Skip to main contentMultimodal explained — Working with more than one content format
Processing formats such as text, images, audio or video. Supported inputs and outputs depend on the model and product.
An everyday example
You upload an error screenshot and ask in text which step to take next.
When you’ll encounter it
For image, recording or video tasks, check supported formats, file sizes and duration limits.
What to watch for
Reading images does not imply image generation or perfect visual accuracy. Small text, charts and spatial details may need checking.
Related terms & sources
Prepared from the public sources below. Examples illustrate the concept. Reviewed on 2026-10-15.