Multimodal
1 min read · Reviewed 17 Oct 2026
In short
A model that handles more than text — images, audio, documents.
In plain English
A model that can take in or produce several kinds of content: reading a photograph, listening to audio, describing a chart, as well as writing.
A real example
Photographing a handwritten flip chart and asking for it as a tidy list. The model is reading an image and producing text.
Why it matters
It removes a lot of retyping. It also widens what you might accidentally send: a screenshot can contain client data just as an email can.
