DescribeInferenceServices

1. API Description

Domain name for API request: teo.intl.tencentcloudapi.com.

This API is used to query the service list for reasoning, supporting filtering by service name, service ID, and status. It returns information such as service configuration, running state, number of instances, and reasoning access address.

A maximum of 20 requests can be initiated per second for this API.

We recommend you to use API Explorer

Try it

API Explorer provides a range of capabilities, including online call, signature authentication, SDK code generation, and API quick search. It enables you to view the request, response, and auto-generated examples.

2. Input Parameters

The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.

Parameter Name	Required	Type	Description
Action	Yes	String	Common Params. The value used for this API: DescribeInferenceServices.
Version	Yes	String	Common Params. The value used for this API: 2022-09-01.
Region	No	String	Common Params. This parameter is not required.
ZoneId	Yes	String	Site ID.
Filters.N	No	Array of AdvancedFilter	Filtering Conditions, maximum 20, multiple conditions have an AND relationship, the maximum for Filters.Values is 20. Detailed filter criteria are as follows: service-name: filter by service name; service-id: filter by service ID; status: filter by service status. Only the field named service-name supports filtering during a fuzzy query.
Offset	No	Integer	Paginated query offset. Default value: 0.
Limit	No	Integer	Paginated query limit. Default value: 20, maximum value: 200.
Order	No	String	Sort returned results based on this field. Valid values: create-time: Creation time. Default sorting order is by create-time if left empty.
Direction	No	String	Sorting order. If the field value is a number, sort based on its size; if the field value is text, sort based on ASCII code size. Valid values: asc: sort in ascending order; desc: sort in descending order. Use default value if not specified.

3. Output Parameters

Parameter Name	Type	Description
TotalCount	Integer	Total number of eligible services.
Services	Array of InferenceService	Inference service list.
RequestId	String	The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem.

4. Example

Example1 Querying an inference service

This example shows you how to filter and query an inference service by condition.

Input Example

POST / HTTP/1.1
Host: teo.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: DescribeInferenceServices
<Common request parameters>

{
    "ZoneId": "zone-2***8ev000",
    "Filters": [
        {
            "Name": "service-name",
            "Values": [
                "image-classification"
            ],
            "Fuzzy": true
        }
    ],
    "Offset": 0,
    "Limit": 20,
    "Order": "create-time",
    "Direction": "desc"
}

Output Example

{
    "Response": {
        "Services": [
            {
                "Containers": [
                    {
                        "EnvironmentVariables": [
                            {
                                "Key": "MODEL_PATH",
                                "Value": "/models/v1"
                            }
                        ],
                        "ImageType": "TCR",
                        "StartupCommand": "python app.py",
                        "TcrRepositoryConfig": {
                            "Image": "ccr.ccs.tencentyun.com/namespace/image:v1.0.0",
                            "RegionName": "ap-guangzhou",
                            "RegistryId": "tcr-ab***ef456",
                            "TCRType": "Enterprise"
                        }
                    }
                ],
                "CreateTime": "2025-12-09T10:00:00Z",
                "Description": "Image inference based on ResNet50 model",
                "InferenceURL": "https://model-zone-***0300.edgeone-ai.com",
                "ListenPort": 8080,
                "Name": "image-classification-service",
                "ResourceConfig": {
                    "AutoScalingConfig": {
                        "MinInstanceCount": 1
                    },
                    "Concurrency": 10,
                    "HardwareSpec": "GPU-T4-8C16G",
                    "ManualInstanceConfig": null,
                    "ScalingMode": "Auto"
                },
                "ServiceId": "inf-9f8***4a3210",
                "Status": "Running",
                "UpdateTime": "2025-12-09T10:30:00Z"
            }
        ],
        "TotalCount": 1,
        "RequestId": "36b93c01-c30f-4865-86f7-710067654fea"
    }
}

5. Developer Resources

SDK

TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.

Command Line Interface

Tencent Cloud CLI 3.0

6. Error Code

The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.

Error Code	Description
InternalError	Internal error.
InvalidParameterValue.ZoneNotFound	No corresponding site. please ensure correct information entry.

1. API Description
2. Input Parameters
3. Output Parameters
4. Example
- Example1 Querying an inference service
5. Developer Resources
- SDK
- Command Line Interface
6. Error Code