Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Bicep resource definition
The workspaces/inferencePools/endpoints resource type can be deployed with operations that target:
For a list of changed properties in each API version, see change log.
Resource format
To create a Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints resource, add the following Bicep to your template.
resource symbolicname 'Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints@2025-07-01-preview' = {
parent: resourceSymbolicName
identity: {
type: 'string'
userAssignedIdentities: {
{customized property}: {}
}
}
kind: 'string'
location: 'string'
name: 'string'
properties: {
authMode: 'string'
description: 'string'
groupName: 'string'
properties: [
{
key: 'string'
value: 'string'
}
]
requestConfiguration: {
maxConcurrentRequestsPerInstance: int
requestTimeout: 'string'
}
}
sku: {
capacity: int
family: 'string'
name: 'string'
size: 'string'
tier: 'string'
}
tags: {
{customized property}: 'string'
}
}
Property Values
Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints
| Name | Description | Value |
|---|---|---|
| identity | Managed service identity (system assigned and/or user assigned identities) | ManagedServiceIdentity |
| kind | Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. | string |
| location | The geo-location where the resource lives | string (required) |
| name | The resource name | string Constraints: Pattern = ^[a-zA-Z0-9][a-zA-Z0-9\-_]{0,254}$ (required) |
| parent | In Bicep, you can specify the parent resource for a child resource. You only need to add this property when the child resource is declared outside of the parent resource. For more information, see Child resource outside parent resource. |
Symbolic name for resource of type: workspaces/inferencePools |
| properties | [Required] Additional attributes of the entity. | InferenceEndpointProperties (required) |
| sku | Sku details required for ARM contract for Autoscaling. | Sku |
| tags | Resource tags | Dictionary of tag names and values. See Tags in templates |
InferenceEndpointProperties
| Name | Description | Value |
|---|---|---|
| authMode | [Required] Authentication mode for the endpoint. | 'AAD' (required) |
| description | Description of the resource. | string |
| groupName | [Required] Group within the same pool with which this endpoint needs to be associated with. | string Constraints: Min length = 1 Pattern = [a-zA-Z0-9_] (required) |
| properties | Property dictionary. Properties can be added, but not removed or altered. | StringKeyValuePair[] |
| requestConfiguration | RequestConfiguration for endpoint. | RequestConfiguration |
ManagedServiceIdentity
| Name | Description | Value |
|---|---|---|
| type | Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). | 'None' 'SystemAssigned' 'SystemAssigned,UserAssigned' 'UserAssigned' (required) |
| userAssignedIdentities | The set of user assigned identities associated with the resource. The userAssignedIdentities dictionary keys will be ARM resource ids in the form: '/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.ManagedIdentity/userAssignedIdentities/{identityName}. The dictionary values can be empty objects ({}) in requests. | UserAssignedIdentities |
RequestConfiguration
| Name | Description | Value |
|---|---|---|
| maxConcurrentRequestsPerInstance | The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. | int |
| requestTimeout | The scoring timeout in ISO 8601 format. Defaults to 5000ms. |
string |
Sku
| Name | Description | Value |
|---|---|---|
| capacity | If the SKU supports scale out/in then the capacity integer should be included. If scale out/in is not possible for the resource this may be omitted. | int |
| family | If the service has different generations of hardware, for the same SKU, then that can be captured here. | string |
| name | The name of the SKU. Ex - P3. It is typically a letter+number code | string (required) |
| size | The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. | string |
| tier | This field is required to be implemented by the Resource Provider if the service has more than one tier, but is not required on a PUT. | 'Basic' 'Free' 'Premium' 'Standard' |
StringKeyValuePair
| Name | Description | Value |
|---|---|---|
| key | string | |
| value | string |
TrackedResourceTags
| Name | Description | Value |
|---|
UserAssignedIdentities
| Name | Description | Value |
|---|
UserAssignedIdentity
| Name | Description | Value |
|---|
ARM template resource definition
The workspaces/inferencePools/endpoints resource type can be deployed with operations that target:
For a list of changed properties in each API version, see change log.
Resource format
To create a Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints resource, add the following JSON to your template.
{
"type": "Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints",
"apiVersion": "2025-07-01-preview",
"name": "string",
"identity": {
"type": "string",
"userAssignedIdentities": {
"{customized property}": {
}
}
},
"kind": "string",
"location": "string",
"properties": {
"authMode": "string",
"description": "string",
"groupName": "string",
"properties": [
{
"key": "string",
"value": "string"
}
],
"requestConfiguration": {
"maxConcurrentRequestsPerInstance": "int",
"requestTimeout": "string"
}
},
"sku": {
"capacity": "int",
"family": "string",
"name": "string",
"size": "string",
"tier": "string"
},
"tags": {
"{customized property}": "string"
}
}
Property Values
Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints
| Name | Description | Value |
|---|---|---|
| apiVersion | The api version | '2025-07-01-preview' |
| identity | Managed service identity (system assigned and/or user assigned identities) | ManagedServiceIdentity |
| kind | Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. | string |
| location | The geo-location where the resource lives | string (required) |
| name | The resource name | string Constraints: Pattern = ^[a-zA-Z0-9][a-zA-Z0-9\-_]{0,254}$ (required) |
| properties | [Required] Additional attributes of the entity. | InferenceEndpointProperties (required) |
| sku | Sku details required for ARM contract for Autoscaling. | Sku |
| tags | Resource tags | Dictionary of tag names and values. See Tags in templates |
| type | The resource type | 'Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints' |
InferenceEndpointProperties
| Name | Description | Value |
|---|---|---|
| authMode | [Required] Authentication mode for the endpoint. | 'AAD' (required) |
| description | Description of the resource. | string |
| groupName | [Required] Group within the same pool with which this endpoint needs to be associated with. | string Constraints: Min length = 1 Pattern = [a-zA-Z0-9_] (required) |
| properties | Property dictionary. Properties can be added, but not removed or altered. | StringKeyValuePair[] |
| requestConfiguration | RequestConfiguration for endpoint. | RequestConfiguration |
ManagedServiceIdentity
| Name | Description | Value |
|---|---|---|
| type | Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). | 'None' 'SystemAssigned' 'SystemAssigned,UserAssigned' 'UserAssigned' (required) |
| userAssignedIdentities | The set of user assigned identities associated with the resource. The userAssignedIdentities dictionary keys will be ARM resource ids in the form: '/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.ManagedIdentity/userAssignedIdentities/{identityName}. The dictionary values can be empty objects ({}) in requests. | UserAssignedIdentities |
RequestConfiguration
| Name | Description | Value |
|---|---|---|
| maxConcurrentRequestsPerInstance | The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. | int |
| requestTimeout | The scoring timeout in ISO 8601 format. Defaults to 5000ms. |
string |
Sku
| Name | Description | Value |
|---|---|---|
| capacity | If the SKU supports scale out/in then the capacity integer should be included. If scale out/in is not possible for the resource this may be omitted. | int |
| family | If the service has different generations of hardware, for the same SKU, then that can be captured here. | string |
| name | The name of the SKU. Ex - P3. It is typically a letter+number code | string (required) |
| size | The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. | string |
| tier | This field is required to be implemented by the Resource Provider if the service has more than one tier, but is not required on a PUT. | 'Basic' 'Free' 'Premium' 'Standard' |
StringKeyValuePair
| Name | Description | Value |
|---|---|---|
| key | string | |
| value | string |
TrackedResourceTags
| Name | Description | Value |
|---|
UserAssignedIdentities
| Name | Description | Value |
|---|
UserAssignedIdentity
| Name | Description | Value |
|---|
Usage Examples
Terraform (AzAPI provider) resource definition
The workspaces/inferencePools/endpoints resource type can be deployed with operations that target:
For a list of changed properties in each API version, see change log.
Resource format
To create a Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints resource, add the following Terraform to your template.
resource "azapi_resource" "symbolicname" {
type = "Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints@2025-07-01-preview"
name = "string"
parent_id = "string"
identity {
type = "string"
identity_ids = [
"string"
]
}
location = "string"
tags = {
{customized property} = "string"
}
body = {
kind = "string"
properties = {
authMode = "string"
description = "string"
groupName = "string"
properties = [
{
key = "string"
value = "string"
}
]
requestConfiguration = {
maxConcurrentRequestsPerInstance = int
requestTimeout = "string"
}
}
sku = {
capacity = int
family = "string"
name = "string"
size = "string"
tier = "string"
}
}
}
Property Values
Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints
| Name | Description | Value |
|---|---|---|
| identity | Managed service identity (system assigned and/or user assigned identities) | ManagedServiceIdentity |
| kind | Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. | string |
| location | The geo-location where the resource lives | string (required) |
| name | The resource name | string Constraints: Pattern = ^[a-zA-Z0-9][a-zA-Z0-9\-_]{0,254}$ (required) |
| parent_id | The ID of the resource that is the parent for this resource. | ID for resource of type: workspaces/inferencePools |
| properties | [Required] Additional attributes of the entity. | InferenceEndpointProperties (required) |
| sku | Sku details required for ARM contract for Autoscaling. | Sku |
| tags | Resource tags | Dictionary of tag names and values. |
| type | The resource type | "Microsoft.MachineLearningServices/workspaces/inferencePools/endpoints@2025-07-01-preview" |
InferenceEndpointProperties
| Name | Description | Value |
|---|---|---|
| authMode | [Required] Authentication mode for the endpoint. | 'AAD' (required) |
| description | Description of the resource. | string |
| groupName | [Required] Group within the same pool with which this endpoint needs to be associated with. | string Constraints: Min length = 1 Pattern = [a-zA-Z0-9_] (required) |
| properties | Property dictionary. Properties can be added, but not removed or altered. | StringKeyValuePair[] |
| requestConfiguration | RequestConfiguration for endpoint. | RequestConfiguration |
ManagedServiceIdentity
| Name | Description | Value |
|---|---|---|
| type | Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). | 'None' 'SystemAssigned' 'SystemAssigned,UserAssigned' 'UserAssigned' (required) |
| userAssignedIdentities | The set of user assigned identities associated with the resource. The userAssignedIdentities dictionary keys will be ARM resource ids in the form: '/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.ManagedIdentity/userAssignedIdentities/{identityName}. The dictionary values can be empty objects ({}) in requests. | UserAssignedIdentities |
RequestConfiguration
| Name | Description | Value |
|---|---|---|
| maxConcurrentRequestsPerInstance | The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. | int |
| requestTimeout | The scoring timeout in ISO 8601 format. Defaults to 5000ms. |
string |
Sku
| Name | Description | Value |
|---|---|---|
| capacity | If the SKU supports scale out/in then the capacity integer should be included. If scale out/in is not possible for the resource this may be omitted. | int |
| family | If the service has different generations of hardware, for the same SKU, then that can be captured here. | string |
| name | The name of the SKU. Ex - P3. It is typically a letter+number code | string (required) |
| size | The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. | string |
| tier | This field is required to be implemented by the Resource Provider if the service has more than one tier, but is not required on a PUT. | 'Basic' 'Free' 'Premium' 'Standard' |
StringKeyValuePair
| Name | Description | Value |
|---|---|---|
| key | string | |
| value | string |
TrackedResourceTags
| Name | Description | Value |
|---|
UserAssignedIdentities
| Name | Description | Value |
|---|
UserAssignedIdentity
| Name | Description | Value |
|---|