Jina Embeddings 5 Omni Nano
Awaiting activationA compact path from Jina text retrieval to images, audio, video and PDFs.
What it does
Jina Embeddings 5 Omni Nano extends the Text Nano backbone with vision and audio encoders. Its default output has 768 dimensions and an 8,192-token context. It supports the same content types as Omni Small, with a lighter model and a smaller source window.
Jina documents text-output compatibility with the corresponding Text Nano variant. Nano inherits the narrower language foundation of Text Nano, rather than Small’s broad multilingual coverage. Compact size is a model characteristic, not a verified hosted latency or price guarantee.
Content types
text · image · audio · video · PDF documents
A compact omni model for mixed-media retrieval, compatible with Jina 5 Text Nano text vectors.
AIRuntime media adapter implemented; commercial media activation is pending. The media API awaits commercial activation.
Where it helps
Product discovery
Match words or a product photo to a compatible catalog collection.
Compact media collections
Evaluate smaller vectors for images, recordings and short clips.
Jina Text Nano expansion
Add media to an existing compatible text collection.
When to choose it
Choose it when a compact representation matters and its language coverage fits. Compare with Omni Small on documents, languages and clips that matter to your business.
Media adapter implemented in AIRuntime; commercial activation, provider credentials and verified pricing are required before calls are enabled. Inline payloads are bounded to 1 MiB per request; remote media URLs and large-file processing are not exposed. Always use a compatible model, task and dimension for indexed content and queries.
Official sources
Paraphrased from the provider’s documentation and original model information. Selection advice is our editorial guidance.
Jina 5 Omni Nano · Official model documentation ↗Reviewed October 4, 2026