embeddinggemma-2 · deepinfra

EmbeddingGemma 2 is a 740M parameter multimodal embedding model from Google DeepMind that maps text (incl. code), images, video and audio, alone or interleaved, into a single 768-dimensional vector space, with task prompts and Matryoshka truncation to 512, 256 or 128 dimensions for search, retrieval, classification and clustering.

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

All Google Gemini models at every provider

Input, $/1M $0.02

Output, $/1M —

Context 8 192

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —