Copyright (c) 2026 MindMesh Academy. All rights reserved. This content is proprietary and may not be reproduced or distributed without permission.
6.2.3. Azure AI Foundry Model Catalog
The Model Catalog provides access to thousands of AI models from multiple providers.
What the catalog includes:
- OpenAI models (GPT-4, DALL-E, etc.)
- Open-source models (Llama, Mistral, etc.)
- Microsoft models
- Partner models
Why use the Model Catalog:
- Compare models for your use case
- Benchmark performance
- Choose the right model for cost/capability tradeoff
- Access both proprietary and open-source options
Model categories:
| Category | Examples | Best For |
|---|---|---|
| Foundation models | GPT-4, Llama | General-purpose tasks |
| Task-specific models | DALL-E, Whisper | Specialized capabilities |
| Fine-tuned models | Custom trained | Domain-specific needs |
| Embedding models | Ada, BERT | Search and similarity |
Model selection considerations:
- Cost: Larger models cost more per token
- Latency: Smaller models respond faster
- Capability: More parameters = more capability (generally)
- Licensing: Open-source vs proprietary restrictions
⚠️ Exam Tip: The Model Catalog is for DISCOVERY and COMPARISON. Azure OpenAI Service is for DEPLOYMENT. Use the catalog to find the right model, then deploy via the appropriate service.
Written byAlvin Varughese
Founder•15 professional certifications