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
| Seller | Lane | Rate |
|---|---|---|
| Google Vertex AI 0 ways | $0.1 | |
| Google Vertex AI cloudnot on the seller's list today | batch | $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 today | standard | $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
- Register
- model
- Takes
- text + image + audio + video + file
- Returns
- embedding
- Context
- 8,192 tokens
- Licence
- not read