Querying the Calling Data of a Service Version

Function

This API is used to query all versions of a service and their corresponding monitoring metric data. 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

POST /v1/{project_id}/maas/monitoring/{service_id}/list-version-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 IDs to be queried. Services are filtered based on the input service ID list. If this parameter is not specified, all service names corresponding to the IDs are returned. 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

Request Parameters

**Table 2** Request header parameter
Parameter	Mandatory	Type	Description
X-Auth-Token	No	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

**Table 3** Request body parameters
Parameter	Mandatory	Type	Description
api_keys	No	Array of strings	Definition: API key tag list, which is used for filtering. MaaS services support API key calls. Go to the API key management page to get the API key tag. The Tag field in the API key list shows the API key tag. Constraints: N/A Range: Example for obtaining the online experience call data: api_keys: [""]. When obtaining the call data of some API keys, transfer the tags of the corresponding API keys. Example: api_keys: ["test01","test02"]. Example for obtaining the call data of online experience and some API keys: api_keys: ["test01", "test02", ""]. When obtaining all call data, do not use this parameter. Default Value: N/A
ips	No	Array of strings	Definition: IP address list, which indicates the source IP addresses of the clients that have been called. If this parameter is not specified, all IP addresses are queried. To query the IP address, you can call the API for obtaining the IP address list. Constraints: The value must be in the IP address format. Range: N/A Default Value: N/A
start_time	Yes	Long	Definition: Timestamp of the start time, in milliseconds. Constraints: The end time must be within 30 days from the start time. Range: The value must be greater than 0 and no greater than the value of end_time. 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
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)
infer_type	Yes	String	Definition: Service inference type. Range: real_time: real-time inference batch: batch inference (Batch inference is under restricted use. To use it, submit a service ticket.) Constraints: N/A Default Value: N/A

Response Parameters

Status code: 200

**Table 4** Response body parameters
Parameter	Type	Description
total	Integer	Definition: Total number of queried versions. Range: N/A
count	Integer	Definition: Total number of queried versions. Range: N/A
items	Array of VersionStatItem objects	Definition: Version information list. Range: N/A

**Table 5** VersionStatItem
Parameter	Type	Description
service_id	String	Definition: Service ID. Range: N/A
version_id	String	Definition: Version ID. Range: N/A
version_name	String	Definition: Version name. Range: N/A
request_count	Integer	Definition: Number of calls. Range: N/A
error_count	Integer	Definition: Number of failed calls. If batch inference is used, this parameter indicates the number of failed inference times. However, batch inference is under restricted use. To use it, submit a service ticket. Range: N/A
error_rate	Double	Definition: Call failure rate. If batch inference is used, this parameter indicates the inference failure rate. However, batch inference is under restricted use. To use it, submit a service ticket. Range: 0 to 1
total_token	Double	Definition: Total number of called tokens, in thousands. If batch inference is used, this parameter indicates the total number of tokens. However, batch inference is under restricted use. To use it, submit a service ticket. Range: N/A
prompt_token	Double	Definition: Number of input tokens Range: N/A
completion_token	Double	Definition: Number of output tokens Range: N/A
avg_latency	Double	Definition: Average response time (ms) Range: N/A
avg_ttft	Double	Definition: Average TTFT (ms) Range: N/A
avg_tpot	Double	Definition: Average TPOT (ms) Range: N/A
completion_tasks_count	Integer	Definition: Number of completed tasks Range: N/A
infer_times	Integer	Definition: Total number of inference times. (This parameter is related to batch inference. However, batch inference is under restricted use. To use it, submit a service ticket.) Range: N/A
avg_consume_time	Double	Definition: Average task handling duration, in minutes. This parameter is related to batch inference. However, batch inference is under restricted use. To use it, submit a service ticket. Range: N/A
avg_generation_time	Double	Definition: Average generation duration (s), that is, the average time generating an image or video. Only video and image generation models are supported. Range: N/A
cache_token	Double	Definition: Number of cache hit tokens (in thousands). Range: N/A
cache_hit_ratio	Double	Definition: Cache hit rate, which is number of cache hit tokens/number of input tokens. Range: 0 to 1
scc_count	Integer	Definition: Number of successful calls. If batch inference is used, this parameter indicates the number of successful inference times. However, batch inference is under restricted use. To use it, submit a service ticket. Range: N/A
video_generate_duration	Double	Definition: Total duration of the generated video. Range: N/A
image_generate_nums	Integer	Definition: Total number of generated images. 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 version information and metric data of the real-time inference service whose service ID is {service-ID} in GMT+8.

/v1/{project_id}/maas/monitoring/{service_id}/list-version-statistics

{
  "start_time" : 1768406400000,
  "end_time" : 1769531307195,
  "timezone" : "Asia/Shanghai",
  "infer_type" : "real_time"
}

Response Example

Status code: 200

Success response

{
  "total" : 1,
  "count" : 1,
  "items" : [ {
    "service_id" : "4f6d50ec-0e80-4ea0-983b-d0ad1ede7596",
    "version_id" : "ac73463d-4453-4d62-a3d9-31b627a116b1",
    "version_name" : "Qwen2-7B-3.1",
    "request_count" : 6,
    "error_count" : 2,
    "error_rate" : 0.3333,
    "total_token" : 2.066,
    "prompt_token" : 0.277,
    "completion_token" : 1.789,
    "avg_latency" : 16439.75,
    "avg_ttft" : 326.46,
    "avg_tpot" : 29.58,
    "completion_tasks_count" : 0,
    "infer_times" : 0,
    "avg_consume_time" : 0,
    "avg_generation_time" : 0,
    "cache_token" : 0,
    "cache_hit_ratio" : 0,
    "scc_count" : 0,
    "video_generate_duration": 0,
    "image_generate_nums": 0
  } ]
}

Status code: 400

Failure response

{
  "error_code" : "ModelArts.0104",
  "error_msg" : "Invalid parameter. Issue: The end time cannot be earlier than the start time."
}

Status Codes

Status Code	Description
200	Success response
400	Failure response

Error Codes

For details, see Error Codes.

Parent Topic: MaaS Call Statistics

Previous topic: Querying Resource Monitoring Metric Details

Next topic: Obtaining the Metrics Supported by Different Model Types

Feedback

Was this page helpful?

Helpful Not helpful

Provide feedback

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

For any further questions, feel free to contact us through the chatbot.

Chatbot