Help Center> ModelArts> Billing> Billing Items> Inference Deployment
Updated on 2023-11-30 GMT+08:00
View PDF

Inference Deployment

Description

Deploying a service in ModelArts uses compute and storage resources, which are billed. Compute resources are billed for running the inference service. Storage resources are billed for storing data in OBS. For details, see Table 1.

Table 1 Billing items

Billing Item

Description

Billing Mode

Billing Formula

Compute resource

Public resource pools

Usage of compute resources (vCPUs and GPUs)

For details, see ModelArts Pricing Details.

Pay-per-use

Specification unit price x Number of compute nodes x Usage duration

Dedicated resource pools

Fees for dedicated resource pools are paid upfront upon purchase. There are no additional charges for service deployment.

For details about fees for dedicated resource pools, see Dedicated Resource Pool.

N/A

N/A

Storage resource

Object Storage Service (OBS)

OBS is used to store the input and output data for service deployment.

For details, see OBS Pricing Details.

CAUTION:

OBS resources for storing data are continuously billed. To stop billing, delete the data stored in OBS.

Pay-per-use

Yearly/Monthly

Creating an OBS bucket is free of charge. You pay only for the storage capacity and duration you actually use.

Event notification (billed only when enabled)

This function uses Simple Message Notification (SMN) to send a message to you when the event you selected occurs.

To use this function, enable event notification when creating a training job.

For pricing details, see Simple Message Notification Pricing Details.

Pay by actual usage
  • SMS: SMS notifications
  • Email: Email notifications + Downstream Internet traffic
  • HTTP or HTTPS: HTTP or HTTPS notifications + Downstream Internet traffic

Run logs (billed only when enabled)

Log Tank Service (LTS) collects, analyzes, and stores logs.

If Runtime Log Output is enabled during service deployment, you will be billed if the log data exceeds the LTS free quota. For details, see LTS Pricing Details.

Pay by actual log size

After the free quota is exceeded, you are billed based on the actual log volume and retention duration.

Billing Example

The following prices are for reference only. For the actual prices, see pricing details for each service.

Example: Using a public resource pool; billing items: compute resources and storage

Assume that you create a real-time service that uses a public resource pool on April 1, 2023 at 10:00:00 and stop it at 11:00:00. The specifications are as follows: CPU: 8 vCPUs 32GB and one compute node. The unit price is $1.3023 USD/hour. The billing items are compute and storage resources. The fee for running this real-time service is calculated as follows:
  • Compute resource fee = $1.3023 USD/hour x 1 hour = $1.3023 USD
  • Storage fee: Training job data is uploaded to or exported from OBS. The storage fee is based on the OBS billing rules.

Fee for running the real-time service = Compute resource fee ($1.3023 USD) + Storage fee

Example: Using a dedicated resource pool; billing item: storage

Assume that you create a real-time service using a dedicated resource pool on April 1 at 10:00:00, 2023 and stop the job at 11:00:00. The billing item is storage. The fee for running the real-time service is as follows:
  • Storage fee: Training job data is uploaded to or exported from OBS. The storage fee is based on the OBS billing rules.

In conclusion, the fee for running the real-time service is equal to the storage fee.

Parent topic: Billing Items