Obtaining the Service Deployment Instance List

Function

This API is used to obtain the service deployment instances of the current tenant and filter them by status, which can be Running and Deleted. Pagination and keyword filtering are supported. It is used when you need to manage and monitor service instance status. Before calling this API, ensure that you have the query permission and provide optional filter criteria and pagination parameters. The returned list contains the basic information about all deployment instances, including the deployment name, latest update time, and status. If the current tenant does not have any service instance that meets the conditions or the provided parameters are invalid, an empty list or the corresponding error message is returned, prompting you to check the validity and permission of the input data.

Debugging

You can debug this API through automatic authentication in API Explorer or use the SDK sample code generated by API Explorer.

Authorization Information

Each account has all the permissions required to call all APIs, but IAM users must be assigned the required permissions.

If you are using role/policy-based authorization, see Permissions Policies and Supported Actions for details on the required permissions.
If you are using identity policy-based authorization, the following identity policy-based permissions are required.

Action

Access Level

Resource Type (*: required)

Condition Key

Alias

Dependencies

modelarts:service:listDeploymentInstances

Read

service *

-

-

-

Action	Access Level	Resource Type (*: required)	Condition Key	Alias	Dependencies
modelarts:service:listDeploymentInstances	Read	service *	-	-	-

URI

GET /v2/{project_id}/services/{id}/deployments/{name}/instances

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Definition Project ID. For details, see Obtaining a Project ID and Name. Constraints N/A Range Project ID. Default Value N/A
id	Yes	String	Definition Unique service ID.
name	Yes	String	Definition Service deployment name. The value can be all.

**Table 2** Query Parameters
Parameter	Mandatory	Type	Description
status	No	Array of strings	Definition Service instance status. Multiple statuses can be filtered at a time. Separate multiple statuses with commas (,). No space is allowed. By default, filtering is disabled. The value can be RUNNING, ERROR, INIT, or DELETED. Constraints N/A
limit	No	Integer	Definition Maximum number of records displayed on each page. Constraints N/A Range [1,500] Default Value 10.
offset	No	String	Definition Start page of the pagination list. Constraints N/A Range N/A Default Value 0.
pod_name	No	String	Definition Pod name. Range N/A

Request Parameters

**Table 3** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	Definition User token. It can be obtained by calling the IAM API used to obtain a user token. The value of X-Subject-Token in the response header is the user token. For details about how to obtain the token, see Obtaining a User Token Through Password Authentication. Constraints N/A Range N/A Default Value N/A

Response Parameters

Status code: 200

**Table 4** Response body parameters
Parameter	Type	Description
current	Integer	Definition Current page number, starting from 0. Range N/A
data	Array of ServiceInstanceResponse objects	Definition Service instance list.
pages	Integer	Definition Total number of pages, which is calculated based on the limit field and the total number of data records. For example, if the total number of records is 10 and the value of limit (maximum number of records on a page) is 3, there are four pages. Range N/A
size	Integer	Definition Number of records on the current page. Range N/A
total	Integer	Definition Total number of records. Range N/A

**Table 5** ServiceInstanceResponse
Parameter	Type	Description
instance_name	String	Definition Service instance name. Range N/A
status	String	Definition Service instance status. Range RUNNING PENDING: The instance is not ready. CONCERNING: There is an alarm. FAILED UNKNOWN DELETED
weight	Integer	Definition Service instance weight. Range [0, 100] or left empty.
pod_count	Long	Definition Number of service instance pods. Range N/A
running_pod_count	Long	Definition Number of running pods of a service instance. Range N/A
update_at	Long	Definition Last update time of the service instance. Range N/A

Status code: 400

**Table 6** Response body parameters
Parameter	Type	Description
error_code	String	Definition: ModelArts error code. Range: N/A.
error_msg	String	Definition: Error message. Range: N/A.

Status code: 401

**Table 7** Response body parameters
Parameter	Type	Description
error_code	String	Definition: ModelArts error code. Range: N/A.
error_msg	String	Definition: Error message. Range: N/A.

Status code: 403

**Table 8** Response body parameters
Parameter	Type	Description
error_code	String	Definition: ModelArts error code. Range: N/A.
error_msg	String	Definition: Error message. Range: N/A.

Status code: 404

**Table 9** Response body parameters
Parameter	Type	Description
error_code	String	Definition: ModelArts error code. Range: N/A.
error_msg	String	Definition: Error message. Range: N/A.

Example Requests

Obtain a specified deployment list.

GET https://{endpoint}/v2/{project_id}/services/{service_id}/deployments/{name}/instances

Example Responses

Status code: 200

Deployment instances are listed.

{
  "current" : 1,
  "data" : [ {
    "instance_name" : "infer-a07f5c03-18c5-4dfb-849a-c3506020a1f8-1ghsj",
    "status" : "DELETED",
    "pod_count" : 1,
    "running_pod_count" : 1,
    "update_at" : 1747766464765,
    "weight" : 50
  }, {
    "instance_name" : "infer-a07f5c03-18c5-4dfb-849a-c3506020a1f8-ecfip",
    "status" : "DELETED",
    "update_at" : 1747785331567,
    "pod_count" : 1,
    "running_pod_count" : 1,
    "weight" : 50
  } ],
  "pages" : 1,
  "size" : 2,
  "total" : 2
}