Manage Azure OpenAI Service quota

Deployment

PUT https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments/{deploymentName}?api-version=2023-05-01

Path parameters

Supported versions

• 2023-05-01 Swagger spec

Request body

This is only a subset of the available request body parameters. For the full list of the parameters, you can refer to the REST API reference documentation.

Example request

curl -X PUT https://management.azure.com/subscriptions/00000000-0000-0000-0000-000000000000/resourceGroups/resource-group-temp/providers/Microsoft.CognitiveServices/accounts/docs-openai-test-001/deployments/gpt-35-turbo-test-deployment?api-version=2023-05-01 \
  -H "Content-Type: application/json" \
  -H 'Authorization: Bearer YOUR_AUTH_TOKEN' \
  -d '{"sku":{"name":"Standard","capacity":10},"properties": {"model": {"format": "OpenAI","name": "gpt-35-turbo","version": "0613"}}}'

For more information, refer to the REST API reference documentation for usages and deployment.

Usage

To query your quota usage in a given region, for a specific subscription

GET https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/{location}/usages?api-version=2023-05-01

Path parameters

Supported versions

• 2023-05-01 Swagger spec

Example request

curl -X GET https://management.azure.com/subscriptions/00000000-0000-0000-0000-000000000000/providers/Microsoft.CognitiveServices/locations/eastus/usages?api-version=2023-05-01 \
  -H "Content-Type: application/json" \
  -H 'Authorization: Bearer YOUR_AUTH_TOKEN' 

Install the Azure CLI. Quota requires Azure CLI version 2.51.0. If you already have Azure CLI installed locally run az upgrade to update to the latest version.

To check which version of Azure CLI you are running use az version. Azure Cloud Shell is currently still running 2.50.0 so in the interim local installation of Azure CLI is required to take advantage of the latest Azure OpenAI features.

Deployment

az cognitiveservices account deployment create --model-format
                                               --model-name
                                               --model-version
                                               --name
                                               --resource-group
                                               [--capacity]
                                               [--deployment-name]
                                               [--scale-capacity]
                                               [--scale-settings-scale-type {Manual, Standard}]
                                               [--sku]

To sign into your local installation of the CLI, run the az login command:

az login

By setting sku-capacity to 10 in the command below this deployment will be set with a 10K TPM limit.

az cognitiveservices account deployment create -g test-resource-group -n test-resource-name --deployment-name test-deployment-name --model-name gpt-35-turbo --model-version "0613" --model-format OpenAI --sku-capacity 10 --sku-name "Standard"

Usage

To query your quota usage in a given region, for a specific subscription

az cognitiveservices usage list --location

Example

az cognitiveservices usage list -l eastus

This command runs in the context of the currently active subscription for Azure CLI. Use az-account-set --subscription to modify the active subscription.

For more details on az cognitiveservices account and az cognitivesservices usage consult the Azure CLI reference documentation

//
// This Azure Resource Manager template shows how to use the new schema introduced in the 2023-05-01 API version to 
// create deployments that set the model version and the TPM limits for standard deployments.
//
{
    "type": "Microsoft.CognitiveServices/accounts/deployments",
    "apiVersion": "2023-05-01",
    "name": "arm-je-aoai-test-resource/arm-je-std-deployment",    // Update reference to parent Azure OpenAI resource
    "dependsOn": [
        "[resourceId('Microsoft.CognitiveServices/accounts', 'arm-je-aoai-test-resource')]"  // Update reference to parent Azure OpenAI resource
    ],
    "sku": {
        "name": "Standard",      
        "capacity": 10            // The deployment will be created with a 10K TPM limit
    },
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": "gpt-35-turbo",
            "version": "0613"        // Version 0613 of gpt-35-turbo will be used
        }
    }
}

For more details, consult the full Azure Resource Manager reference documentation.

//
// This Bicep template shows how to use the new schema introduced in the 2023-05-01 API version to 
// create deployments that set the model version and the TPM limits for standard deployments.
//
resource arm_je_std_deployment 'Microsoft.CognitiveServices/accounts/deployments@2023-05-01' = {
  parent: arm_je_aoai_resource   // Replace this with a reference to the parent Azure OpenAI resource
  name: 'arm-je-std-deployment'
  sku: {
    name: 'Standard'            
    capacity: 10                 // The deployment will be created with a 10K TPM limit
  }
  properties: {
    model: {
      format: 'OpenAI'
      name: 'gpt-35-turbo'
      version: '0613'           // gpt-35-turbo version 0613 will be used
    }
  }
}

For more details consult the full Bicep reference documentation.

# This Terraform template shows how to use the new schema introduced in the 2023-05-01 API version to 
# create deployments that set the model version and the TPM limits for standard deployments.
# 
# The new schema is not yet available in the AzureRM provider (target v4.0), so this template uses the AzAPI
# provider, which provides a Terraform-compatible interface to the underlying ARM structures.
# 
# For more details on these providers:
#     AzureRM: https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs
#     AzAPI: https://registry.terraform.io/providers/azure/azapi/latest/docs
#

# 
terraform {
  required_providers {
    azapi   = { source  = "Azure/azapi" }
    azurerm = { source  = "hashicorp/azurerm" }
  }
}

provider "azapi" {
  # Insert auth info here as necessary
}

provider "azurerm" {
    # Insert auth info here as necessary  
    features {
    }
}

# 
# To create a complete example, AzureRM is used to create a new resource group and Azure OpenAI Resource
# 
resource "azurerm_resource_group" "TERRAFORM-AOAI-TEST-GROUP" {
  name     = "TERRAFORM-AOAI-TEST-GROUP"
  location = "canadaeast"
}

resource "azurerm_cognitive_account" "TERRAFORM-AOAI-TEST-ACCOUNT" {
  name                  = "terraform-aoai-test-account"
  location              = "canadaeast"
  resource_group_name   = azurerm_resource_group.TERRAFORM-AOAI-TEST-GROUP.name
  kind                  = "OpenAI"
  sku_name              = "S0"
  custom_subdomain_name = "terraform-test-account-"
  }


# 
# AzAPI is used to create the deployment so that the TPM limit and model versions can be set
#
resource "azapi_resource" "TERRAFORM-AOAI-STD-DEPLOYMENT" {
  type      = "Microsoft.CognitiveServices/accounts/deployments@2023-05-01"
  name      = "TERRAFORM-AOAI-STD-DEPLOYMENT"
  parent_id = azurerm_cognitive_account.TERRAFORM-AOAI-TEST-ACCOUNT.id

  body = jsonencode({
    sku = {                            # The sku object specifies the deployment type and limit in 2023-05-01
        name = "Standard",             
        capacity = 10                  # This deployment will be set with a 10K TPM limit
    },
    properties = {
        model = {
            format = "OpenAI",
            name = "gpt-35-turbo",
            version = "0613"           # Deploy gpt-35-turbo version 0613
        }
    }
  })
}

For more details consult the full Terraform reference documentation.