Pass IndexThe State of AISign in

embeddinggemma-300m

EmbeddingGemma is a 300M parameter multilingual open embedding model from Google DeepMind, designed for efficient deployment even on low-resource devices, producing high-quality text vector representations for tasks such as search, classification, clustering, and semantic similarity.

text → embedding · made by Google

$0.002per Mtok in
DeepInfra

Sold by 1 way

SellerLaneRate
DeepInfra aggregatorstandard$0.002per Mtok inapi.deepinfra.com · read 2026-08-25

Measured 1 standing

PlaceBoardMetricScore
29thof 86MTEB · Multilingual (MTEB(Multilingual, v2))meanTask (mean score, 0-1)0.6115

About

embeddinggemma-300m — a vectors model from Google, sold by one company from $0.002 per Mtok in, placed 29th of 86 on MTEB · Multilingual (MTEB(Multilingual, v2)).

It takes text and returns vectors, with a context window of 2,048 tokens. The catalogue files it under embedding. Only DeepInfra sells it, at $0.002 per Mtok in. It stands 29th of 86 on MTEB · Multilingual (MTEB(Multilingual, v2)).

Every current figure

Maker
Google
Register
model
Takes
text
Returns
embedding
Context
2,048 tokens
Licence
not read
Sellers
1
Maker's own price
not read
Price
$0.002 per Mtok in — DeepInfra
Boards
1
Best place
29th of 86 — MTEB · Multilingual (MTEB(Multilingual, v2))

Known as 1 name

google/embeddinggemma-300m