Before deploying the accelerator, ensure sufficient quota availability for the required AI models and Fabric capacity.
The default capacities match the deployment parameters in
infra/main.bicepparam.
az login
These match the modelDeploymentList in the Bicep parameters:
gpt-4.1-mini:40:GlobalStandard, text-embedding-3-large:40:Standard
eastus, eastus2, swedencentral, uksouth, westus, westus2, southcentralus, canadacentral, australiaeast, japaneast, norwayeast
The accelerator also deploys a Microsoft Fabric F8 capacity. Pass --check-fabric (bash) or -CheckFabric (PowerShell) to verify Fabric SKU availability.
- No parameters passed → Default models and capacities will be checked in default regions.
- Only model(s) provided → The script will check for those models in the default regions.
- Only region(s) provided → The script will check default models in the specified regions.
- Both models and regions provided → The script will check those models in the specified regions.
--verbosepassed → Enables detailed logging output for debugging and traceability.--check-fabricpassed → Also checks Microsoft Fabric capacity availability.
Use the --models, --regions, --verbose, and --check-fabric options for parameter handling:
✔️ Run without parameters to check default models & regions:
./quota_check.sh✔️ Enable verbose logging:
./quota_check.sh --verbose✔️ Check specific model(s) in default regions:
./quota_check.sh --models gpt-4.1-mini:40:GlobalStandard,text-embedding-3-large:40:Standard✔️ Check default models in specific region(s):
./quota_check.sh --regions eastus,westus✔️ All parameters combined:
./quota_check.sh --models gpt-4.1-mini:40 --regions eastus,westus --verbose✔️ Also check Fabric capacity availability:
./quota_check.sh --check-fabric --verboseUse the -Models, -Regions, -Verbose, and -CheckFabric parameters:
✔️ Run without parameters:
.\quota_check.ps1✔️ Check specific model(s):
.\quota_check.ps1 -Models "gpt-4.1-mini:40:GlobalStandard,text-embedding-3-large:40:Standard"✔️ Check specific region(s):
.\quota_check.ps1 -Regions "eastus,westus2"✔️ All parameters combined:
.\quota_check.ps1 -Models "gpt-4.1-mini:40" -Regions "eastus,westus" -CheckFabric -VerboseThe final table lists regions with available quota. You can select any of these regions for deployment.
╔══════════════════════════════════════════════════════════════╗
║ QUOTA CHECK SUMMARY ║
╚══════════════════════════════════════════════════════════════╝
Region gpt-4.1-mini text-embedding-3-large Status
──────────────────────────────────────────────────────────────────────────────────────────
eastus ✅ 200/240 (need 40) ✅ 120/200 (need 40) ✅ PASS
eastus2 ❌ 10/240 (need 40) ✅ 50/200 (need 40) ❌ FAIL
swedencentral ✅ 100/240 (need 40) ✅ 80/200 (need 40) ✅ PASS
-
Navigate to the Azure Portal.
-
Click on Azure Cloud Shell in the top right navigation menu.
-
Run the appropriate command based on your requirement:
To check quota for the deployment
curl -L -o quota_check.sh "https://raw.githubusercontent.com/microsoft/Deploy-Your-AI-Application-In-Production/main/scripts/quota_check.sh" chmod +x quota_check.sh ./quota_check.sh- Refer to Input Formats — Bash for detailed commands.
- Open the terminal in VS Code or Codespaces.
- Use a terminal that can run bash.

- Navigate to the
scriptsfolder and make the script executable:cd scripts chmod +x quota_check.sh - Run the script:
./quota_check.sh
- Refer to Input Formats — Bash for detailed commands.
- Open a PowerShell terminal in VS Code.
- Navigate to the
scriptsfolder:cd scripts
- Run the script:
.\quota_check.ps1
- Refer to Input Formats — PowerShell for detailed commands.