Using the Zhuque Model
This document describes how to call the Zhuque AIGC detection model through Tencent Cloud EdgeOne Makers to identify AI-generated content.
Overview
Zhuque is Tencent's capability for AIGC content detection, which can determine whether text or images are AI-generated. After unified integration through EdgeOne Makers built-in models, you can directly call the text detection capability (@makers/zhuque-text).
Note:
1. Currently, only text detection is supported, and image detection is not yet supported.
2. The monthly free quota is 500,000 tokens. To try it through the website, visit the Zhuque AI Detection Assistant official website.
3. If you need image detection capabilities, or if the free quota cannot meet your call volume, please contact us to apply for an enterprise-exclusive plan.
Operation Steps
Step 1: Creating an API Key
1. Log in to the EdgeOne console.
2. After you go to the console, the page is automatically located at Makers - Models - API Key.
3. Click Create API Key, enter a name and confirm. After creation, keep the Key secure.
Step 2: Calling the Model
You can see
@makers/zhuque-text in the built-in model list on the Models and Keys page, marked as a built-in model.
Request parameters:
Parameter | Position | Type | Required | Description |
text | Body | string | Yes | Text content to be detected |
is_merge | Body | bool | No | Whether to merge paragraphs. Defaults to true. When set to false, confidence is output independently for each paragraph. |
curl example:
curl -i -X POST "https://ai-gateway.edgeone.link/v1/providers/zhuque-text/classify" \-H "Authorization: Bearer $MAKERS_MODELS_KEY" \-H "Content-Type: application/json" \-d '{"text": "hello world","is_merge": true}'
Response example:
{"status": "success","softmax_confidence": 0.0019,"ratio_confidence": 0,"labels_ratio": {"0": 1, "1": 0, "2": 0},"segment_labels": [{"text": "hello world", "label": 0, "conf": 0.0019, "order": 1, "position": [0, 11]}],"usage": {"total_tokens": 50},"msg": "","makers_models_usage": {"total_tokens": 30}}
Response field description:
Field | Type | Description |
status | string | Inference status. success indicates success. |
labels_ratio | object | Proportion of each content type. "0" indicates the proportion of Human content, "1" indicates the proportion of AI content, "2" indicates the proportion of suspected AI content, and all values fall within [0, 1]. |
ratio_confidence | float | Proportion of overall suspected risky content. A higher value indicates a greater probability of hitting risky content. |
segment_labels | array | Type labels and confidence of each segment. |
softmax_confidence | float | Overall confidence. A higher value indicates a greater probability of hitting risky content. |
usage.total_tokens | int | Usage statistics of the Zhuque model, indicating the number of characters in this call. |
msg | string | Error message. Empty when normal. |
makers_models_usage.total_tokens | int | Number of Makers free quota tokens actually deducted for this call. Use this field for free quota calculation. |
Viewing Model Usage
Go to the Makers Overview page. In the Model Usage Overview section, select Built-in Models to view usage details.
