Embed v4.0

About

Latest multimodal embedding model supporting text, images, and mixed content (e.g., PDFs). Embed v4.0 offers variable embedding dimensions (256, 512, 1024, 1536 default) and supports multiple similarity metrics (Cosine, Dot Product, Euclidean Distance). Ideal for semantic search, classification, and clustering across multimodal data.

Capabilities

Rankings