Models🤖
Mistral Large 4 (1T-A52B)
Released Sep 30, 2026
Mistral's largest open-weight model: natively multimodal MoE with 1 trillion total parameters, ~49B active per token (52B including embeddings and output), up to 1M-token context. Trained from scratch on 3,800 NVIDIA Grace Blackwell. Mistral Ecosystem Open-Weight License (a modified MIT): commercial use ok; a Model-as-a-Service business requires a separate commercial license.
LLMMistralMoEMultimodaleOpen Source

