DocsICP FilingConsole
Documentation

DescribeAIDBClusterAttribute

Updated at:
Copy as MD
Product
My Favorites

Queries the details of a custom instance.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

  • Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.

  • API: The API that you can call to perform the action.

  • Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.

  • Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.

    • For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.

    • For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.

  • Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.

  • Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

polardb:DescribeAIDBClusterAttribute

get

*AICluster

acs:polardb:{#regionId}:{#accountId}:aicluster/{#DBClusterId}

 None None

Request parameters

Parameter

Type

Required

Description

Example
DBClusterId

string

Yes

The cluster ID.

pc-****************

Response elements

Element

Type

Description

Example

object

Schema of Response

AiNodeType

string

The node type. Valid values:

  • vnode: ACK-managed node.

  • container: container that supports logon.

  • maas: model service.

vnode
ApiKey

string

The API key.

x********
Command

string

The startup command currently used by the model service.

python -m vllm.entrypoints.openai.api_server
CreationTime

string

The time when the cluster was created.

The time follows the ISO 8601 standard in UTC (format: YYYY-MM-DDTHH:mm:ssZ).

2020-08-14T05:58:42Z
CurrentCapacity

integer

The current measured model capacity of the instance. The abstract capacity unit is 1000, which is equivalent to one L20N card.

8000
CustomOssPath

string

The custom Object Storage Service (OSS) path of the model currently used by the instance.

/my-model-bucket/models/qwen3
DBClusterDescription

string

The description of the cluster. Fuzzy match is supported.

test
DBClusterId

string

The cluster ID.

pc-**************
DBClusterStatus

string

The status of the cluster. Valid values:

  • Creating: The cluster is being created.

  • Running: The cluster is running.

  • Deleting: The cluster is being released.

  • DBNodeCreating: Nodes are being added.

  • DBNodeDeleting: Nodes are being deleted.

  • ClassChanging: The node specifications are being changed.

  • Deleted: The cluster is released.

Running
DBInstanceStatusDesc

string

The database instance status description. A value of ACTIVATION indicates that the database instance is running.

ACTIVATION
DBNodes

array<object>

The details of the node information.

array<object>

The details of the node information.

ChildVolumes

array<object>

The list of data cloud disks.

object

The data cloud disk information.

MountPath

string

The actual mount path.

/tmp/CrowdStrike
Name

string

The disk name.

jueming
SizeGB

string

The size of the cloud disk.

8192
StorageCategory

string

The storage type.

PolarFs
StorageType

string

The storage category.

PL1
Command

string

The startup command currently used by the model. If no record exists, an empty string is returned.

python -m vllm.entrypoints.openai.api_server
CpuCores

string

The number of CPU cores of the node.

2
CreationTime

string

The time when the node was created.

The time follows the ISO 8601 standard in UTC (format: YYYY-MM-DDTHH:mm:ssZ).

2020-08-14T05:58:42Z
DBNodeClass

string

The cluster specifications.

polar.pg.g8.8xlarge.gu30
DBNodeDescription

string

The description of the node.

test
DBNodeId

string

The node ID.

pi-****************
DBNodeStatus

string

The status of the node. Valid values:

  • Creating: The node is being created.

  • Running: The node is running.

  • Deleting: The node is being deleted.

  • Rebooting: The node is being restarted.

  • DBNodeCreating: Nodes are being added.

  • DBNodeDeleting: Nodes are being deleted.

  • ClassChanging: The node specifications are being changed.

  • MinorVersionUpgrading: The minor version is being upgraded.

  • Maintaining: The instance is being maintained.

  • Switching: A switchover is in progress.

Running
GPU

string

The number of GPUs.

2
LinkIP

string

The private IP address.

10.*.*12
LogIndex

string

The log indexing of the worker node.

worker-0
MemorySize

string

The memory size of the node. Unit: MB.

8192
ModelName

string

The model name.

Qwen3-Embedding-8B
ModelSpaceName

string

The name of the workspace to which the model belongs.

my-model-space
PublicIp

string

The public IP address.

101.101.101.101
SupportedApis

array<object>

The supported APIs.

object

ApiName

string

The name of the API supported by the database node.

Completions
GenerationMode

string

The generation mode of the API.

stream
Path

string

The path of the supported API.

/v1/chat/completions
Protocol

string

The protocol type of the supported API.

HTTP
VNodeId

string

The ID of the Kubernetes virtual node.

vn-***************
VPCId

string

The VPC ID.

vpc-*******************
VSwitchId

string

The vSwitch ID.

vsw-*********************
ZoneId

string

The zone.

cn-hangzhou-d

DBVersion

string

The cluster version. Valid values:

1.0

2.0

3.0

1.0
DedicatedHostModel

boolean

Specifies whether the dedicated host mode is used.

EcsSecurityGroupId

string

The security group ID.

sg-xxxxxx
EndpointList

array<object>

The list of network endpoint addresses of the instance.

array<object>

The network endpoint address of the instance.

NetInfoItems

array<object>

The list of network information of the instance.

object

The network information of the instance.

ConnectionString

string

The database connection address.

pc-**********.rwlb.rds.aliyuncs.com
NetType

string

The network type of the connection string. Valid values:

  • Public: Public network address.

  • Private: Private network address.

  • Inner: Private network address (classic network).

Public
Port

string

The port number.

3306
ExpireTime

string

The expiration time of the cluster.

Note

A specific value is returned only for clusters whose billing method is Prepaid (subscription). For clusters whose billing method is Postpaid (pay-as-you-go), an empty value is returned.

The time follows the ISO 8601 standard in UTC (format: YYYY-MM-DDTHH:mm:ssZ).

2020-11-14T16:00:00Z
Expired

boolean

Indicates whether the cluster has expired. Valid values:

  • true

  • false

false
GatewayId

string

The ID of the AI gateway instance.

pg-2ze24rr575j5b18cg
InferenceEngine

string

The model inference engine.

sglang
InternalIp

string

The internal IP address.

10.*.*.72
KVCacheInstanceId

string

The KVCache instance ID.

pkv-xxxxx
KubeClusterId

string

The ACK cluster ID.

xxxxxxxxxxxxxxxxxxxxxxx
LockMode

string

The lock mode of the instance. A value of lock indicates that the instance has expired or has an overdue payment.

Unlock
MaxQPM

string

The maximum number of requests per minute.

20
MaxTPM

string

The maximum number of tokens allowed per minute.

10000
ModelName

string

The model name.

Qwen3-Embedding-8B
ModelSpaceName

string

The name of the workspace to which the model belongs.

my-model-space
ModelType

string

The model type.

custom
PayType

string

The billing method. Valid values:

  • Postpaid: pay-as-you-go

  • Prepaid: subscription

Postpaid
PreviousCustomOssPath

string

The custom model OSS path before the last change.

/my-model-bucket/models/qwen2
PublicIp

string

The public IP address.

8.xxx.xxx.xxx
RegionId

string

The region ID.

cn-hangzhou
RequestId

string

Id of the request

EBEAA83D-1734-42E3-85E3-E25F6E******
RunType

string

The architecture type. Valid values:

  • container: AI container

  • ainode: AI node

container
StorageType

string

The storage type. Valid values for Enterprise Edition:

  • PSL5

  • PSL4

Valid values for Standard Edition:

  • ESSDPL0

  • ESSDPL1

  • ESSDPL2

  • ESSDPL3

  • ESSDAUTOPL

essdpl1
TimeSlicesInfo

object

The time slice configuration for pay-as-you-go billing.

TimeSlices

array<object>

The list of time slices for pay-as-you-go billing.

object

BeginTime

string

The start time of the time slice, in the HH:mm format.

08:00
EndTime

string

The end time of the time slice, in the HH:mm format.

18:00
TimeSlicesType

string

The cycle type of the time slice configuration.

daily
VPCId

string

The VPC ID specified for zone switching.

vpc-*******************
VSwitchId

string

The vSwitch ID.

Note

If VPCId is specified, VSwitchId is required.

vsw-*********************
VnodeKubernetesConfig

object

The Kubernetes configuration of the virtual node.

Labels

array<object>

The list of Kubernetes node labels.

object

Key

string

The key of the node label.

environment
Value

string

The value of the node label.

production
Taints

array<object>

The list of Kubernetes node taints.

object

Effect

string

The scheduling effect of the node taint.

NoSchedule
Key

string

The key of the node taint.

dedicated
Value

string

The value of the node taint.

groupName
Volumes

array<object>

The list of data cloud disks.

object

The data cloud disk information.

MountPath

string

The mount path in the container.

/var/run/secrets/kubernetes.io/serviceaccount
Name

string

The disk name.

jueming
SizeGB

string

The storage size.

8192
StorageCategory

string

The storage type.

PL1
StorageType

string

The storage category.

PolarFs
ZoneId

string

The zone ID of the PolarDB cluster node.

cn-hangzhou-d

ZoneIds

string

The zone IDs.

cn-hangzhou-i,cn-hangzhou-g

Examples

Success response

JSON format

{
  "AiNodeType": "vnode",
  "ApiKey": "x********",
  "Command": "python -m vllm.entrypoints.openai.api_server",
  "CreationTime": "2020-08-14T05:58:42Z",
  "CurrentCapacity": 8000,
  "CustomOssPath": "/my-model-bucket/models/qwen3",
  "DBClusterDescription": "test",
  "DBClusterId": "pc-**************",
  "DBClusterStatus": "Running",
  "DBInstanceStatusDesc": "ACTIVATION",
  "DBNodes": [
    {
      "ChildVolumes": [
        {
          "MountPath": "/tmp/CrowdStrike",
          "Name": "jueming",
          "SizeGB": "8192",
          "StorageCategory": "PolarFs",
          "StorageType": "PL1"
        }
      ],
      "Command": "python -m vllm.entrypoints.openai.api_server",
      "CpuCores": "2",
      "CreationTime": "2020-08-14T05:58:42Z",
      "DBNodeClass": "\npolar.pg.g8.8xlarge.gu30",
      "DBNodeDescription": "test",
      "DBNodeId": "pi-****************",
      "DBNodeStatus": "Running",
      "GPU": "2",
      "LinkIP": "10.*.*12",
      "LogIndex": "worker-0",
      "MemorySize": "8192",
      "ModelName": "Qwen3-Embedding-8B",
      "ModelSpaceName": "my-model-space",
      "PublicIp": "101.101.101.101",
      "SupportedApis": [
        {
          "ApiName": "Completions",
          "GenerationMode": "stream",
          "Path": "/v1/chat/completions",
          "Protocol": "HTTP"
        }
      ],
      "VNodeId": "vn-***************",
      "VPCId": "vpc-*******************",
      "VSwitchId": "vsw-*********************",
      "ZoneId": "cn-hangzhou-d\t\n"
    }
  ],
  "DBVersion": "1.0",
  "DedicatedHostModel": false,
  "EcsSecurityGroupId": "sg-xxxxxx",
  "EndpointList": [
    {
      "NetInfoItems": [
        {
          "ConnectionString": "pc-**********.rwlb.rds.aliyuncs.com",
          "NetType": "Public",
          "Port": "3306"
        }
      ]
    }
  ],
  "ExpireTime": "2020-11-14T16:00:00Z",
  "Expired": false,
  "GatewayId": "pg-2ze24rr575j5b18cg",
  "InferenceEngine": "sglang",
  "InternalIp": "10.*.*.72",
  "KVCacheInstanceId": "pkv-xxxxx",
  "KubeClusterId": "xxxxxxxxxxxxxxxxxxxxxxx",
  "LockMode": "Unlock",
  "MaxQPM": "20",
  "MaxTPM": "10000",
  "ModelName": "\nQwen3-Embedding-8B",
  "ModelSpaceName": "my-model-space",
  "ModelType": "custom",
  "PayType": "Postpaid",
  "PreviousCustomOssPath": "/my-model-bucket/models/qwen2",
  "PublicIp": "8.xxx.xxx.xxx",
  "RegionId": "cn-hangzhou",
  "RequestId": "EBEAA83D-1734-42E3-85E3-E25F6E******",
  "RunType": "container",
  "StorageType": "essdpl1",
  "TimeSlicesInfo": {
    "TimeSlices": [
      {
        "BeginTime": "08:00",
        "EndTime": "18:00"
      }
    ]
  },
  "TimeSlicesType": "daily",
  "VPCId": "vpc-*******************",
  "VSwitchId": "vsw-*********************",
  "VnodeKubernetesConfig": {
    "Labels": [
      {
        "Key": "environment",
        "Value": "production"
      }
    ],
    "Taints": [
      {
        "Effect": "NoSchedule",
        "Key": "dedicated",
        "Value": "groupName"
      }
    ]
  },
  "Volumes": [
    {
      "MountPath": "/var/run/secrets/kubernetes.io/serviceaccount",
      "Name": "jueming",
      "SizeGB": "8192",
      "StorageCategory": "PL1",
      "StorageType": "PolarFs"
    }
  ],
  "ZoneId": "cn-hangzhou-d\t\n",
  "ZoneIds": "cn-hangzhou-i,cn-hangzhou-g"
}

Error codes

HTTP status code

Error code

Error message

Description
404 InvalidDBClusterId.Malformed The specified parameter DBClusterId is not valid. The specified DBClusterId parameter is invalid.
404 InvalidDBClusterId.NotFound The DBInstanceId provided does not exist in our records. The specified DBClusterId parameter does not exist in the current record.

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.