voyage-multimodal-3.5
Embeds text, images and interleaved content into one space.
voyage-multimodal-3.5 vectorises text and images — including content that interleaves them, such as screenshots of documents and slides — into a single vector space for multimodal retrieval.
- Provider
- Voyage AI (MongoDB)
- Type
- Embedding model
- Released
- Jul 27, 2026
- Context window
- 32K tokens
- Price
- $0.12 per 1M input tokens
- Input
- text, image
- Output
- embedding
- Open weights
- No
Best for
- Vision
- Multimodal
- Research
Strengths
- Interleaved text + image inputs
- Document screenshots without OCR
More from Voyage AI (MongoDB)
- voyage-4-large — Voyage AI (MongoDB). Voyage’s highest-quality general and multilingual retrieval embedding.
- voyage-code-4 — Voyage AI (MongoDB). Code-retrieval embedding built for coding agents.