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.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Todos os modelos Google Gemini em todos os provedores

Entrada, $/1M $0.002 ⚠

Saída, $/1M —

Contexto 2 048

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —