An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
Hello Gael Gomes
This error is consistent with an Azure OpenAI account/subscription-level security or risk-protection restriction, rather than a problem with your model deployment configuration.
Here's what I recommend:
- Stop deleting and recreating resources. A new Foundry resource does not necessarily clear an account-level restriction.
- Go to Azure Portal → Help + support → Create a support request and select Billing / Subscription management, describing the issue as an account restriction affecting Azure OpenAI deployments. Billing and subscription support is available without purchasing a technical support plan.
- If the request is rejected or redirected to paid technical support, ask a Microsoft Q&A moderator to facilitate a private escalation to the Azure OpenAI account-protection team. Similar cases have received private Microsoft staff follow-up.
Include the exact error, model names, region, UTC timestamp, and request/correlation IDs. Provide subscription and resource IDs privately.
Also mention the previous temporary content-policy block. It may be relevant to the investigation, although we cannot confirm that it caused the new deployment restriction.
This requires Microsoft-side review if the restriction is confirmed. Changing models, recreating resources, or increasing quota is unlikely to resolve it.
Official references: