Magistral | Mistral AI

This post announces Magistral, Mistral AI's first reasoning model family. It details two variants: Magistral Small (24B, open-source, Apache 2.0) and Magistral Medium (enterprise). Key features include domain-specific reasoning, transparent chain-of-thought across languages, and optimized speed (10x faster token throughput for Medium in Le Chat). Performance metrics on AIME2024 are provided. The post also references a supporting research paper and highlights applications in business strategy, regulated industries, systems engineering, and content creation.