Pass IndexThe State of AISign in

Doubao-embedding-vision

Doubao-embedding-vision is ByteDance's multimodal embedding model.

text + image + video → embedding · made by ByteDance

$0.1per Mtok in
ByteDance

Sold by 1 way

SellerLaneRate
ByteDance apistandard$0.1per Mtok in$0.27per Mtok in, imagevolcengine.com · read 2026-08-25

About

Doubao-embedding-vision — a vectors model from ByteDance, sold by one company from $0.1 per Mtok in.

It takes text, images and video and returns vectors, with a context window of 131,072 tokens. The catalogue files it under embedding. Only ByteDance sells it, at $0.1 per Mtok in.

Every current figure

Maker
ByteDance
Register
model
Takes
text + image + video
Returns
embedding
Context
131,072 tokens
Sellers
1
Price
$0.1 per Mtok in — ByteDance

Known as 1 name

doubao-embedding-vision-251215