When you need to filter content that is not suitable for display in your community or application, this endpoint can help you quickly complete the detection.

Overview

This endpoint can identify sensitive words in text and return whether they are hit, list of hit words and other results, suitable for comment sections, communities, forums and content publishing scenarios.

Key Features

- Fast Detection: Can process multiple hits in a whole paragraph of text at once

- Simplified/Traditional Support: Supports simplified Chinese, traditional Chinese and mixed text detection

- Intuitive Results: Returns clear detection results, convenient for direct integration into review processes

- Stable Response: Suitable for daily content moderation and batch checking scenarios

Whether it's a forum, social platform or comment system, this endpoint can help you quickly build content moderation functionality.