There is no per-unit API price: self-host only.
There is no free API. The weights are open, so you can run it yourself.
#14 of 27 in Multimodal.
On MVEB text video v1 · Video Classification · multilingual (16 languages), Xclip Base Patch16 scores 41.9 vs 43.7 — lower.
Released 2022-08-04. It is the current version in its line.
Yes, the weights are open (MIT licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Xclip Base Patch16 is an open-weights embeddings & retrieval model from Microsoft, released Aug 2022.
Qwen 3 VL Embedding 8B (better).