Platform For AI:Machine Learning Designer billing

Overview

Machine Learning Designer algorithm components may incur fees for PAI algorithm components, PAI-DLC, or MaxCompute, depending on your usage. This topic uses PAI algorithm component fees as an example. For information about other fees, see DLC billing and MaxCompute billing. All prices are for reference only. Actual prices are specified on your bill.

Billable items

Billing methods

The unit price varies by algorithm type. The billing details are as follows:

• Formula: Bill amount = Number of billable hours × Unit price

  Number of billable hours = max(Number of CPU cores × Duration (h), Memory (GB) × Duration (h) / 4)

• Billing period: From when a component starts to when it stops.

• Billing example: Assume that you use a data analytics algorithm that consumes 2 CPU cores and 5 GB of memory for 1 hour and 30 minutes. The number of billable hours is max(2 × (1 + 30/60), 5 × (1 + 30/60) / 4) = 3. Therefore, the bill amount is Number of billable hours × Unit price = 3 × 0.21 = USD 0.63. The unit prices for different algorithm types are listed in the following table.

  Algorithm type	Unit price (USD/billable hour)	Description
  Data pre-processing (data_manipulation)	0.16	Data preprocessing and feature engineering components.
  Data analytics (data_analysis)	0.21	Statistical analysis, machine learning, time series analysis, network analysis, and finance components.
  Text analytics (text_analysis)	0.27	Text analytics components.
  Deep learning algorithm (deep_learning)	0.16	Deep learning components such as the CPU version of TensorFlow and EasyRec series algorithms.

  Note

  • If MaxCompute is enabled when you activate PAI, you are charged for MaxCompute when you use the SQL Script, JOIN, UNION ALL, or Filter and Map components.

  • If Flink is enabled when you activate PAI, you are charged for Flink when you use Alink components and select Flink as the compute resource.

Billing examples

A Machine Learning Designer experiment consists of multiple algorithm components, each containing multiple subtasks. To calculate the total cost, calculate the cost of each subtask and sum them.

1. Find the algorithm component category.

   1. Log on to the PAI console.

   2. In the upper-left corner, select a region.

   3. In the left-side navigation pane, choose Workspace List. Click the name of the target workspace.

   4. In the left-side navigation pane, choose Model Development and Training > Machine Learning Designer.

   5. On the Workflows page, select the target workflow and click Go to Workflow to open it.

   6. In the component list, find the PLDA component. This component belongs to the text analytics category, with a unit price of USD 0.27/billable hour.

      

2. View the resources consumed by each job.

   1. On the canvas, right-click the PLDA component.

   2. From the shortcut menu, select View Log.

   3. On the Log-PLDA page, each blue link corresponds to a subtask. Click a link to view details.

      

   4. On the LogView page, click the SourceXML tab.

   5. In the TaskPlan section, view the CPU and Memory values.

      • Divide the CPU value by 100 to get the number of CPU cores. In this example, the job used 1 CPU core.

      • The Memory unit is MB. In this example, the job used 1 GB of memory.

   6. On the LogView page, click the Job Details tab.

   7. Click the task object on the AlgoTask_0_0 tab. In the area that appears, click the Terminated tab. The Latency column indicates the runtime of each job.

      This subtask has 49 jobs, each running for about 26 seconds.

3. Calculate the cost of the subtask.

   1. Number of billable hours for the subtask = max(Number of CPU cores × Duration (h), Memory (GB) × Duration (h) / 4) = max(49 × 1 × (26 / 3600), 49 × 1 × (26 / 3600) / 4) ≈ 0.35 billable hours

   2. Cost of the subtask = Number of billable hours for the subtask × Unit price = 0.35 × 0.27 = USD 0.095

4. Calculate the costs of all subtasks in the PLDA component and sum them to get the total PLDA component cost.

5. Repeat the preceding steps for all components in the experiment and sum the costs to get the total experiment cost.