Next-generation multimodal embedding model built for retrieval over text, images, and videos, supporting Matryoshka embeddings with 4.56% higher accuracy than Cohere Embed v4 on visual document retrieval.
Loading more......
On this page
Voyage Multimodal 3.5
voyage-multimodal-3.5 extends Voyage's industry-leading multimodal capabilities to video retrieval. This represents a significant advancement in their multimodal embedding offerings, announced in January 2026.
voyage-multimodal-3.5 is a next-generation multimodal embedding model built for retrieval over text, images, and videos, with explicit support for video frames. It's the first production-grade video embedding model to support Matryoshka embeddings for flexible dimensionality.
Embeds interleaved text and images including:
Voyage multimodal embeddings are accessible in:
voyage-multimodal-3.5 attains:
The models are newly available on:
API-based pricing available through Voyage AI.
Explore more items related to this one