$0.01 per 1M tokens.
There is no free API; the cheapest paid price is $0.01 per 1M input tokens. The weights are open, so you can run it yourself.
#163 of 220 in Embeddings.
On MTEB German v1 · Classification · German, Bge M3 scores 68.9 vs 69.5 — about the same. It is 0% more expensive.
Through the BAAI API.
Released 2024-06-28. 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.
Bge M3 is an open-weights embeddings & retrieval model from BAAI, released Jun 2024.
Jina Embeddings v5 Text Nano (better), F2LLM v2 8B (open weights).
BetterJina Embeddings v5 Text NanounstatedOpen+24%+100%$0.02cOpenF2LLM v2 8Bunstated+29%——Memory (4-bit): 0.3 GB → 4.5 GBiBetterE5 Mistral 7B InstructunstatedOpen+5%+124%$0.022Memory (4-bit): 0.3 GB → 4.3 GB