voyage-multimodal-3.5
voyage-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities.
text + image → embedding · made by voyageai
$0.12per Mtok in
Nous Research · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Voyage AI api | standard | $0.12per Mtok indocs.voyageai.com · read 2026-08-25 |
| Nous Research aggregator | standard | $0.12per Mtok ininference-api.nousresearch.com · read 2026-09-12 |
About
voyage-multimodal-3.5 — a vectors model from voyageai, sold by 2 companies from $0.12 per Mtok in.
It takes text and images and returns vectors, with a context window of 32,000 tokens. The catalogue files it under embedding. Two companies sell it. The cheapest is $0.12 per Mtok in at Nous Research.
Every current figure
- Maker
- voyageai
- Register
- model
- Takes
- text + image
- Returns
- embedding
- Context
- 32,000 tokens
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.12 per Mtok in — Nous Research
Known as 2 names
voyageai/voyage-multimodal-3.5VoyageAI by MongoDB: voyage-multimodal-3.5