gemini-embedding-2
Google's first multimodal embedding model. Supports text, images, video, audio, and PDF documents in a unified embedding space. Enables cross-modal search, classification, and clustering across 100+ languages.
Provider:
Model type:
embedding
Location:
europe
Context Window
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
0.2
Input tokens per million
$
0
Output tokens per million
Features
Vision
Supported
Audio Input
Supported
