Azure AI Foundry
Use open-source and partner models hosted on Azure AI Foundry (formerly Azure AI Model Catalog) — access Phi, Llama, Mistral, Cohere, and more through Azure’s infrastructure with enterprise compliance. Azure AI Foundry exposes an OpenAI-compatible API, so Agentium connects to it using the standardopenai SDK pointed at your Azure endpoint.
Setup
- Install
- Environment
Uses the standard OpenAI SDK:
Factory
string
required
The model name as deployed on Azure AI Foundry (e.g.,
"Phi-4", "Meta-Llama-3.1-70B-Instruct").AzureFoundryConfig
Optional configuration. See Config below.
Supported Models
Microsoft Models
Meta Models
Mistral Models
Cohere Models
Discovering more models
Discovering more models
Browse the full model catalog at Azure AI Foundry. Available models depend on your Azure region and subscription.
Config
string
Azure API key. Falls back to
AZURE_API_KEY env var.string
required
Azure AI Foundry endpoint URL. Falls back to
AZURE_ENDPOINT env var. Format: https://<host>.<region>.models.ai.azure.comstring
API version. Falls back to
AZURE_API_VERSION env var.Authentication
Environment Variables (Recommended)
Explicit Config
Tool Calling
Tool calling is supported by models that implement function calling (Mistral Large, Llama 3.1, Cohere Command R/R+):Vision Models
Some Azure AI Foundry models support image input (e.g.,Phi-3.5-vision-instruct):
Full Example
Azure AI Foundry vs Other Providers
Use
azureFoundry() when you want open-source model quality with Azure enterprise compliance — without managing GPU infrastructure.
Environment Variables
Cross-References
- Azure OpenAI — OpenAI GPT/o-series models on Azure
- Ollama — Run the same open-source models locally
- AWS Bedrock — Similar model catalog on AWS
- Custom Provider — Build your own provider