EmbeddingGemma 300M · deepinfra

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.

Base modelAll models on this baseAll models of the providerto the provider

All Google Gemini models at every provider

Input, $/1M $0.002 ⚠

Output, $/1M —

Context 2 048

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —