Subscribing to Built-in Services

Constraints

• This function is available only in the CN-Hong Kong region.
• Subscribing to a built-in service will subscribe all versions of the service. You cannot subscribe to just one version alone.
• Currently, built-in services cannot be disabled.

Billing

Model inference services process input by converting it into identifiable tokens. Using a built-in MaaS service charges you based on token count. For details, see Inference Service Billing Items.

Coupon Instructions

• When there is a discount offer, a relevant prompt will appear on the built-in service page. When subscribing to a built-in service, available coupons will be claimed by default. During the billing process, coupons will be applied first.
• The scope of application and eligibility criteria for different coupon activities vary. Whether you can successfully claim a coupon depends on the actual activity rules.
• For information on the issuance and usage of discount coupons for model services, go to Billing Center > Promotions > Coupons.

Service Calls

The platform can send requests to different regions as needed.

Subscribing to Built-in Services

1. Log in to the MaaS console and select the target region on the top navigation bar.
2. In the navigation pane on the left, choose Model Inference > Real-time inference.
3. Click the Built-in Services tab. In the Operation column of the target service, click Subscribe.
4. Select the built-in service as required. Select I have read and agree to the above terms and MaaS Service Statement and click Subscribe. The model experience page is displayed.

   Selecting a built-in service will subscribe all model versions of the service.

   The service list is organized by model series, with built-in services shown first. Within each model, services are sorted by creation time in descending order. The following table describes the parameters in the built-in service list.

   Table 1 Built-in service list parameters

   Parameter	Description
   Name/Resource ID	Name and ID of the built-in service. Click on the left of the service name to view the service version. The name displayed in the model Parameter column can be used for model calls. Figure 1 Viewing the model version Click the version name to go to the Model Description page and view details about the model version. Viewing the service bill: Click after the built-in service ID to copy the ID. On the Billing > Expenditure Details page of the Billing Center, view the bill details by resource ID.
   Subscription Status	Subscribed: The built-in service is enabled. Not Subscribed: The built-in service is not enabled.
   Type	Type of the built-in service
   Billing Mode	Billing mode of the built-in service. The billing mode varies depending on the model. For details, see Billing Items.
   Infer Price	Inference pricing of the built-in service. The inference pricing varies depending on the model. For details, see Billing Items. In the upper right corner of the page, enable or disable Million tokens unit display. Figure 2 Million tokens unit display If Million tokens unit display is disabled, the price is displayed by thousand tokens. If Million tokens unit display is enabled, the price is displayed by million tokens.
   Discounts	Discounts available for the built-in service. -- indicates that there is no discount.
   Model flow limiting	Total quota for accessing all services under the same model within the current account. TPM: The number of tokens processed per minute, including both input and output. RPM: The number of requests processed per minute.
   Call Statistics	Click to go to the Service Call Details page and view the call data and monitoring metric details of the built-in service in a specified period. For more information, see Viewing the Call Data and Monitoring Metrics of Real-Time Inference on MaaS.
   Operation	Operations supported by the built-in service Unsubscribe: If this button is unavailable, the service cannot be disabled. No fee is generated when the service is not used. View Call Description: See Calling a Built-in Service. Try: See Trying Built-in Services. ModelArts Guard: Configure content guard if you have a V2 or higher account level. After built-in services are enabled, ModelArts Guard is enabled by default. . NOTE: To view your account level, log in to the MaaS console, click the username in the upper right corner, click Basic Information, and view the level next to the account name. ModelArts Guard blocks harmful content in inputs and outputs during model inference. Enabling it might slow down processing. When disabled, the models rely on their native security features. To enable ModelArts Guard, click More and select Enable ModelArts Guard. In the displayed Enable ModelArts Guard dialog box, read the note and click OK. To disable ModelArts Guard, click More and select Disable ModelArts Guard. In the displayed Disable ModelArts Guard dialog box, read the note, select I have read and agree to the above terms and Content Moderation Disclaimer, and click OK.

Calling a Built-in Service

1. Click View Call Description in the Operation column of the subscribed built-in service. Select a version.
2. On the View Call Description panel, call the built-in service as prompted.
   • For details about how to obtain an API key, see Managing API Keys.
   • API parameters vary depending on the model type. For details, see MaaS API Call Specifications.
   • If an error occurs when you call a built-in service, locate the fault by referring to Error Codes.

Trying Built-in Services

Click More and select Try in the Operation column of the subscribed built-in service, and select a version.

If Try is not displayed, the built-in service does not support this operation. You can use an API to call the built-in service. For details, see Calling a Built-in Service.

Traffic Control Rules

To ensure fairness in users' calls to the model, MaaS has set up basic traffic limiting. If the limit is exceeded, API requests will fail, and you will need to wait until the traffic limiting conditions are lifted before making another call.

• Tokens Per Minute (TPM): The number of tokens (input + output) processed per minute.
• Requests Per Minute (RPM): The number of requests processed per minute.

It is recommended that you send API requests evenly to avoid sending a large number of requests in a short period. Rate limiting policies may be enforced based on QPS (RPM/60). Even if the total request volume is below the per-minute limit, sending a large burst of requests in a short period may trigger rate limiting. This will result in request failure and the return of error code ModelArts.81101 (Too Many Requests). For details about error codes, see Error Codes.

About Arrears

If you are in arrears when using a model service, the resource is frozen and enters the grace period. The resource status changes to Frozen. At this point, the frozen resources cannot be used, and new models that have not been subscribed to will not be supported for subscription.

Both the grace and retention periods are 15 days. After the retention period expires, if you still have not paid the account arrears, the related resources and order records under your account for this model will be cleared, and the data cannot be recovered. To use the model service again, pay off the outstanding amount and subscribe to the model service again.

Check your account balance and top up your account in time to ensure stable online services.

Figure 3 Periods of pay-per-use resources

FAQs

• Is there any billing example?

  For details about billing items and examples, see Prices of Real-Time Inference Model Services.

• Can a built-in service be disabled after subscription?

  Built-in services cannot be disabled. No expenditures are generated for unused services.

• What should I do if the subscription status is frozen when I use a built-in service?

  For details about how to handle the frozen status, see What Should I Do If the Subscription Status is Frozen When I Use a Built-in Service?

• What should I do if the subscription status is invalid when I use a built-in service?

  If the subscription status is invalid, the resource has been frozen due to arrears and the resource retention period has expired. You can subscribe to the built-in service again.