product · May 18, 2026
Elastic Introduces Jina v5 Omni Family: Two Models to Power Text, Image, Video, and Audio Search
Share the canonical public link.
Elastic (NYSE: ESTC) announced jina-embeddings-v5-omni, a new family of multimodal embedding models with the ability to represent text, images, video, and audio as vectors. Developers can now perform search, classification, clustering, and deduplication across different media types. The models are available in two sizes, small and nano, and share the exact same semantic space as jina-embeddings-v5-text. jina-embeddings-v5-omni-small and jina-embeddings-v5-omni-nano models are available on Elastic Inference Service, via the Jina API, and for local installation via download.
Spend governor blocked model creation: provider_circuit_open (lane=dev, provider=together)