Domain name for API request: teo.intl.tencentcloudapi.com.
This API is used to create an inference service. It allows setting the service name, listening port, container image configuration, and resource configuration. Once created successfully, an inference access address is provided.
A maximum of 20 requests can be initiated per second for this API.
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: CreateInferenceService. |
| 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. |
| Name | Yes | String | Service name. Length limit is no more than 30 characters, only lowercase letters, digits, and hyphens are supported, must start with a letter, ends with a digit or letter, duplicates are not supported. |
| ListenPort | Yes | Integer | Ports monitored by the model service. Only integers between 1 and 65535 are supported. |
| Containers.N | Yes | Array of InferenceContainerConfig | Container configuration of the inference service. Currently only support setting 1 container. |
| ResourceConfig | Yes | InferenceResourceConfig | Resource configuration of the inference service. |
| RequestPaths.N | No | Array of String | Request path list for inference service. Supports up to 20 paths. |
| Description | No | String | Description. Length limit: no more than 60 characters. |
| Parameter Name | Type | Description |
|---|---|---|
| ServiceId | String | Service ID. |
| 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. |
Create an inference service.
POST / HTTP/1.1
Host: teo.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: CreateInferenceService
<Common request parameters>
{
"ZoneId": "zone-3*********hx",
"Name": "***-test-060202",
"ListenPort": 5000,
"Containers": [
{
"ImageType": "TCR",
"TcrRepositoryConfig": {
"TCRType": "Personal",
"Image": "ccr.ccs.tencentyun.com/*******/de****est:cc-1.0",
"RegionName": "ap-guangzhou"
}
}
],
"ResourceConfig": {
"ScalingMode": "Manual",
"HardwareSpec": "spec-******1g",
"ManualInstanceConfig": {
"FixedInstanceCount": 1
},
"Concurrency": 1
},
"RequestPaths": [
"/predictions"
]
}
{
"Response": {
"ServiceId": "inf-xm*******fvt",
"RequestId": "815eada4-858c-45a7-8373-eadf09e6ab2e"
}
}
TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.
The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.
| Error Code | Description |
|---|---|
| InvalidParameterValue.InferenceServiceName | Incorrect inference service name format. |
| InvalidParameterValue.InferenceServiceNameDuplicate | Duplicated reasoning service name. |
| InvalidParameterValue.ZoneNotFound | No corresponding site. please ensure correct information entry. |
| LimitExceeded.InferenceService | The number of inference services has exceeded the limit. |
| OperationDenied | Operation denied. |
피드백