TAAFT
Free mode
100% free
Freemium
Free Trial
Prompts Deals
Companies
Voyage AI
Models
Voyage multimodal 3

Voyage multimodal 3

By Voyage AI
Model family: Voyage
voyage-multimodal-3 is a multimodal embedding model designed for RAG and semantic search across knowledge bases containing both text and visual data. Unlike CLIP-based models that process text and images through separate encoders, it runs all inputs through a single transformer backbone, enabling vectorization of interleaved text and images in a unified representation. This eliminates the modality gap that causes CLIP-based models to favor same-modality results over semantically relevant cross-modal ones.

The model supports screenshots of PDFs, slide decks, tables, charts, and figures, removing the need for heuristic-based parsing or OCR pipelines. In evaluations across 20 multimodal retrieval datasets, it outperforms OpenAI CLIP large and Cohere multimodal v3 by over 40% on table/figure retrieval and over 25% on document screenshot retrieval, while matching voyage-3 on pure text retrieval. Accessible via API with query and document input types for retrieval-optimized embeddings.
Multimodal
Released: November 12, 2024

Overview

Multimodal embedding model that vectorizes interleaved text and images through a unified transformer encoder. Supports screenshots of PDFs, slides, tables, and figures without complex document parsing. Unlike CLIP-based models, eliminates the modality gap, enabling accurate mixed-modality retrieval across text and visual content.

🔎Semantic search🔍Multimodal search🔍Image search

Pricing

Source

Compare Voyage multimodal 3 with other models listed in the same vendor pricing tiers and context lengths.

Tier

Standard

Model Input Cached input Output Unit
rerank 2.5 Voyage AI
$0.05 - $0 per 1M tokens
Rerank 2.5 lite Voyage AI
$0.02 - $0 per 1M tokens
Voyage 4 Voyage AI
$0.06 - $0 per 1M tokens
Voyage 4 large Voyage AI
$0.12 - $0 per 1M tokens
Voyage 4 lite Voyage AI
$0.02 - $0 per 1M tokens
Voyage code 2 Voyage AI
$0.12 - $0 per 1M tokens
Voyage code 3 Voyage AI
$0.18 - $0 per 1M tokens
Voyage context 3 Voyage AI
$0.18 - $0 per 1M tokens
Voyage finance 2 Voyage AI
$0.12 - $0 per 1M tokens
Voyage law 2 Voyage AI
$0.12 - $0 per 1M tokens
Voyage multilingual 2 Voyage AI
$0.12 - $0 per 1M tokens
Voyage multimodal 3 This model Voyage AI
$0.12 - $0 per 1M tokens
Voyage multimodal 3.5 Voyage AI
$0.12 - $0 per 1M tokens

About Voyage AI

Voyage AI provides best-in-class embedding models and rerankers for search and retrieval over unstructured data, used to power retrieval-augmented generation (RAG) and AI applications. It offers general-purpose, domain-specific (finance, legal, code) and company-specific fine-tuned models. Founded in 2023 and based in Palo Alto, the company was acquired by MongoDB, Inc. in February 2025 and now operates as a MongoDB subsidiary.

Industry: Artificial Intelligence
Location: Palo Alto, California, US
Website: voyageai.com
View Company Profile

Other models from this family

  • Voyage
    Voyage 4 large
    By Voyage AI
    voyage-4-large is a state-of-the-art general-purpose and multilingual text embedding model using a mixture-of-experts (MoE) architecture. It delivers frontier retrieval accuracy with serving costs 40% lower than comparable dense models. Features a 32K context window, flexible output dimensions (256, 512, 1024, 2048), and multiple quantization options including float, int8, uint8, binary, and ubinary.
    🔗Embeds🔍Text classification
    Text
    Released 6mo ago
  • Voyage
    Voyage multimodal 3.5
    By Voyage AI
    Multimodal embedding model that vectorizes interleaved text, images, and videos into a shared vector space for retrieval tasks. Uses a single transformer encoder for all modalities, eliminating the modality gap. Supports document screenshots, PDFs, slides, figures, tables, and video frames. Context window of 32,000 tokens with Matryoshka embeddings at 256, 512, 1024, and 2048 dimensions.
    🔗Embeds🔍Information retrieval🔎Search
    Multimodal
    Released 6mo ago
  • Voyage
    Voyage 4 lite
    By Voyage AI
    Lightweight, general-purpose text embedding model optimized for low latency and cost. Supports a 32K token context window and flexible output dimensions (2048, 1024, 512, 256) via Matryoshka learning. Offers multiple quantization formats including float, int8, uint8, binary, and ubinary. Part of the Voyage 4 series with a shared embedding space across models.
    🔗Embeds🔍Text classification
    Text
    Released 6mo ago
View all models from this family

Related Models

Last updated: July 8, 2026
0 AIs selected
Clear selection
#
Name
Task