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.
#144 of 200 in Embeddings.
On MTEB Indic v1 · Clustering · multilingual (21 languages), Sentence Croissant Alpha v0.2 scores 4.5 vs 4.7 — about the same.
Released 2024-03-15. It is the current version in its line.
Yes, the weights are open.
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Sentence Croissant Alpha v0.2 is an open-weights embeddings & retrieval model from manu, released Mar 2024.
EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).
BetterEmbeddingGemma 300MunstatedOpen×7.8—$0.002cOpenF2LLM v2 8Bunstated×19.6——Memory (4-bit): 0.8 GB → 4.5 GB
BetterQwen 3 Embedding 8BunstatedOpen×12.4—$0.01Memory (4-bit): 0.8 GB → 4.5 GBiBetterMultilingual E5 Large InstructunstatedOpen×11.5—$0.01
Bge M3unstatedOpen×6.7—$0.01