by OpenAI· Released August 2023
OpenAI's Moderation stable model is designed to detect harmful or unsafe content in text. It is optimized for accuracy and reliability in content moderation tasks, helping developers filter inappropriate material. This model is part of OpenAI's moderation endpoint and is the stable version recommended for production use.
Input cost
Free
Output cost
Free
Context window
8192 tokens
Max output
—
Modalities
License
proprietary
Classifying text for harmful or unsafe content across multiple categories.
