Gemini-Embedding-001 is Google’s multilingual embedding model, supporting over 100 languages and flexible output dimensions (3072, 1536, or 768), across domains including science, legal, finance, and coding. It is optimized for semantic search, clustering, and recommendations, uses Matryoshka Representation Learning for efficient, high-quality embeddings, and has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard.
$0.075
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Daily usage of this model on NagaAI.
Gemini-Embedding-001 is Google’s multilingual embedding model, supporting over 100 languages and flexible output dimensions (3072, 1536, or 768), across domains including science, legal, finance, and coding.
On NagaAI, Gemini Embedding 001 costs $0.075 per 1M tokens. You pay only for what you use, with no subscription.
It takes text as input and returns embeddings.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI SDK pointed at NagaAI. The API section on this page has a ready example.
