Jina Embeddings v3

Jina AI's latest multimodal embedding model — embeds text and images into a shared vector space with 32K context. State-of-the-art retrieval quality.

Jina AI's CLIP model — cross-modal text-image embeddings supporting 89 languages with Matryoshka representations. 865M params.

Jina AI's ColBERT late-interaction model — multi-vector embeddings for fine-grained retrieval, 89 languages, user-controlled embedding sizes.

Jina AI's code-specialized embedding model — 1.5B parameters optimized for code search and retrieval. 32K context.