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 JMTEB v2 · Clustering · Japanese, Bilingual Embedding Base scores 48.3 vs 48.3 — 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.
EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).
BetterEmbeddingGemma 300MunstatedOpen+10%—$0.002cOpenF2LLM v2 8Bunstated+48%——Memory (4-bit): 0.2 GB → 4.5 GBiBetterMultilingual E5 Large InstructunstatedOpen+13%—$0.01Memory (4-bit): 0.2 GB → 0.3 GBiBetterE5 Mistral 7B InstructunstatedOpen+18%—$0.022Memory (4-bit): 0.2 GB → 4.3 GBVBetterVoyage Large 2 Instructunstated+5%—$0.12
Text Embedding 3 Largeunstated+4%—$0.13