank you for your assistance.

Regards,
Parth

Microsoft Foundry
Microsoft Foundry

A unified Azure platform for creating and managing AI models, agents, and applications with built‑in enterprise security, monitoring, and governance

1 answer

Sort by: Most helpful
Most helpful Newest Oldest

  1. AI answer

    2026-11-05T05:23:16.9066667+00:00

    This error requires Microsoft-side review; with Basic support, the available no-cost route is to keep this Microsoft Q&A thread focused on error 715-123420 and ask a Microsoft moderator to escalate it for Azure OpenAI/Foundry product-group review.

    What to request in this thread

    Add a short comment or update containing only non-sensitive deployment details:

    • Exact error code: 715-123420, if shown in Azure portal → Monitor → Activity log
    • UTC failure timestamp
    • Model and version: text-embedding-3-small, version 1
    • Region: Southeast Asia
    • Deployment type: Global Standard
    • Requested TPM: 10,000
    • Whether every deployment fails or only this model
    • Existing support-request number, masked except for enough information to identify it privately
    • An explicit request for moderator escalation and private contact

    A suitable request is:

    Please escalate this thread for Azure OpenAI/Microsoft Foundry product-group review of deployment error 715-123420. The deployment is rejected immediately as unusual activity before provisioning. My Basic support request was closed because this requires technical investigation. I can provide the subscription ID, tenant ID, resource ID, UTC timestamp, support-request number, and correlation ID through Microsoft Q&A private messaging.

    This closely matches cases where the product group performed analysis and adjustments and asked customers to retry after one or two hours.^1^ Another matching case records a security-team collaboration and remediation of a temporary backend block.^2^

    Do not repeatedly retry deployments or create replacement resources while waiting. There is no documented client-side command that removes this restriction.

    What a moderator can—and cannot—do

    Microsoft Q&A moderators can escalate a thread into the moderator escalation queue, drawing attention from the wider moderator community.^3^ Matching Azure OpenAI cases have subsequently been reviewed by the product group, but that outcome does not establish a guaranteed escalation or response time for every Q&A post.

    Only a Microsoft moderator can initiate Q&A private messaging. If one does:

    1. Enable notifications under Microsoft Learn profile → Settings → Q&A preferences → Private message notifications.
    2. Open the blue private-message banner on this question.
    3. Send the requested subscription, tenant, resource, ticket, and diagnostic identifiers there.

    Subscription and tenant IDs, support ticket IDs, logs, and traces are permitted in private messages, but should not be posted publicly.^4^

    Basic support limitation

    Your Subscription Management request has already established the applicable boundary: Azure provides unlimited subscription-management assistance, but technical investigation requires an eligible support plan.^5^ Basic support does not include direct technical support by email, phone, or chat.^6^

    Reclassifying the same deployment restriction as billing, quota, or subscription management is unlikely to help because it requires service-side technical review. The Support REST API is not a workaround: creating technical tickets through that API requires Professional Direct, Premier, or Unified support, plus the appropriate subscription role.^7^

    If no moderator picks up the Q&A escalation, the documented fallback is to purchase an eligible technical support plan and create a Technical request against the affected Azure OpenAI/Foundry resource. Include all collected identifiers and state that the failure occurs before deployment provisioning.

    Keep these details private

    Do not publish:

    • Full subscription or tenant IDs
    • Full resource IDs if they expose identifiable naming
    • Access keys, API keys, tokens, or connection strings
    • Unredacted screenshots or traces containing credentials

    The information already posted publicly—model, region, deployment type, TPM, error text, and support-plan level—is sufficient for initial routing.

    References

    1. Error 715-123420 when deploying model in Foundry - Microsoft Q&A
    2. 715-123420: An error occurred. Please reach out to support for additional assistance. - Microsoft Q&A
    3. Escalate a question on Microsoft Q&A
    4. Private messages on Microsoft Q&A
    5. Create an Azure support request
    6. Compare support plans
    7. Azure Support REST API Reference
    AI-generated content may be incorrect. Read our transparency notes for more information.

    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.