Google: Gemini Embedding 2 (batch)
google/gemini-embedding-2:batch- Modalities
- text+image+file+audio+video->embeddings
- In / out price
- $0.1 / $0
- Context
- 8K
- Released
- May 20, 2026
- Knowledge cutoff
- —
per 1M
The playground sends chat/completions only. This model outputs Embeddings, so a chat turn may not return what you expect.
Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports...
VisionAudioVideoEmbeddings
Supported parameters
This model does not publish a parameter list.