embeddinggemma-2
EmbeddingGemma 2 is a 740M parameter multimodal embedding model from Google DeepMind that maps text (incl.
text → embedding · made by Google
$0.02per Mtok in
DeepInfra
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra aggregator | standard | $0.02per Mtok inapi.deepinfra.com · read 2026-10-16 |
About
embeddinggemma-2 — a vectors model from Google, sold by one company from $0.02 per Mtok in.
It takes text and returns vectors, with a context window of 8,192 tokens. It was published in September 2026. The catalogue files it under embedding. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest. Only DeepInfra sells it, at $0.02 per Mtok in.
Every current figure
- Maker
- Register
- model
- Takes
- text
- Returns
- embedding
- Context
- 8,192 tokens
- Published
- September 2026
- Parameters
- 744 million · read from its own weights
- Licence
- apache-2.0
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.02 per Mtok in — DeepInfra
Known as 1 name
google/embeddinggemma-2