G

Google: embeddinggemma-300m

embeddinggemma-300m:free
2.0K contextembedding
Released Sep 4, 2025Updated Jun 21, 2026

EmbeddingGemma is a 308M parameter multilingual text embedding model from Google, trained on 100+ languages and designed to run on device. It outputs 768 dimensional embeddings with Matryoshka truncation to 512, 256 or 128 dimensions.

Mode embedding

Inputs used for the providers' own purposes

At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.

Read the privacy policy

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 2.0K tokensCompatible endpoints openai, embeddingVendor Google
GroupInputOutputTTFTSuccessUptimeCache hit
lf1-embeddinggemma-300m-free$0.00$0.00----
lf2-embeddinggemma-300m-free$0.00$0.00----
cf1-embeddinggemma-300m-free$0.00$0.00----

Uptime

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Frequently asked questions

Use embeddinggemma-300m in

Similar models