Mistral Moderation API

Mistral AI · 1 year ago

Mistral AI released a content moderation API that classifies text into nine safety categories, using the same system that powers moderation in its Le Chat product. The model operates natively across 11 languages including Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish, with two endpoints for raw text and conversational content. Users can now integrate and customize the moderation tool to enforce their own safety standards across applications.