To compare the costs of large language models in Microsoft Foundry portal, use the Model leaderboard.
Microsoft documentation states that the model leaderboard helps compare models across quality, safety, estimated cost, and throughput. It also supports trade-off charts and side-by-side model comparison for features, performance, and estimated cost.

To call a deployed Azure OpenAI model from an application, the app must know the service endpoint and authenticate its request. Microsoft documentation states that Azure OpenAI supports API key authentication or Microsoft Entra ID authentication, and API key authentication requires including the API key in the request. Microsoft quickstart guidance also states that to successfully make a call against Azure OpenAI, you need an endpoint and a key.
The application does not need the model training dataset, the Foundry project display name, or exported playground session history to call the deployed model.

Azure AI Content Safety is a new Azure AI Service that can detect harmful user-generated and AI-generated content. This service is being integrated across MS products, including Azure OpenAI Service and Machine Learning prompt flow.
Reference:
https://ivanatilca.medium.com/testing-azure-ai-content-safety-ccd512f9b350