Skip to main content

Azure OpenAI Configuration

Use Azure OpenAI for enterprise-grade AI with data residency, VNET integration, and SLA guarantees.

Step 1: Create an Azure OpenAI Resource​

  1. Log into portal.azure.com

  2. Search for "Azure OpenAI" in the top search bar

  3. Click "Create" → "Azure OpenAI"

    Azure OpenAI creation

  4. Configure:

    • Subscription: Your Azure subscription
    • Resource Group: Create new or select existing
    • Region: Choose a supported region (e.g., East US, West Europe)
    • Name: Unique name (e.g., roostgpt-openai-prod)
    • Pricing Tier: Standard S0

  5. Click Review + Create

Step 2: Deploy a Model​

  1. Open your Azure OpenAI resource
  2. Go to Model deployments in the left sidebar
  3. Click "Create new deployment"
  4. Configure:
    • Model: Select model (e.g., gpt-4o)
    • Deployment name: Your custom name (e.g., gpt-4o-deployment)
    • Model version: Select latest
    • Deployment type: Standard
  5. Click Create

Step 3: Get API Key and Endpoint​

  1. In your resource, navigate to "Keys and Endpoint"
  2. Copy KEY 1 (or KEY 2)
  3. Copy the Endpoint URL (format: https://your-resource.openai.azure.com/)
  4. Store both the key and endpoint securely together

Step 4: Add to RoostGPT​

Web UI (Connector)​

  1. Click Connectors in the top navigation bar → AI Model
  2. Select Azure OpenAI
  3. Enter:
    • API Key
    • Endpoint URL
    • Deployment name (the name you chose in Step 2)

CLI (.env file)​

AI_TYPE=azure_open_ai
AZURE_OPENAI_KEY=your_key
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_DEPLOYMENT_NAME=gpt-4o-deployment
ModelID (Deployment Name)Context WindowBest For
GPT-4o (Primary)your deployment name128KAll RoostGPT tasks
GPT-4o-mini (Cost-Effective)your deployment name128KHigh-volume, cost-sensitive tasks
GPT-5 (Advanced)your deployment name272KComplex reasoning, large codebases

Azure Advantages Over Direct OpenAI​

  • Data residency — data stays in your chosen Azure region
  • VNET integration — keep traffic inside your private network
  • Private endpoints — no public internet exposure
  • Managed identity — no API keys in code
  • SLA guarantees — enterprise uptime commitments
  • Azure Monitor — integrated observability and alerting