Deploy monitoring

更新时间：2025-07-02 15:32:25

Query base model resource monitoring information, including CPU, GPU (VRAM and computing power), and MEM (requires Prometheus deployment specialized for monitoring business Pods).

GET

https://api.alayanew.com/api/serverless-infer/v1/deployment/{serviceId}/resource/metrics

Authorizations

Authorizations：StringHeaderRequired

用户可通过已获取Open API Key做验证，例如：plain Credential=[YOUR_AK],Signature=[YOUR_SK]。

Path Parameters

serviceId：StringRequired

Service ID.

Response

状态码：

200

application/json

code：Int

The 'code' is a common return value format indicating the execution result of the query operation.

0

-1

0 is the success indicator, meaning the operation completed successfully.

data：Array

data. worker-0：Object

msg：StringRequired

Returns error information when the code value is -1.

cURL

Python

JavaScript

Go

Java

curl --location --request GET 'https://api.alayanew.com/api/serverless-infer/v1/deployment/38fbfc3d-6a88-4c35-b8b6-9efc83949d47/resource/metrics' 
     --header 'Authorization:plain Credential=YOUR_AK,Signature=YOUR_SK' 
     --header 'Content-Type: application/json'

200

400

401

403

404

500

{
    "code": 0,
    "data": {
        "ks-49eo39mdrmvjuqngw2cabuthw6lt5uma-00001": {
            "worker-0": {
                "mem": {
                    "total": 0.0146,
                    "rate": 212.3701,
                    "used": 3.1109
                },
                "cpu": {
                    "total": 7.0,
                    "rate": 0.0517,
                    "used": 0.3616
                }
            },
            "worker-1": {
                "mem": {
                    "total": 0.0146,
                    "rate": 174.9089,
                    "used": 2.5621
                },
                "cpu": {
                    "total": 7.0,
                    "rate": 0.0842,
                    "used": 0.5895
                },
                "gpu": {
                    "GPU-b61c1fde-9dba-e840-0b58-086ce93486e5": {
                        "mem": {
                            "used": 42.4805
                        },
                        "name": "gpu-l40s",
                        "utilization": {
                            "used": 0.0
                        }
                    }
                }
            }
        }
    }
}