All Products
Search
Document Center

Tair (Redis® OSS-Compatible):DescribeTairKVCacheInferInstances

Last Updated:Jan 28, 2026

Queries the information of one or more Tair (Redis OSS-compatible) KVCache instances.

Operation description

You can call this operation to query the following Tair (Redis OSS-compatible) KVCache instances: inference operator instances, virtual cluster instances, and cache service instances.

Debugging

You can run this interface directly in OpenAPI Explorer, saving you the trouble of calculating signatures. After running successfully, OpenAPI Explorer can automatically generate SDK code samples.

Authorization information

The following table shows the authorization information corresponding to the API. The authorization information can be used in the Action policy element to grant a RAM user or RAM role the permissions to call this API operation. Description:

  • Operation: the value that you can use in the Action element to specify the operation on a resource.
  • Access level: the access level of each operation. The levels are read, write, and list.
  • Resource type: the type of the resource on which you can authorize the RAM user or the RAM role to perform the operation. Take note of the following items:
    • For mandatory resource types, indicate with a prefix of * .
    • If the permissions cannot be granted at the resource level, All Resources is used in the Resource type column of the operation.
  • Condition Key: the condition key that is defined by the cloud service.
  • Associated operation: other operations that the RAM user or the RAM role must have permissions to perform to complete the operation. To complete the operation, the RAM user or the RAM role must have the permissions to perform the associated operations.
OperationAccess levelResource typeCondition keyAssociated operation
kvstore:DescribeTairKVCacheInferInstanceslist
*All Resources
*
    none
none

Request parameters

ParameterTypeRequiredDescriptionExample
RegionIdstringYes

The ID of the region where the instance resides.

cn-beijing
InstanceIdsstringNo

The IDs of the instances that you want to query.

Note If you want to specify multiple instance IDs, separate the instance IDs with commas (,). You can specify a maximum of 30 instance IDs in a single request.
tk-2zefe7728c2c****
InstanceStatusstringNo

The state of the instance. Valid values:

  • Normal: The instance is normal.
  • Creating: The instance is being created.
Note For more information about instance states, see Instance states and impacts.
Normal
ChargeTypestringNo

The billing method of the simple application servers. Valid values:

  • PrePaid: subscription
  • PostPaid: pay-as-you-go
PrePaid
NetworkTypestringNo

The network type of the instance. Default value: VPC. Valid values:

  • VPC (default)

Valid values:

  • CLASSIC
  • VPC
VPC
InstanceClassstringNo

The instance type.

kvcache.cu.g4c.2
VpcIdstringNo

The ID of the VPC.

vpc-bp1nme44gek34slfc****
VSwitchIdstringNo

The ID of the vSwitch.

vsw-bp1e7clcw529l773d****
PageNumberintegerNo

The page number of the instance list. Start value: 1. Default value: 1.

1
PageSizeintegerNo

The number of entries per page. Default value: 30.

30
SearchKeystringNo

The keyword that you want to use for fuzzy match. The keyword can be a part of an instance name or an instance ID.

apitest
ExpiredstringNo

Specifies whether the instance has expired. Valid values:

  • true: The instance has expired.
  • false: The instance has not expired.
false
ZoneIdstringNo

The zone ID.

cn-hangzhou-e
ResourceGroupIdstringNo

The resource group ID. You can leave this parameter empty.

rg-acfmyiu4ekp****
Tagarray<object>No

Details of the tags.

objectNo

Details of the tag.

KeystringNo

The tag key.

Note A maximum of five key-value pairs can be specified at a time.
key1_test
ValuestringNo

The value of tag N of the instance.

Note N specifies the value of the nth tag. For example, Tag.1.Value specifies the value of the first tag, and Tag.2.Value specifies the value of the second tag.
testvalue
PrivateIpstringNo

The private IP address of the instance. This parameter is deprecated.

172.16.49.***

Response parameters

ParameterTypeDescriptionExample
object
RequestIdstring

The request ID.

CD225838-7069-5CE4-89E1-67B83AC149C8
PageNumberinteger

The page number.

1
PageSizeinteger

The number of entries per page.

30
TotalCountinteger

The total number of returned records.

3
Instancesarray<object>

The information about the returned Tair (Redis OSS-compatible) KVCache instance.

TairInferInstanceDTOobject
VpcIdstring

The VPC ID of the instance.

vpc-2zef5w848p4j5g***
CreateTimestring

The creation time of the instance.

2025-04-07T04:46Z
ChargeTypestring

The billing method of the instance.

PostPaid
NetworkTypestring

The network type of the instance.

VPC
InstanceNamestring

The instance name.

kvcache-7
InstanceClassstring

The instance type.

kvcache.cu.g4b.2
DestroyTimestring

The time when the instance was deleted.

2025-04-07T04:46Z
InstanceIdstring

The ID of the instance.

tk-9dp7e37bab*****
InstanceTypestring

The type of the instance. Valid values:

  • TairInfer: the inference operator instance
  • TairKVCacheVnode: the virtual cluster instance.
  • TairKVCacheService: the cache service instance.
TairInfer
RegionIdstring

The region ID of the instance.

cn-beijing
EndTimestring

The time when the subscription instance expires.

2025-11-04T02:09:26Z
VSwitchIdstring

The vSwitch ID.

vsw-8vbf0ksk774ai6q1d****
ResourceGroupIdstring

The resource group ID.

rg-acfm4bdru5z****
ZoneIdstring

The zone ID.

cn-hangzhou-g
InstanceStatusstring

The instance state. Valid values:

  • Normal: The instance is normal.
  • Creating: The instance is being created.
Normal
Tagsarray<object>

Details of the tags.

Tagobject

Details of the tag.

Keystring

The tag key.

thread
Valuestring

The tag value.

900
PrivateIpstring

The private IP address of the instance. This parameter is deprecated.

172.16.49.***
Capacitylong

The capacity of the KVCache. Unit: GB.

256
Modelstring

The built-in model of the inference operator instance.

DeepSeek-OCR
ModelServiceNuminteger

The number of model services of the inference operator instance.

1
ComputeUnitNuminteger

The number of compute units.

1
VNodeNamestring

The list of vNode instance names under the virtual cluster instance. This parameter is deprecated.

tv-xxxxx
AckIdstring

The ACK cluster ID corresponding to the virtual cluster instance.

c809******************************
VNodeCountinteger

The number of vNodes in the virtual cluster.

2

Examples

Sample success responses

JSONformat

{
  "RequestId": "CD225838-7069-5CE4-89E1-67B83AC149C8",
  "PageNumber": 1,
  "PageSize": 30,
  "TotalCount": 3,
  "Instances": {
    "TairInferInstanceDTO": [
      {
        "VpcId": "vpc-2zef5w848p4j5g***",
        "CreateTime": "2025-04-07T04:46Z",
        "ChargeType": "PostPaid",
        "NetworkType": "VPC",
        "InstanceName": "kvcache-7",
        "InstanceClass": "kvcache.cu.g4b.2",
        "DestroyTime": "2025-04-07T04:46Z\n",
        "InstanceId": "tk-9dp7e37bab*****",
        "InstanceType": "TairInfer",
        "RegionId": "cn-beijing",
        "EndTime": "2025-11-04T02:09:26Z",
        "VSwitchId": "vsw-8vbf0ksk774ai6q1d****",
        "ResourceGroupId": "rg-acfm4bdru5z****",
        "ZoneId": "cn-hangzhou-g",
        "InstanceStatus": "Normal",
        "Tags": {
          "Tag": [
            {
              "Key": "thread",
              "Value": 900
            }
          ]
        },
        "PrivateIp": "172.16.49.***",
        "Capacity": 256,
        "Model": "DeepSeek-OCR",
        "ModelServiceNum": 1,
        "ComputeUnitNum": 1,
        "VNodeName": "tv-xxxxx",
        "AckId": "c809******************************",
        "VNodeCount": 2,
        "FixedVNodeCount": 0,
        "ElasticVNodeCount": 0
      }
    ]
  }
}

Error codes

HTTP status codeError codeError message
400InvalidInstanceIds.MalformedThe Specified parameter InstanceIds is not valid.

For a list of error codes, visit the Service error codes.

Change history

Change timeSummary of changesOperation
2025-12-04The Error code has changed. The response structure of the API has changedView Change Details
2025-11-27Add OperationView Change Details