AI Wiki · Mediocre Security
Concept

Multimodal

A model that handles more than one type of input or output (text, images, audio, video) rather than text only.

A multimodal model handles several data types. Gemini was natively multimodal from 1.0; 2026 examples include Kimi’s text/image/video models, LongCat-2.5, Cloudflare’s vision-capable Clef, and voice-native models such as Grok Voice 3.0 and Block Dessa.

Timeline

Every dated event in the wiki that involves Multimodal, newest first.

Connections

Multimodal and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Model family Gemini · GPT

Concept Large language model (LLM)

Sources

  1. Wikipedia, “Multimodal learning”