Help Center/ MaaS/ API Reference/ MaaS Call Statistics/ Querying Resource Monitoring Metric Details
Updated on 2026-08-11 GMT+08:00

Querying Resource Monitoring Metric Details

Function

This API is used to obtain the resource metric information of My Services in the MaaS real-time inference module. Data is retained for 30 days only.

Constraints

  • Region restrictions: Only the CN-Hong Kong region is supported.
  • API rate limiting: The total number of requests for this API from all users cannot exceed 1,000 within one minute.
  • User request limit: The number of requests for this API from a single user cannot exceed 200 within one minute.
  • Rate-limiting response: When the rate limit is exceeded, the API returns the HTTP status code 429 "Too Many Requests".
  • Retry suggestion: If the rate limit is exceeded, wait 60 seconds and try again.

URI

GET /v1/{project_id}/maas/monitoring/{service_id}/detail-statistics

Table 1 URI parameters

Parameter

Mandatory

Type

Description

project_id

Yes

String

Definition: Project ID. For details about how to obtain the project ID, see Obtaining a Project ID and Name.

Constraints: N/A

Range: The value can contain 32 characters. Only lowercase letters and digits are allowed.

Default Value: N/A

service_id

Yes

String

Definition: Service ID. You can obtain the service ID from the response body during service creation, or call the API for obtaining the service list. The service_id field indicates the service ID.

Constraints: N/A

Range: The value can contain 1 to 128 characters. Only letters, digits, underscores (_), and hyphens (-) are allowed.

Default Value: N/A

Table 2 Query parameters

Parameter

Mandatory

Type

Description

start_time

Yes

Long

Definition: Timestamp of the start time, in milliseconds.

Constraints: The value must be less than or equal to that of end_time. The difference between the end time and the start time must be less than 30 days.

Range: The value must be greater than 0.

Default Value: N/A

end_time

Yes

Long

Definition: Timestamp of the end time, in milliseconds.

Constraints: The end time must be within 30 days from the start time.

Range: The value must be greater than 0.

Default Value: N/A

metric_name

Yes

String

Definition: Metric name.

Constraints: N/A

Range:

  • npu_util: NPU compute usage
  • cpu_usage: CPU usage
  • mem_usage: memory usage
  • npu_mem_usage: NPU memory usage
  • disk_read_rate: disk read rate
  • disk_write_rate: disk write rate
  • recv_bytes_rate: downlink rate
  • send_bytes_rate: uplink rate
  • running_task: number of running requests
  • pending_task: number of pending requests
  • kv_cache_usage: KV cache usage
  • prompt_tps: input TPS
  • completion_tps: output TPS

Default Value: N/A

timezone

No

String

Definition: Time zone.

Constraints: N/A

Range: The value must comply with the IANA time zone specifications, such as Asia/Shanghai and UTC.

Default Value: Asia/Shanghai (GMT+8)

model_id

Yes

String

Definition: Model ID. To obtain the model ID, log in to the MaaS console. In the navigation pane on the left, choose Model Inference > Real-Time Inference. In the My Services tab, click the service name. On the displayed details page, press F12 and access the Network tab. Then, view the value of model_id in the response body of the models API.

Constraints: N/A

Range: N/A

Default Value: N/A

Request Parameters

Table 3 Request header parameter

Parameter

Mandatory

Type

Description

X-Auth-Token

Yes

String

Definition: User token. It can be obtained by calling the IAM API that is used to obtain a user token. The value of X-Subject-Token in the response header is the user token. For details, see Authentication.

Constraints: N/A

Range: N/A

Default Value: N/A

Response Parameters

Status code: 200

Table 4 Response body parameters

Parameter

Type

Description

points

Array of DataPoint objects

Definition: Data point of a monitoring metric, including the metric value and reporting timestamp.

Range: N/A

metric_name

String

Definition: Metric name.

Range:

  • npu_util: NPU compute usage
  • cpu_usage: CPU usage
  • mem_usage: memory usage
  • npu_mem_usage: NPU memory usage
  • disk_read_rate: disk read rate
  • disk_write_rate: disk write rate
  • recv_bytes_rate: downlink rate
  • send_bytes_rate: uplink rate
  • running_task: number of running requests
  • pending_task: number of pending requests
  • kv_cache_usage: KV cache usage
  • prompt_tps: input TPS
  • completion_tps: output TPS

unit

String

Definition: Metric unit.

Range: N/A

Table 5 DataPoint

Parameter

Type

Description

val

Double

Definition: Metric value.

Range: N/A

time

Long

Definition: Timestamp, in milliseconds.

Range: N/A

Status code: 400

Table 6 Response body parameters

Parameter

Type

Description

error_code

String

Definition: Error code, which identifies the error type. For details, see MaaS Error Codes.

Range: N/A

error_msg

String

Definition: Error description. For details, see MaaS Error Codes.

Range: N/A

Request Example

Query the output TPS of the service whose service ID is {service_id} and model ID is 29f474eb-67bc-4a7c-9771-c98c568c1c8c from 1769532157287 to 1769535757287.

/v1/{project_id}/maas/monitoring/{service_id}/detail-statistics?start_time=1769532157287&end_time=1769535757287&metric_name=completion_tps&model_id=29f474eb-67bc-4a7c-9771-c98c568c1c8c&timezone=Asia/Shanghai

Response Example

Status code: 200

Success response

{
  "points" : [ ],
  "metric_name" : "running_task",
  "unit" : "num"
}

Status code: 400

Failure response

{
  "error_msg" : "Database error.",
  "error_code" : "ModelArts.2010"
}

Status Codes

Status Code

Description

200

Success response

400

Failure response

Error Codes

For details, see Error Codes.