Share via

Error 715-123420

Adiran Choudhury 5 Reputation points
2026-04-16T20:07:55.6+00:00

I have been trying to deploy an LLM via Foundry/Azure OpenAI (tried both) but keep receiving this error:

Failed to deploy model [model name]

715-123420: An error occurred. Please reach out to support for additional assistance.

I did some research and it seems like the action is triggering some sort of fraud protection and that's why I'm receiving the error code, however, I can't submit a support ticket for some reason. Would appreciate help with getting this unblocked ASAP.

I am on the Developer support plan which only allows tickets to be created with engineers through this Microsoft QnA platform. So I'd appreciate it if someone can help me get this ticket created ASAP.

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

2 answers

Sort by: Most helpful
Most helpful Newest Oldest
  1. Pavankumar Purilla 11,575 Reputation points Microsoft External Staff Moderator
    2026-05-10T09:58:10.16+00:00

    Hi Adiran Choudhury,
    Hope you are doing well. Sorry for the delayed response.

    We have received an update from the PG team that the issue has been rectified. Could you please check from your end and confirm whether the issue is now resolved?

    Looking forward to your response.

    Was this answer helpful?

  2. AI answer

    2026-04-16T20:08:09.96+00:00

    Error 715-123420 is not documented in the provided material, but the guidance available for similar deployment issues and for support escalation can still be applied.

    For Foundry Models and Azure OpenAI deployments, first validate that the deployment itself is not failing due to standard platform constraints before treating it purely as a fraud/eligibility issue:

    1. Check quota and region constraints
      • In the Foundry portal, verify that the selected model is available in the target region and that the subscription has sufficient Tokens-per-Minute (TPM) quota for that model. Deploying and running inference consume quota per region and per model.
      • If quota is exhausted, either:
        • Reallocate TPM from existing deployments of the same model, or
        • Submit a quota increase request using the quota increase form referenced in the documentation.
      • If deployment status shows Failed, confirm both model availability in the region and quota sufficiency.
    2. Validate subscription and marketplace eligibility
      • For third‑party/partner models, ensure the offer is available in the subscription’s billing country/region and that the subscription type is supported:
        • Some offers are not available in certain countries/regions.
        • CSP subscriptions cannot purchase some third‑party offerings.
      • If the error is tied to marketplace purchase eligibility or “offer not available” conditions, the documented resolution is to deploy using a subscription with billing in a supported country/region or to use first‑party models instead.
    3. Check for authorization/RBAC issues
      • When deploying via CLI or automation, ensure the identity used has the required roles on the Foundry resource (for example, Cognitive Services Contributor for deployment operations, and Cognitive Services OpenAI User for calling the model once deployed).
    4. When to escalate via support
      • The error text explicitly instructs to contact support. For deployment errors, quota issues, and urgent problems, the documented path is to open a support ticket in the Azure portal.
      • If the portal UI is blocking ticket creation due to plan constraints, the documented guidance for startups and similar programs is:
        • Use the Azure portal support request flow for error messages, quota requests, billing questions, and urgent issues whenever possible.
        • If that is not available, use Microsoft Q&A to describe the issue (including subscription ID, region, model SKU, and exact error) so a moderator or engineer can help route it or advise on next steps.

    Given that 715‑123420 is not a standard quota/region/RBAC code in the documentation and explicitly says to contact support, the next step is to:

    • Confirm quota and regional availability as above.
    • If those are correct and the error persists, use the Azure portal’s “Create a support request” flow under Help + support to open a ticket for this specific deployment error. If the Developer plan UI blocks that, continue working through Microsoft Q&A so a moderator can escalate, as is done for other severe/blocked scenarios in the provided examples.

    References:

    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.