title: "Più economico, migliore, più veloce, più forte | Mistral AI"

Mixtral 8x22B is a new open model from Mistral AI that establishes a new standard for performance and efficiency. It is a sparse Mixture-of-Experts (SMoE) model that uses only 39B active parameters out of 141B, offering significant cost efficiency for its size. The model is fluent in English, French, Italian, German, and Spanish, with strong capabilities in math, coding, and native function calling. Released under the permissive Apache 2.0 license, it demonstrates superior performance on various reasoning, knowledge, and multilingual benchmarks compared to other open models.