[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3
SEQ. 4

Exploring the Model Catalog

🗂️ The Model Catalog 7 min 60 BASE XP

Your AI Model Marketplace

The Foundry Model Catalog is one of the platform's most powerful features — a curated marketplace of 1,800+ AI models from multiple providers, continuously updated with the latest releases.

Available Model Providers (April 2026)

ProviderKey ModelsStrengths
OpenAIGPT-5.4, GPT-5.2, GPT-4o, o4-mini, o3Frontier reasoning, multimodal, agentic tool-calling
Microsoft (MAI)MAI-Transcribe-1, MAI-Voice-1, MAI-Image-2, Phi-4First-party speech/vision, efficient on-device
MetaLlama 3.3 70B, Llama 3.2Open-source, customizable
MistralMistral Large, Ministral 3BEfficient, multilingual
AlibabaQwen3 32BMultilingual reasoning
Fireworks AIDeepSeek V3.2, Kimi K2.5Ultra-fast open-weight inference
CohereCommand R+, Embed v3Enterprise RAG, embeddings

Model Card Information

Every model has a Model Card containing benchmarks, license info, supported deployment types, pricing, and sample code.

The Model Router

Foundry includes a Model Router that can automatically select the most appropriate model for a given prompt or workflow. This means your application can dynamically choose between GPT-5.4 for complex reasoning or a smaller model like Phi-4 for simple tasks — optimizing cost and speed without code changes.

💡 Key Insight: The Model Catalog uses the Azure AI Model Inference API — a unified API that works across all models regardless of provider. Combined with the Model Router, you can swap or auto-select models without changing your code.
FOUNDRY VERIFICATION
QUERY 1 // 2
What is the Azure AI Model Inference API?
An API specific to OpenAI models
A unified API that works across all catalog models regardless of provider
A training API
A billing API
Watch: 139x Rust Speedup
Exploring the Model Catalog | The Model Catalog — Azure Foundry Academy