Mistral 3 Large

Mistral Large 3, is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. It features 41B active parameters and 675B total parameters.

Model Specifications

Context window 256,000 tokens
Max output 16,384 tokens
Knowledge cutoff May 2025
Multipart messages Yes
Vision capabilities No

Default Parameters

Temperature 0.3
Top P 1.0
Frequency penalty 0.0
Presence penalty 0.0

More models from Mistral