
voyage-multimodal-3
Voyage AI's first all-in-one multimodal embedding model supporting interleaved text and content-rich images including screenshots, PDFs, slide decks, tables, and figures.
About this tool
Overview
voyage-multimodal-3 is Voyage AI's first multimodal embedding model that supports text and content-rich images such as screenshots of texts, figures, tables, PDFs, slide decks, and more.
Features
- Supports interleaved text and images in a single embedding
- Processes content-rich visual documents (PDFs, presentations, screenshots)
- Handles tables, figures, and complex document layouts
- Unified embedding space for text and visual content
- Optimized for document retrieval and multimodal search
Use Cases
- Document search across PDFs and presentations
- Visual question answering over documents
- Multimodal RAG applications
- Content-rich screenshot retrieval
- Technical documentation search
Pricing
API-based pricing with flexible usage tiers
Surveys
Loading more......
Information
Websiteblog.voyageai.com
PublishedMar 10, 2026
Categories
Tags
Similar Products
6 result(s)