# Multimodal Model

> A model that can take in text, photos and sound, not just one kind.

**Field:** Artificial Intelligence  
**Category:** LLMs  
**Also known as:** Multimodal LLM, MLLM

## Think of it like

Think of it like a friend you can show a note, a snap or a song. They get all of them.

## Definition

A multimodal model can take in more than one kind of data. That can be text, images, sound and video. Some can give out more than one kind too. Each kind is turned into tokens the model can read side by side. So you can show it a photo and ask a question about it in words. Many large chat assistants now work this way.

## Example

Lucy takes a photo of her broken washer. She asks what the red light means. The model reads the photo and her question together.

## Why it matters

Real problems come as photos, screens, voice and documents, not just typed text. These models can handle them in one place.

## Common mistake

Thinking it sees like a person. It can misread small text, count wrong or miss what is plain to a human eye.

## Three principles

- **Many kinds of data.** Text, image, sound, video.
- **All become tokens.** Read side by side.
- **One model.** Not a chain of tools.

## Related terms

- [Large Language Model (LLM)](https://learn.benibix.com/term/ai/large-language-model)
- [Token (AI)](https://learn.benibix.com/term/ai/token)
- [Generative AI](https://learn.benibix.com/term/ai/generative-ai)
- [Vision Language Model (VLM)](https://learn.benibix.com/term/ai/vision-language-model)
- [Vision-Language-Action Model (VLA)](https://learn.benibix.com/term/ai/vision-language-action-model)
- [Gemini](https://learn.benibix.com/term/ai/gemini)
- [Contrastive Language-Image Pre-Training (CLIP)](https://learn.benibix.com/term/ai/clip-model)

## Taught in

- [Open-Weight vs Closed Models](https://learn.benibix.com/learn/ai-llms/open-weight-vs-closed-models): LLMs, 11/15

![Text, an image and a sound clip all go into one model. Text and an image come out.](https://learn.benibix.com/diagrams/llm-multimodal.svg)

---

Source: https://learn.benibix.com/term/ai/multimodal-model
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
