The Quanmiao product matrix includes four SaaS products—Miaobi, Miaoce, Miaosou, and Miaodu—and several AI Agents (scenario-based capabilities). This document describes billing for the Network Content Moderation application within AI Agents.
Billing overview
When you call an API, usage is measured based on the selected Large Language Model (LLM) and the total number of output tokens. You are charged on a pay-as-you-go basis. For more information about the fees, see the Billing items document.
-
You can try this product for free on the 'Performance Debugging' page.
-
The base model can be scaled out and upgraded to ensure business stability and meet growing computing power demands. To scale out, contact us or join our DingTalk group (ID: 116015001424) for assistance.
Billing details
|
Model |
Input price |
Output price |
|
Qwen-Plus-Latest |
¥0.0008 per 1,000 tokens |
¥0.002 per 1,000 tokens |
|
Qwen-Plus |
¥0.0008 per 1,000 tokens |
¥0.002 per 1,000 tokens |
|
Qwen-Max-Latest |
¥0.0024 per 1,000 tokens |
¥0.0096 per 1,000 tokens |
|
Qwen-Max |
¥0.0024 per 1,000 tokens |
¥0.0096 per 1,000 tokens |
|
Qwen-Long |
¥0.0005 per 1,000 tokens |
¥0.002 per 1,000 tokens |
Bill-to address
View your bill at: Bill details.
Product link
Click product link to try the product.
References
Network Content Moderation API documentation
FAQ
-
How is billing calculated if a task fails midway?
If a task fails during execution, billing depends on the `event` in the last event message. If the event is `task-failed`, you are not charged. Otherwise, you are charged only for the parts of the task that completed successfully. The task is immediately stopped, and its status is displayed on the product client page.