Pass IndexThe State of AISign in

Gemini Embedding 2 (Unified Multimodal, Preview)

Gemini Embedding 2 is Google's first multimodal embedding model, providing efficient numerical mapping of text, images, video, audio, and PDFs into a single unified embedding space.

text + image + audio + video + file → embedding · made by Google

$0.1per Mtok in
Google Vertex AI

Sold by 2 ways

SellerLaneRate
Google Vertex AI 0 ways$0.1
Google Vertex AI cloudnot on the seller's list todaybatch$0.1per Mtok incloud.google.com · read 2026-08-24
Google Vertex AI 0 ways$0.2
Google Vertex AI cloudnot on the seller's list todaystandard$0.2per Mtok incloud.google.com · read 2026-08-24

About

Gemini Embedding 2 (Unified Multimodal, Preview) — a vectors model from Google.

It takes text, images, audio, video and files and returns vectors, with a context window of 8,192 tokens. The catalogue files it under embedding.

Every current figure

Maker
Google
Register
model
Takes
text + image + audio + video + file
Returns
embedding
Context
8,192 tokens
Licence
not read