---
title: "GET /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments"
method: GET
path: "/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments"
tags: ["Deployments"]
---

# GET /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments

`GET /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments`

## Request

- Base URL: `https://management.azure.com`
- URL: `https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments`
- Auth: OAuth 2
  - Implicit: `https://login.microsoftonline.com/common/oauth2/authorize`
  - Scopes: `user_impersonation`

Gets the deployments associated with the Cognitive Services account.

## Path parameters

- `subscriptionId` string, required
- `resourceGroupName` string, required
- `accountName` string, required

## Query parameters

- `api-version` string, required

## Response `200`

The request has succeeded.

- DeploymentListResult: The list of cognitive services accounts operation response.
  - `nextLink` string: The link used to get the next page of Deployment.
  - `value` Deployment[]: Gets the list of Cognitive Services accounts Deployment and their properties.
    - `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
    - `type` string: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"
    - `systemData` SystemData: Metadata pertaining to creation and last modification of the resource.
      - `createdBy` string: The identity that created the resource.
      - `createdByType` 'User' | 'Application' | 'ManagedIdentity' | 'Key': The type of identity that created the resource.
      - `createdAt` string, date-time: The timestamp of resource creation (UTC).
      - `lastModifiedBy` string: The identity that last modified the resource.
      - `lastModifiedByType` 'User' | 'Application' | 'ManagedIdentity' | 'Key': The type of identity that last modified the resource.
      - `lastModifiedAt` string, date-time: The timestamp of resource last modification (UTC)
    - `properties` DeploymentProperties: Properties of Cognitive Services account deployment.
      - `provisioningState` 'Accepted' | 'Creating' | 'Deleting' | 'Moving' | 'Failed' | 'Succeeded' | 'Disabled' | 'Canceled': Gets the status of the resource at the time the operation was called.
      - `model` DeploymentModel: Properties of Cognitive Services account deployment model.
        - `publisher` string: Deployment model publisher.
        - `format` string: Deployment model format.
        - `name` string: Deployment model name.
        - `version` string: Optional. Deployment model version. If version is not specified, a default version will be assigned. The default version is different for different models and might change when there is new version available for a model. Default version for a model could be found from list models API.
        - `source` string: Optional. Deployment model source ARM resource ID.
        - `sourceAccount` string, arm-id: Optional. Source of the model, another Microsoft.CognitiveServices accounts ARM resource ID.
        - `callRateLimit` CallRateLimit: The call rate limit Cognitive Services account.
          - `count` number, float: The count value of Call Rate Limit.
          - `renewalPeriod` number, float: The renewal period in seconds of Call Rate Limit.
          - `rules` ThrottlingRule[]
            - `key` string
            - `renewalPeriod` number, float
            - `count` number, float
            - `minCount` number, float
            - `dynamicThrottlingEnabled` boolean
            - `matchPatterns` RequestMatchPattern[]
              - …
      - `speculativeDecoding` DeploymentSpeculativeDecoding: Speculative decoding settings for a deployment.
        - `draftModel` DeploymentModel, required: Properties of Cognitive Services account deployment model.
          - `publisher` string: Deployment model publisher.
          - `format` string: Deployment model format.
          - `name` string: Deployment model name.
          - `version` string: Optional. Deployment model version. If version is not specified, a default version will be assigned. The default version is different for different models and might change when there is new version available for a model. Default version for a model could be found from list models API.
          - `source` string: Optional. Deployment model source ARM resource ID.
          - `sourceAccount` string, arm-id: Optional. Source of the model, another Microsoft.CognitiveServices accounts ARM resource ID.
          - `callRateLimit` CallRateLimit: The call rate limit Cognitive Services account.
            - `count` number, float: The count value of Call Rate Limit.
            - `renewalPeriod` number, float: The renewal period in seconds of Call Rate Limit.
            - `rules` ThrottlingRule[]
              - …
        - `draftTokenCount` integer: The number of draft tokens attempted per speculation step.
      - `scaleSettings` DeploymentScaleSettings: Properties of Cognitive Services account deployment model. (Deprecated, please use Deployment.sku instead.)
        - `scaleType` 'Standard' | 'Manual': Deployment scale type.
        - `capacity` integer: Deployment capacity.
        - `activeCapacity` integer: Deployment active capacity. This value might be different from `capacity` if customer recently updated `capacity`.
      - `capabilities` object: The capabilities.
      - `raiPolicyName` string: The name of RAI policy.
      - `callRateLimit` CallRateLimit: The call rate limit Cognitive Services account.
        - `count` number, float: The count value of Call Rate Limit.
        - `renewalPeriod` number, float: The renewal period in seconds of Call Rate Limit.
        - `rules` ThrottlingRule[]
          - `key` string
          - `renewalPeriod` number, float
          - `count` number, float
          - `minCount` number, float
          - `dynamicThrottlingEnabled` boolean
          - `matchPatterns` RequestMatchPattern[]
            - `path` string
            - `method` string
      - `rateLimits` ThrottlingRule[]
        - `key` string
        - `renewalPeriod` number, float
        - `count` number, float
        - `minCount` number, float
        - `dynamicThrottlingEnabled` boolean
        - `matchPatterns` RequestMatchPattern[]
          - `path` string
          - `method` string
      - `versionUpgradeOption` 'OnceNewDefaultVersionAvailable' | 'OnceCurrentVersionExpired' | 'NoAutoUpgrade': Deployment model version upgrade option.
      - `dynamicThrottlingEnabled` boolean: If the dynamic throttling is enabled.
      - `currentCapacity` integer: The current capacity.
      - `capacitySettings` DeploymentCapacitySettings: Internal use only.
        - `designatedCapacity` integer: The designated capacity.
        - `priority` integer: The priority of this capacity setting.
      - `parentDeploymentName` string: The name of parent deployment.
      - `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.
      - `serviceTier` 'Default' | 'Priority': 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.
      - `deploymentState` 'Running' | 'Paused': 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.
      - `routing` DeploymentRouting: Routing configuration for the model-router deployment. Specifies how requests are routed across multiple models.
        - `mode` 'cost' | 'balanced' | 'quality': The model-router routing mode that determines how requests are distributed across models.
        - `models` DeploymentModel[]: Optional. The list of model-router supported models that the model router can use to route requests across. If not specified, the model router will route to all available models specified in the model-router version.
          - `publisher` string: Deployment model publisher.
          - `format` string: Deployment model format.
          - `name` string: Deployment model name.
          - `version` string: Optional. Deployment model version. If version is not specified, a default version will be assigned. The default version is different for different models and might change when there is new version available for a model. Default version for a model could be found from list models API.
          - `source` string: Optional. Deployment model source ARM resource ID.
          - `sourceAccount` string, arm-id: Optional. Source of the model, another Microsoft.CognitiveServices accounts ARM resource ID.
          - `callRateLimit` CallRateLimit: The call rate limit Cognitive Services account.
            - `count` number, float: The count value of Call Rate Limit.
            - `renewalPeriod` number, float: The renewal period in seconds of Call Rate Limit.
            - `rules` ThrottlingRule[]
              - …
    - `sku` Sku: The resource model definition representing SKU
      - `name` string, required: The name of the SKU. Ex - P3. It is typically a letter+number code
      - `tier` 'Free' | 'Basic' | 'Standard' | 'Premium' | 'Enterprise': 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.
      - `size` string: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code.
      - `family` string: If the service has different generations of hardware, for the same SKU, then that can be captured here.
      - `capacity` integer: 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.
    - `etag` string: Resource Etag.
    - `tags` object: Resource tags.

## Other responses

- `default`: An unexpected error response.

## Changes

- **2026-07-13** (2016-02-01-preview) `d0eb21b3d2a7`: 3 breaking
  - added the new path request parameter `resourceGroupName`
  - added the new path request parameter `subscriptionId`
  - added the new required `query` request parameter `api-version`
- **2026-07-13** (2016-02-01-preview) `c4a2e59a4ce0`: 1 info
  - endpoint added
- **2017-12-28** (2016-02-01-preview) `9fddc284caf8`: 1 breaking
  - api path removed without deprecation

[Operation history](https://skmtc.dev/azure/apis/cognitiveservices-microsoft-cognitiveservices/changes/subscriptions/:subscriptionId/resourceGroups/:resourceGroupName/providers/Microsoft.CognitiveServices/accounts/:accountName/deployments/get.md)

---

[API](https://skmtc.dev/azure/apis/cognitiveservices-microsoft-cognitiveservices.md) - [All operations](https://skmtc.dev/azure/apis/cognitiveservices-microsoft-cognitiveservices/llms.txt) - [OpenAPI document](https://skmtc.dev/azure/apis/cognitiveservices-microsoft-cognitiveservices/revisions/d0eb21b3d2a7?raw)
