Activation

Unduh

Mode fokus

Ukuran font

Terakhir diperbarui: 2026-09-16 17:46:47

Diterjemahkan oleh AI

Feature Overview
Activation provides a centralized view and management of all models and tools on the platform that must be enabled before use. The following operations are supported:
View the free trial models available to the current account, the remaining free quota claimed, and the expiration time.
You can claim free trial packages for models individually or in batches.
You can enable or disable pay-as-you-go billing for models or tools individually or in batches.
View the rate limiting quota for each model.
Page structure
Note:
Operations on the Activation page take effect only on the "default" service in "Online Inference". This service is automatically created by the platform after you claim a free trial package and shares the same name as the model. It does not affect the "custom" inference services that you manually create in "Online Inference". To configure billing, rate limiting, and other policies for custom services, go to the Online Inference page.
The Activation page contains two tabs:
Tab
Managed Object
Models
Various large models supported by the platform (language, vision, multimodal understanding, vector, speech models), managing the pay-as-you-go billing for their free trial packages and default model services.
Tools
Various tool capabilities provided by the platform, managing their enablement status and pay-as-you-go billing.
Model Tab
The top of the page summarizes the overall enablement status of the current account in the form of cards, which is divided into two parts:
Free Trial Package
Display the "claimable free models / total models" quantity and the "expiring soon" quantity.
A Claim Free Resources button is provided. Clicking it opens a batch claim dialog. For details, see New User Free Trial Package.
Pay-as-you-go
Display the number of models with pay-as-you-go billing enabled/disabled.
A one-click enable and one-click disable button is provided. Clicking it opens a batch operation dialog.
Model List
The list supports filtering by tabs for language models / vision models / multimodal understanding models / embedding models / speech models. It is divided into three sections: "Model Information", "Free Trial", and "Pay-as-you-go".
Model Information
Column
﻿
Description
Model Name
﻿
Click a model name to go to the corresponding default inference service details. If the free package has not been claimed for the model, the default inference service endpoint has not been created, and the jump cannot be performed.
Model Rate Limiting
﻿
Displays the TPM / RPM quota of the model.
Status
Running
Indicates that the default model service is running normally.
﻿
Not Enabled
Indicates that a model with free quota has not claimed the free trial package, or a model without free quota has not enabled pay-as-you-go billing.
﻿
Stopped
Indicates that the default model service has been stopped. This may occur when the free quota is exhausted but pay-as-you-go billing is not enabled, or when the account has an overdue payment.
﻿
Creating
In the process of claiming the free package or enabling pay-as-you-go billing.
﻿
Running (Model Pending Deprecation)
Indicates that the default model service is running normally, but the model is about to be taken offline.
﻿
Running (Model Under Maintenance)
Indicates that the default model service is running normally, but the model is under maintenance.
Free Trial
Column
Description
Claim Status
Unclaimed: You can click the button to claim the free trial package for this model.
Claimed: The button is grayed out and cannot be used to claim again.
Not Supported: This model does not support free trials. To use it, enable pay-as-you-go billing.
Free quota balance
Displays the remaining free quota for claimed models in the form of remaining percentage + progress bar.
Hover over the progress bar to view details: free quota tokens, consumed tokens, remaining tokens, and remaining percentage %. Models that are not claimed / not supported are not displayed.
Free quota expiration time
Displays the expiration time of the free quota. Not displayed for models that are not claimed / not supported.
Note:
Remaining Quota Alarm:
When the remaining free quota percentage is less than 20%, the remaining quota progress bar turns red.
When the validity period has less than 7 days remaining, the expiration time column displays "7 days remaining" in red text.
Pay-as-you-go
Column
Description
Enabling Status
Not Enabled: You can click the button to enable pay-as-you-go billing for this model.
Enabled: You can click the button to disable pay-as-you-go billing for this model.
A secondary confirmation dialog box pops up for both enabling and disabling.
Billing Mode
Currently supports token-based billing. For models that do not have pay-as-you-go billing enabled, this column does not display information.
Note:
If a model has an unclaimed free trial package and you directly enable pay-as-you-go billing for it, the platform automatically claims the free trial package for that model, and the "Claim Status" changes to "Claimed". During invocation, the platform prioritizes the consumption of free quota, and after the quota is exhausted, billing is based on tokens.
Tools Tab
This section manages the enabling and billing of various platform tools: Once enabled, a tool can be invoked. After pay-as-you-go billing is enabled, fees are deducted from your account balance based on actual usage.
Relationship with Online Inference
The Activation page works together with the Online Inference page, with the following division of responsibilities:
Page
Responsibilities
Activation
Model-level overview entry for viewing model lists, claiming free quotas, and enabling/disabling pay-as-you-go billing, helping users perform lightweight activation.
Online Inference Service
Service-level management entry. A model can have multiple inference services (1 default service with the same name + n custom services). You can create custom services, configure rate limiting and billing, and make API calls as needed.

Bantuan dan Dukungan

Apakah halaman ini membantu?

Anda juga dapat Menghubungi Penjualan atau Mengirimkan Tiket untuk meminta bantuan.

masukan

tencent cloud

LLM Service TokenHub

Activation

Feature Overview

Page structure

Model Tab

Model List

Tools Tab

Relationship with Online Inference

Bantuan dan Dukungan

Tab	Managed Object
Models	Various large models supported by the platform (language, vision, multimodal understanding, vector, speech models), managing the pay-as-you-go billing for their free trial packages and default model services.
Tools	Various tool capabilities provided by the platform, managing their enablement status and pay-as-you-go billing.

Column			Description
Model Name			Click a model name to go to the corresponding default inference service details. If the free package has not been claimed for the model, the default inference service endpoint has not been created, and the jump cannot be performed.
Model Rate Limiting			Displays the TPM / RPM quota of the model.
Status	Running	Indicates that the default model service is running normally.
		Not Enabled	Indicates that a model with free quota has not claimed the free trial package, or a model without free quota has not enabled pay-as-you-go billing.
		Stopped	Indicates that the default model service has been stopped. This may occur when the free quota is exhausted but pay-as-you-go billing is not enabled, or when the account has an overdue payment.
		Creating	In the process of claiming the free package or enabling pay-as-you-go billing.
		Running (Model Pending Deprecation)	Indicates that the default model service is running normally, but the model is about to be taken offline.
		Running (Model Under Maintenance)	Indicates that the default model service is running normally, but the model is under maintenance.

Column	Description
Claim Status	Unclaimed: You can click the button to claim the free trial package for this model. Claimed: The button is grayed out and cannot be used to claim again. Not Supported: This model does not support free trials. To use it, enable pay-as-you-go billing.
Free quota balance	Displays the remaining free quota for claimed models in the form of remaining percentage + progress bar. Hover over the progress bar to view details: free quota tokens, consumed tokens, remaining tokens, and remaining percentage %. Models that are not claimed / not supported are not displayed.
Free quota expiration time	Displays the expiration time of the free quota. Not displayed for models that are not claimed / not supported.

Column	Description
Enabling Status	Not Enabled: You can click the button to enable pay-as-you-go billing for this model. Enabled: You can click the button to disable pay-as-you-go billing for this model. A secondary confirmation dialog box pops up for both enabling and disabling.
Billing Mode	Currently supports token-based billing. For models that do not have pay-as-you-go billing enabled, this column does not display information.

Page	Responsibilities
Activation	Model-level overview entry for viewing model lists, claiming free quotas, and enabling/disabling pay-as-you-go billing, helping users perform lightweight activation.
Online Inference Service	Service-level management entry. A model can have multiple inference services (1 default service with the same name + n custom services). You can create custom services, configure rate limiting and billing, and make API calls as needed.