Tech media outlet WinBuzzer published a blog post on Nov. 8 thatReports said Mistral AI Company Launches New Content Audit API, to meet the growing demand for secure online environments.
Citing a press release, the content review API is based on the fine-tuned Ministral 8B model, which can categorize content into nine categories such as hate speech, violence and personal data breaches.
The Content Audit API supports 11 languages - Chinese, Arabic, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish - for processing raw text and analyzing conversational content.
Mistral also introduced the Mistral Batch API, designed for companies that need to process large amounts of data. This feature allows for asynchronous content processing, which Mistral claims can reduce processing costs by 251 TP3 T. This feature appeals to companies looking to optimize their operations and further strengthens Mistral's competitive position in the market.