Start building
The new Gemini Embedding model is now live in the Gemini API. Start building better Retrieval-Augmented Generation (RAG), classification, and search today.
It’s our most powerful and versatile text embedding model ever, achieving top-ranking scores on the Massive Text Embedding Benchmark (MTEB) leaderboard, and is priced at $0.15 USD per million tokens. Gemini Embedding supports 100+ languages and has a controllable embedding size.
You can generate text embeddings by using the embed_content method:
