Mistral AI's model family. Mistral pioneered the efficient small-model approach with Mixtral MoE. The Large and Small variants cover enterprise and edge use cases respectively. Magistral adds reasoning capabilities.
chatfast
pros
efficient architecture (MoE)
open weights on some variants
strong European language support
good function calling
cons
not frontier-tier on latest benchmarks
smaller than competitors
can struggle with very long contexts
use this model on surp.ivc.lol
Reference this model in a custom combo to always get the cheapest price for it: