Mistral-Large-4
Mistral AIwith multimodal input
coremodel architecturein Mistral Large 4Mistral AI
filed under model architecture
Accepts multimodal inputs including images; the evidence does not define a more specific processing mechanism.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.
Also called image input.
2 quotes from 2 sources, one card per model, each opening with its strongest.
with multimodal input
Since K3 accepts image input