The Quanmiao product matrix includes four SaaS products (Miaobi, Miaoce, Miaosou, and Miaodu) and several AI Agents (scenario-based capabilities). This document describes the billing for the Composition Scoring application, which is one of the AI Agents.
Billing
You are billed based on the total number of input and output tokens generated by the models you use. This service is pay-as-you-go.
Activate the product and access the product console
- Activate the product: Go to the Composition Scoring activation page to activate the Composition Scoring service.
- Product console: Go to the product console to try the product.
Billing details
Model | Input price | Output price |
|---|---|---|
Composition Scoring Model 1 | ¥0.015/1,000 tokens | ¥0.015/1,000 tokens |
Composition Scoring Lightweight Model | ¥0.0015/1,000 tokens | ¥0.0015/1,000 tokens |
Custom Scoring Model | ¥0.0015/1,000 tokens | ¥0.0015/1,000 tokens |
Tongyi Qianwen-OCR model | ¥0.01/1,000 tokens | ¥0.01/1,000 tokens |
Tongyi Qianwen-OCR Lightweight Model | ¥0.0006/1,000 tokens | ¥0.0006/1,000 tokens |
FAQ
-
How is billing calculated if a task fails midway?
If a task fails during execution, billing depends on the
eventin the last event message. If the event istask-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.