Skip to main content

​
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 RadarOS connects to it using the standard openai SDK pointed at your Azure endpoint.

​
Setup

Uses the standard OpenAI SDK:
npm install openai

​
Factory

import { azureFoundry } from "@radaros/core";

const model = azureFoundry("Phi-4");
​
modelId
string
required
The model name as deployed on Azure AI Foundry (e.g., "Phi-4", "Meta-Llama-3.1-70B-Instruct").
​
config
AzureFoundryConfig
Optional configuration. See Config below.

​
Supported Models

​
Microsoft Models

ModelDescription
Phi-4Latest Phi model. Strong reasoning for its size.
Phi-3.5-mini-instructFast, compact, good for edge scenarios.
Phi-3.5-vision-instructVision-capable Phi model.

​
Meta Models

ModelDescription
Meta-Llama-3.1-405B-InstructLargest open model. Exceptional capability.
Meta-Llama-3.1-70B-InstructStrong balance of size and performance.
Meta-Llama-3.1-8B-InstructFast, efficient, good for most tasks.

​
Mistral Models

ModelDescription
Mistral-largeHigh capability, strong reasoning.
Mistral-smallFast, cost-effective.
Mistral-NemoLatest Nemo model.

​
Cohere Models

ModelDescription
Cohere-command-r-plusStrong RAG and tool use.
Cohere-command-rFast, efficient.
Browse the full model catalog at Azure AI Foundry. Available models depend on your Azure region and subscription.

​
Config

​
apiKey
string
Azure API key. Falls back to AZURE_API_KEY env var.
​
endpoint
string
required
Azure AI Foundry endpoint URL. Falls back to AZURE_ENDPOINT env var. Format: https://<host>.<region>.models.ai.azure.com
​
apiVersion
string
API version. Falls back to AZURE_API_VERSION env var.

​
Authentication

export AZURE_API_KEY="..."
export AZURE_ENDPOINT="https://my-host.eastus.models.ai.azure.com"

const model = azureFoundry("Phi-4");

​
Explicit Config

const model = azureFoundry("Phi-4", {
  apiKey: "...",
  endpoint: "https://my-host.eastus.models.ai.azure.com",
});

​
Tool Calling

Tool calling is supported by models that implement function calling (Mistral Large, Llama 3.1, Cohere Command R/R+): 
import { Agent, azureFoundry, defineTool } from "@radaros/core";
import { z } from "zod";

const agent = new Agent({
  name: "foundry-assistant",
  model: azureFoundry("Mistral-large"),
  instructions: "You are a helpful assistant with tool access.",
  tools: [
    defineTool({
      name: "getStockPrice",
      description: "Get current stock price",
      parameters: z.object({ symbol: z.string() }),
      execute: async ({ symbol }) => `${symbol}: $185.42 (+2.3%)`,
    }),
  ],
});

const result = await agent.run("What's the current price of AAPL?");
console.log(result.text);
Not all Azure AI Foundry models support tool calling. Phi models and some smaller models may not support function calling. Test with your specific model.

​
Vision Models

Some Azure AI Foundry models support image input (e.g., Phi-3.5-vision-instruct): 
import { Agent, azureFoundry, type ContentPart } from "@radaros/core";
import { readFileSync } from "node:fs";

const agent = new Agent({
  name: "vision-agent",
  model: azureFoundry("Phi-3.5-vision-instruct"),
  instructions: "Describe images in detail.",
});

const imageData = readFileSync("photo.jpg").toString("base64");
const result = await agent.run([
  { type: "text", text: "What's in this image?" },
  { type: "image", data: imageData, mimeType: "image/jpeg" },
] as ContentPart[]);

​
Full Example

import { Agent, azureFoundry, CostTracker, defineTool } from "@radaros/core";
import { z } from "zod";

const costTracker = new CostTracker({
  pricing: {
    "Meta-Llama-3.1-70B-Instruct": { promptPer1k: 0.00268, completionPer1k: 0.00354 },
    "Mistral-large": { promptPer1k: 0.004, completionPer1k: 0.012 },
  },
});

const agent = new Agent({
  name: "research-agent",
  model: azureFoundry("Meta-Llama-3.1-70B-Instruct", {
    endpoint: "https://my-host.eastus.models.ai.azure.com",
  }),
  instructions: "You are a research assistant. Use tools to find information.",
  tools: [
    defineTool({
      name: "search",
      description: "Search for information",
      parameters: z.object({ query: z.string() }),
      execute: async ({ query }) => `Results for "${query}": ...`,
    }),
  ],
  costTracker,
  maxToolRoundtrips: 3,
});

const result = await agent.run("Research the latest trends in AI agent frameworks");
console.log(result.text);
console.log(`Cost: $${costTracker.getSummary().totalCost.toFixed(4)}`);

​
Azure AI Foundry vs Other Providers

Featureopenai()azureFoundry()ollama()
ModelsOpenAI onlyPhi, Llama, Mistral, CohereAny local model
AuthAPI keyAzure API keyNone
HostingOpenAI cloudAzure cloudLocal machine
CostPer-tokenPer-token (Azure pricing)Free (your hardware)
PrivacyOpenAI termsAzure data residencyFully local
ComplianceSOC2SOC2, HIPAA, GDPRN/A
GPU requiredNoNoYes (recommended)
Use azureFoundry() when you want open-source model quality with Azure enterprise compliance — without managing GPU infrastructure.

​
Environment Variables

VariableDescription
AZURE_API_KEYAzure AI Foundry API key
AZURE_ENDPOINTAzure AI Foundry endpoint URL
AZURE_API_VERSIONAPI version (optional)

​
Cross-References