Error 715-123420 blocks GPT model deployment - Basic plan has no support path for required review

Hello Aeolus Travel,

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

Error 715-123420 is not a quota, RBAC, or template issue. It is generated by Azure's Real-Time Fraud Protection (RTFP) system, which sits in front of the deployment pipeline for Azure AI Foundry / Azure OpenAI resources. When RTFP flags a subscription, it blocks new model deployments immediately, before the request ever reaches provisioning, which is exactly the pattern you are seeing (an existing deployment on the same resource still works, but the new gpt-5.3-codex deployment fails outright). This is a manual hold that has to be reviewed and cleared by Microsoft's internal Fraud Protection and Security team. There is no configuration change, region switch, redeploy, or resource recreation on your side that will clear it, so please avoid repeatedly deleting and recreating the resource, since that can make the activity pattern look worse rather than better.

Here is how to get it resolved:

Open a support request through the Azure portal, not the Basic support plan technical-ticket path. Go to Help + support > Create a support request. Choose issue type "Subscription management" or "Billing", not "Technical". Fraud/account-protection reviews are handled under subscription and billing support, which is available on every support plan including Basic, so you do not need to upgrade to a paid plan to get this looked at.

In the request, reference the RTFP block explicitly. State that you are hitting error 715-123420 on a model deployment in Azure AI Foundry, and that this requires review by the Fraud Protection and Security (RTFP) team, not standard technical troubleshooting.

Include the diagnostic details you already have. Provide:

• Subscription ID and tenant ID
• Resource group: aeolus-ai
• Resource: founders-0933-resource
• Correlation ID: 98d960a5-8282-4712-8941-1902bdce61b1
• UTC timestamp: 2026-08-13T20:38:41Z

The model and deployment type that failed (gpt-5.3-codex, GlobalStandard) and note that a prior deployment (gpt-5.6-sol) on the same resource succeeded, which supports this being a per-deployment fraud flag rather than a subscription-wide quota or policy issue.

If the portal flow does not let you file the ticket as Basic support, use the "Same question" or "Sign in to comment" option on similar threads here in Q&A and ask a moderator to help route an internal collaboration ticket to the RTFP team. Several other posters with this exact error code have had moderators do this successfully.

Once a ticket is opened, keep the resource and resource group as-is until you get a response, so the team reviewing the flag has a stable state to investigate.

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

Best Regards,

Jerald Felix.

Hello @Aeolus Travel ,

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

• Region availability for Foundry Models sold by Azure - Microsoft Foundry | Microsoft Learn
• Azure OpenAI in Microsoft Foundry Models Quotas and Limits - Microsoft Foundry | Microsoft Learn
• Azure resource providers and types - Azure Resource Manager | Microsoft Learn
• Overview of Azure Policy - Azure Policy | Microsoft Learn
• az cognitiveservices account deployment | Microsoft Learn
• Sponsorship Coverage for Microsoft Foundry Models | Microsoft Learn

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

Thank you