Repository within Azure AI Foundry that lists and compares foundation models from OpenAI, Meta, Mistral, Cohere, and other providers, with benchmark metrics, cost, and capabilities, before deploying them as an endpoint.
In AI-901 it's used to justify choosing a model other than GPT (e.g., a smaller, cheaper model for simple tasks) based on cost, latency, and capability criteria, compared side by side in the catalog.
Azure AI Foundry model catalog is a concept that can show up on the exam. Check the full guide to see it in context.