Mistral AI
·
1 year ago
Mistral introduced a batch API that processes high-volume requests asynchronously at 50% lower cost than synchronous API calls. The batch API is available today on La Plateforme for all Mistral models, with a usage limit of 1 million ongoing requests per workspace. Developers building applications prioritizing data volume over real-time responses can now reduce inference costs for tasks like document summarization, sentiment analysis, and vector embeddings.
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.
