There is no per-unit API price: price not verified.
#130 of 206 in Embeddings.
On MTEB multilingual v2 · Clustering · multilingual (208 languages), Bekko Static Embedding v1 scores 40 vs 40.1 — about the same.
Released 2026-10-21. 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 Static Embedding v1 is an open-weights embeddings & retrieval model from hotchpotch, released Oct 2026.
EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).