• Home
  • Categories
  • Tags
  • Pricing
  • Submit
    Decorative pattern
    1. Home
    2. Machine Learning Models
    3. voyage-multimodal-3

    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.

    🌐Visit Website

    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

    1 Item
    Machine Learning Models

    Tags

    3 Items
    #Multimodal#Embeddings#Visual Search

    Similar Products

    6 result(s)
    ColPali
    Featured

    State-of-the-art image-based multi-vector retrieval model for PDF documents, enabling effective document search without text extraction by processing visual document representations.

    BGE-VL
    Featured

    State-of-the-art multimodal embedding model from BAAI supporting text-to-image, image-to-text, and compositional visual search. Trained on the MegaPairs dataset with over 26 million retrieval triplets.

    Cohere Embed v4

    Multilingual, multimodal enterprise embedding model supporting over 100 programming languages and primary business languages with advanced quantization for cost optimization.

    Mastering Multimodal RAG

    A course focused on mastering multimodal Retrieval Augmented Generation (RAG) and embeddings, which are fundamental components often stored and managed by vector databases.

    ColBERTv2
    Featured

    Advanced multi-vector retrieval model creating token-level embeddings with late interaction mechanism, featuring denoised supervision and improved memory efficiency over original ColBERT.

    pinecone-sparse-english-v0
    Featured

    Learned sparse embedding model built on DeepImpact architecture, outperforming BM25 by up to 44% on TREC benchmarks for high-precision keyword search and hybrid retrieval.

    Decorative pattern
    Built with
    Ever Works
    Ever Works

    Connect with us

    Stay Updated

    Get the latest updates and exclusive content delivered to your inbox.

    Product

    • Categories
    • Tags
    • Pricing
    • Help

    Clients

    • Sign In
    • Register
    • Forgot password?

    Company

    • About Us
    • Admin
    • Sitemap

    Resources

    • Blog
    • Submit
    • API Documentation
    All product names, logos, and brands are the property of their respective owners. All company, product, and service names used in this repository, related repositories, and associated websites are for identification purposes only. The use of these names, logos, and brands does not imply endorsement, affiliation, or sponsorship. This directory may include content generated by artificial intelligence.
    Copyright © 2025 Awesome Vector Databases. All rights reserved.·Terms of Service·Privacy Policy·Cookies