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.
#134 of 200 in Embeddings.
On MTEB Indic v1 · Clustering · multilingual (21 languages), Bilingual Embedding Base scores 34.5 vs 34.5 — about the same.
Released 2024-06-26. It is the current version in its line.
Yes, the weights are open (Apache-2.0 licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Bilingual Embedding Base is an open-weights embeddings & retrieval model from Lajavaness, released Jun 2024.
Qwen 3 Embedding 8B (better), F2LLM v2 8B (open weights).
BetterQwen 3 Embedding 8BunstatedOpen+62%—$0.01Memory (4-bit): 0.2 GB → 4.5 GBcOpenF2LLM v2 8Bunstated×2.6——Memory (4-bit): 0.2 GB → 4.5 GBiBetterMultilingual E5 Large InstructunstatedOpen+50%—$0.01Memory (4-bit): 0.2 GB → 0.3 GB
Jina Embeddings v5 Text NanounstatedOpen+30%—$0.02