Wonder if you have looked into Azure Content Safety, it has a few ways you could configure the level of content safety. the content safety feature could not by turned off/disabled by yourself directly.

This content filtering system is powered by Azure AI Content Safety, and it works by running both the prompt input and completion output through an ensemble of classification models aimed at detecting and preventing the output of harmful content. https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/content-filtering

If you really find the Content Safety is causing unexpected result for your use case and you are a managed Azure customer, you can request de-activation of the content filtering in your subscription by the following online form: https://ncv.microsoft.com/uEfCgnITdR (Azure OpenAI Limited Access Review:  Modified Content Filtering)

https://learn.microsoft.com/en-us/answers/questions/2110040/how-can-i-disable-the-content-filter-in-azure-open