Tech · Releases
voyage-multimodal-3.5: a new multimodal retrieval frontier with video support
Thu, January 15, 2026
10 mo agoUnverified
The voyage-multimodal-3.5 model adds support for embedding video frames alongside text and images. It also supports Matryoshka embeddings for flexible dimensionality.
Every year
Introducing the Batch API: Simpler and more efficient for large-scale workloadsvoyage-aiAn event.11 mo agovoyage-aiDetails →
voyage-multimodal-3.5: a new multimodal retrieval frontier with video supportvoyage-aiAn event.10 mo agovoyage-ai
Announcing New Models and Expanded Availabilityvoyage-aiAn event.10 mo agovoyage-aiDetails →The Voyage 4 model family: shared embedding space with MoE architecturevoyage-aiAn event.10 mo agovoyage-aiDetails →voyage-context-4: stop worrying about chunking with our best-performing modelvoyage-aiAn event.4 mo agovoyage-aiDetails →voyage-code-4: code retrieval built for coding agentsvoyage-aiAn event.3 mo agovoyage-aiDetails →rerank-3 and rerank-3-lite: the next generation of Voyage rerankersvoyage-aiAn event.40 days agovoyage-aiDetails →Also on Jan 15, 2026
Source, method and history
- Source
- voyage-ai
- How we know
- From the Releases API (releases.fru.dev), which reads each vendor's changelog.
- Who
- voyage-ai
- Recurs
- one-off
- More on Glyph
- releases.fru.dev
- Feed
- Subscribe to Releases
- Changes
- 2026-10-27: added to 2026-01-15