There is no per-unit API price: API price not public.
There is no free API. The weights are open, so you can run it yourself.
#107 of 200 in Embeddings.
On RTEB Law beta · Mean over tasks · multilingual (4 languages), Bekko Embedding v1 A25m scores 47.9 vs 47.9 — about the same.
Released 2026-07-28. 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.
Bekko Embedding v1 A25m is an open-weights embeddings & retrieval model from hotchpotch, released Jul 2026.
Qwen 3 Embedding 8B (better), Octen Embedding 8B (open weights).
BetterQwen 3 Embedding 8BunstatedOpen+41%—$0.01Memory (4-bit): 0.1 GB → 4.5 GBOOpenOcten Embedding 8B+62%——Memory (4-bit): 0.1 GB → 4.5 GB
BetterNemotron 3 Embed 1B BF16Open+28%—$0.015Memory (4-bit): 0.1 GB → 0.7 GBVBetterVoyage 4 Lite+21%—$0.02
BetterJina Embeddings v5 Text NanounstatedOpen+12%—$0.02