deployments

Creates, updates, deletes, gets or lists a deployments resource.

Overview

Name	deployments
Type	Resource
Id	azure.cognitive_services.deployments

Fields

The following fields are returned by SELECT queries:

get

Name	Datatype	Description
id	string	Fully qualified resource ID for the resource. Ex - /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/{resourceProviderNamespace}/{resourceType}/{resourceName}.
name	string	The name of the resource.
callRateLimit	object	The call rate limit Cognitive Services account.
capabilities	object	The capabilities.
capacitySettings	object	Internal use only.
currentCapacity	integer	The current capacity.
deploymentState	string	The state of the deployment. Controls whether the deployment is accepting inference requests. Use 'Running' for active deployments that process requests, or 'Paused' to temporarily stop inference while preserving the deployment configuration. Known values are: "Running" and "Paused". (Running, Paused)
dynamicThrottlingEnabled	boolean	If the dynamic throttling is enabled.
etag	string	Resource Etag.
model	object	Properties of Cognitive Services account deployment model.
parentDeploymentName	string	The name of parent deployment.
provisioningState	string	Gets the status of the resource at the time the operation was called. Known values are: "Accepted", "Creating", "Deleting", "Moving", "Failed", "Succeeded", "Disabled", and "Canceled". (Accepted, Creating, Deleting, Moving, Failed, Succeeded, Disabled, Canceled)
raiPolicyName	string	The name of RAI policy.
rateLimits	array	:vartype rate_limits: list[~azure.mgmt.cognitiveservices.models.ThrottlingRule]
routing	object	Routing configuration for the model-router deployment. This property is only applicable when the deployed model is 'model-router' version 2025-11-18 or later. Allows you to select the models subset for routing and the routing mode (balanced, quality, cost) for routing across all supported models or the model subset.
scaleSettings	object	Properties of Cognitive Services account deployment model. (Deprecated, please use Deployment.sku instead.).
serviceTier	string	The service tier for the deployment. Determines the pricing and performance level for request processing. Use 'Default' for standard pricing or 'Priority' for higher-priority processing with premium pricing. Note: Pause operations are only supported on Standard, DataZoneStandard, and GlobalStandard SKUs. Known values are: "Default" and "Priority". (Default, Priority)
sku	object	The resource model definition representing SKU.
speculativeDecoding	object	Speculative decoding settings for the deployment. This configuration applies to Fireworks model formats.
spilloverDeploymentName	string	Specifies the deployment name that should serve requests when the request would have otherwise been throttled due to reaching current deployment throughput limit.
systemData	object	Azure Resource Manager metadata containing createdBy and modifiedBy information.
tags	object	Resource tags.
type	string	The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts".
versionUpgradeOption	string	Deployment model version upgrade option. Known values are: "OnceNewDefaultVersionAvailable", "OnceCurrentVersionExpired", and "NoAutoUpgrade". (OnceNewDefaultVersionAvailable, OnceCurrentVersionExpired, NoAutoUpgrade)

list

Name	Datatype	Description
id	string	Fully qualified resource ID for the resource. Ex - /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/{resourceProviderNamespace}/{resourceType}/{resourceName}.
name	string	The name of the resource.
callRateLimit	object	The call rate limit Cognitive Services account.
capabilities	object	The capabilities.
capacitySettings	object	Internal use only.
currentCapacity	integer	The current capacity.
deploymentState	string	The state of the deployment. Controls whether the deployment is accepting inference requests. Use 'Running' for active deployments that process requests, or 'Paused' to temporarily stop inference while preserving the deployment configuration. Known values are: "Running" and "Paused". (Running, Paused)
dynamicThrottlingEnabled	boolean	If the dynamic throttling is enabled.
etag	string	Resource Etag.
model	object	Properties of Cognitive Services account deployment model.
parentDeploymentName	string	The name of parent deployment.
provisioningState	string	Gets the status of the resource at the time the operation was called. Known values are: "Accepted", "Creating", "Deleting", "Moving", "Failed", "Succeeded", "Disabled", and "Canceled". (Accepted, Creating, Deleting, Moving, Failed, Succeeded, Disabled, Canceled)
raiPolicyName	string	The name of RAI policy.
rateLimits	array	:vartype rate_limits: list[~azure.mgmt.cognitiveservices.models.ThrottlingRule]
routing	object	Routing configuration for the model-router deployment. This property is only applicable when the deployed model is 'model-router' version 2025-11-18 or later. Allows you to select the models subset for routing and the routing mode (balanced, quality, cost) for routing across all supported models or the model subset.
scaleSettings	object	Properties of Cognitive Services account deployment model. (Deprecated, please use Deployment.sku instead.).
serviceTier	string	The service tier for the deployment. Determines the pricing and performance level for request processing. Use 'Default' for standard pricing or 'Priority' for higher-priority processing with premium pricing. Note: Pause operations are only supported on Standard, DataZoneStandard, and GlobalStandard SKUs. Known values are: "Default" and "Priority". (Default, Priority)
sku	object	The resource model definition representing SKU.
speculativeDecoding	object	Speculative decoding settings for the deployment. This configuration applies to Fireworks model formats.
spilloverDeploymentName	string	Specifies the deployment name that should serve requests when the request would have otherwise been throttled due to reaching current deployment throughput limit.
systemData	object	Azure Resource Manager metadata containing createdBy and modifiedBy information.
tags	object	Resource tags.
type	string	The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts".
versionUpgradeOption	string	Deployment model version upgrade option. Known values are: "OnceNewDefaultVersionAvailable", "OnceCurrentVersionExpired", and "NoAutoUpgrade". (OnceNewDefaultVersionAvailable, OnceCurrentVersionExpired, NoAutoUpgrade)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	resource_group_name, account_name, deployment_name, subscription_id		Gets the specified deployments associated with the Cognitive Services account.
list	select	resource_group_name, account_name, subscription_id		Gets the deployments associated with the Cognitive Services account.
create_or_update	insert	resource_group_name, account_name, deployment_name, subscription_id		Update the state of specified deployments associated with the Cognitive Services account.
update	update	resource_group_name, account_name, deployment_name, subscription_id		Update specified deployments associated with the Cognitive Services account.
create_or_update	replace	resource_group_name, account_name, deployment_name, subscription_id		Update the state of specified deployments associated with the Cognitive Services account.
delete	delete	resource_group_name, account_name, deployment_name, subscription_id		Deletes the specified deployment associated with the Cognitive Services account.
list_skus	exec	resource_group_name, account_name, deployment_name, subscription_id		Lists the specified deployments skus associated with the Cognitive Services account.
pause	exec	resource_group_name, account_name, deployment_name, subscription_id		Pause a deployment. Pauses inferencing on a deployment by setting the deploymentState to 'Paused' (see #/definitions/DeploymentProperties/properties/deploymentState). Only Standard, DataZoneStandard, and GlobalStandard SKUs support this operation. Inference requests to the paused deployment endpoint will receive HTTP 423 (Locked). This operation is idempotent.
resume	exec	resource_group_name, account_name, deployment_name, subscription_id		Resume a deployment. Resumes inferencing on a previously paused deployment by setting the deploymentState to 'Running' (see #/definitions/DeploymentProperties/properties/deploymentState). This operation is idempotent and can be safely called on already running deployments.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
account_name	string	The name of Cognitive Services account. Required.
deployment_name	string	The name of the deployment associated with the Cognitive Services Account. Required.
resource_group_name	string	The name of the resource group. The name is case insensitive. Required.
subscription_id	string

SELECT examples

get

Gets the specified deployments associated with the Cognitive Services account.

SELECT
id,
name,
callRateLimit,
capabilities,
capacitySettings,
currentCapacity,
deploymentState,
dynamicThrottlingEnabled,
etag,
model,
parentDeploymentName,
provisioningState,
raiPolicyName,
rateLimits,
routing,
scaleSettings,
serviceTier,
sku,
speculativeDecoding,
spilloverDeploymentName,
systemData,
tags,
type,
versionUpgradeOption
FROM azure.cognitive_services.deployments
WHERE resource_group_name = '{{ resource_group_name }}' -- required
AND account_name = '{{ account_name }}' -- required
AND deployment_name = '{{ deployment_name }}' -- required
AND subscription_id = '{{ subscription_id }}' -- required
;

list

Gets the deployments associated with the Cognitive Services account.

SELECT
id,
name,
callRateLimit,
capabilities,
capacitySettings,
currentCapacity,
deploymentState,
dynamicThrottlingEnabled,
etag,
model,
parentDeploymentName,
provisioningState,
raiPolicyName,
rateLimits,
routing,
scaleSettings,
serviceTier,
sku,
speculativeDecoding,
spilloverDeploymentName,
systemData,
tags,
type,
versionUpgradeOption
FROM azure.cognitive_services.deployments
WHERE resource_group_name = '{{ resource_group_name }}' -- required
AND account_name = '{{ account_name }}' -- required
AND subscription_id = '{{ subscription_id }}' -- required
;

INSERT examples

create_or_update

Update the state of specified deployments associated with the Cognitive Services account.

INSERT INTO azure.cognitive_services.deployments (
properties,
sku,
tags,
resource_group_name,
account_name,
deployment_name,
subscription_id
)
SELECT 
'{{ properties }}',
'{{ sku }}',
'{{ tags }}',
'{{ resource_group_name }}',
'{{ account_name }}',
'{{ deployment_name }}',
'{{ subscription_id }}'
RETURNING
id,
name,
etag,
properties,
sku,
systemData,
tags,
type
;

Manifest

# Description fields are for documentation purposes
- name: deployments
props:
  - name: resource_group_name
    value: "{{ resource_group_name }}"
    description: Required parameter for the deployments resource.
  - name: account_name
    value: "{{ account_name }}"
    description: Required parameter for the deployments resource.
  - name: deployment_name
    value: "{{ deployment_name }}"
    description: Required parameter for the deployments resource.
  - name: subscription_id
    value: "{{ subscription_id }}"
    description: Required parameter for the deployments resource.
  - name: properties
    description: |
      Properties of Cognitive Services account deployment.
    value:
      provisioningState: "{{ provisioningState }}"
      model:
        publisher: "{{ publisher }}"
        format: "{{ format }}"
        name: "{{ name }}"
        version: "{{ version }}"
        source: "{{ source }}"
        sourceAccount: "{{ sourceAccount }}"
        callRateLimit:
          count: {{ count }}
          renewalPeriod: {{ renewalPeriod }}
          rules:
            - key: "{{ key }}"
              renewalPeriod: {{ renewalPeriod }}
              count: {{ count }}
              minCount: {{ minCount }}
              dynamicThrottlingEnabled: {{ dynamicThrottlingEnabled }}
              matchPatterns: "{{ matchPatterns }}"
      speculativeDecoding:
        draftModel:
          publisher: "{{ publisher }}"
          format: "{{ format }}"
          name: "{{ name }}"
          version: "{{ version }}"
          source: "{{ source }}"
          sourceAccount: "{{ sourceAccount }}"
          callRateLimit:
            count: {{ count }}
            renewalPeriod: {{ renewalPeriod }}
            rules:
              - key: "{{ key }}"
                renewalPeriod: {{ renewalPeriod }}
                count: {{ count }}
                minCount: {{ minCount }}
                dynamicThrottlingEnabled: {{ dynamicThrottlingEnabled }}
                matchPatterns: "{{ matchPatterns }}"
        draftTokenCount: {{ draftTokenCount }}
      scaleSettings:
        scaleType: "{{ scaleType }}"
        capacity: {{ capacity }}
        activeCapacity: {{ activeCapacity }}
      capabilities: "{{ capabilities }}"
      raiPolicyName: "{{ raiPolicyName }}"
      callRateLimit:
        count: {{ count }}
        renewalPeriod: {{ renewalPeriod }}
        rules:
          - key: "{{ key }}"
            renewalPeriod: {{ renewalPeriod }}
            count: {{ count }}
            minCount: {{ minCount }}
            dynamicThrottlingEnabled: {{ dynamicThrottlingEnabled }}
            matchPatterns: "{{ matchPatterns }}"
      rateLimits:
        - key: "{{ key }}"
          renewalPeriod: {{ renewalPeriod }}
          count: {{ count }}
          minCount: {{ minCount }}
          dynamicThrottlingEnabled: {{ dynamicThrottlingEnabled }}
          matchPatterns: "{{ matchPatterns }}"
      versionUpgradeOption: "{{ versionUpgradeOption }}"
      dynamicThrottlingEnabled: {{ dynamicThrottlingEnabled }}
      currentCapacity: {{ currentCapacity }}
      capacitySettings:
        designatedCapacity: {{ designatedCapacity }}
        priority: {{ priority }}
      parentDeploymentName: "{{ parentDeploymentName }}"
      spilloverDeploymentName: "{{ spilloverDeploymentName }}"
      serviceTier: "{{ serviceTier }}"
      deploymentState: "{{ deploymentState }}"
      routing:
        mode: "{{ mode }}"
        models:
          - publisher: "{{ publisher }}"
            format: "{{ format }}"
            name: "{{ name }}"
            version: "{{ version }}"
            source: "{{ source }}"
            sourceAccount: "{{ sourceAccount }}"
            callRateLimit:
              count: {{ count }}
              renewalPeriod: {{ renewalPeriod }}
              rules:
                - key: "{{ key }}"
                  renewalPeriod: {{ renewalPeriod }}
                  count: {{ count }}
                  minCount: {{ minCount }}
                  dynamicThrottlingEnabled: {{ dynamicThrottlingEnabled }}
                  matchPatterns: "{{ matchPatterns }}"
  - name: sku
    description: |
      The resource model definition representing SKU.
    value:
      name: "{{ name }}"
      tier: "{{ tier }}"
      size: "{{ size }}"
      family: "{{ family }}"
      capacity: {{ capacity }}
  - name: tags
    value: "{{ tags }}"
    description: |
      Resource tags.

UPDATE examples

update

Update specified deployments associated with the Cognitive Services account.

UPDATE azure.cognitive_services.deployments
SET 
tags = '{{ tags }}',
sku = '{{ sku }}'
WHERE 
resource_group_name = '{{ resource_group_name }}' --required
AND account_name = '{{ account_name }}' --required
AND deployment_name = '{{ deployment_name }}' --required
AND subscription_id = '{{ subscription_id }}' --required
RETURNING
id,
name,
etag,
properties,
sku,
systemData,
tags,
type;

REPLACE examples

create_or_update

Update the state of specified deployments associated with the Cognitive Services account.

REPLACE azure.cognitive_services.deployments
SET 
properties = '{{ properties }}',
sku = '{{ sku }}',
tags = '{{ tags }}'
WHERE 
resource_group_name = '{{ resource_group_name }}' --required
AND account_name = '{{ account_name }}' --required
AND deployment_name = '{{ deployment_name }}' --required
AND subscription_id = '{{ subscription_id }}' --required
RETURNING
id,
name,
etag,
properties,
sku,
systemData,
tags,
type;

DELETE examples

delete

Deletes the specified deployment associated with the Cognitive Services account.

DELETE FROM azure.cognitive_services.deployments
WHERE resource_group_name = '{{ resource_group_name }}' --required
AND account_name = '{{ account_name }}' --required
AND deployment_name = '{{ deployment_name }}' --required
AND subscription_id = '{{ subscription_id }}' --required
;

Lifecycle Methods

list_skus

Lists the specified deployments skus associated with the Cognitive Services account.

EXEC azure.cognitive_services.deployments.list_skus 
@resource_group_name='{{ resource_group_name }}' --required, 
@account_name='{{ account_name }}' --required, 
@deployment_name='{{ deployment_name }}' --required, 
@subscription_id='{{ subscription_id }}' --required
;

pause

Pause a deployment. Pauses inferencing on a deployment by setting the deploymentState to 'Paused' (see #/definitions/DeploymentProperties/properties/deploymentState). Only Standard, DataZoneStandard, and GlobalStandard SKUs support this operation. Inference requests to the paused deployment endpoint will receive HTTP 423 (Locked). This operation is idempotent.

EXEC azure.cognitive_services.deployments.pause 
@resource_group_name='{{ resource_group_name }}' --required, 
@account_name='{{ account_name }}' --required, 
@deployment_name='{{ deployment_name }}' --required, 
@subscription_id='{{ subscription_id }}' --required
;

resume

Resume a deployment. Resumes inferencing on a previously paused deployment by setting the deploymentState to 'Running' (see #/definitions/DeploymentProperties/properties/deploymentState). This operation is idempotent and can be safely called on already running deployments.

EXEC azure.cognitive_services.deployments.resume 
@resource_group_name='{{ resource_group_name }}' --required, 
@account_name='{{ account_name }}' --required, 
@deployment_name='{{ deployment_name }}' --required, 
@subscription_id='{{ subscription_id }}' --required
;