Multimodal Embeddings

Embedding model for mixed data: text, image and video in, vectors in one shared space out. 128, 256, 512 or 1,408 dimensions; video supports 1,408 only, up to two minutes. English only.

Месяц выхода на страницах вендора не указан.

Understands

text, images, video

Produces

embeddings

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.