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.
#150 of 200 in Embeddings.
On MTEB German v1 · Pair Classification · German, Sgpt Bloom 7b1 Msmarco scores 52.8 vs 52.8 — about the same.
Released 2022-08-26. 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.
Sgpt Bloom 7b1 Msmarco is an open-weights embeddings & retrieval model from bigscience, released Aug 2022.
Jina Embeddings v5 Text Nano (better), Gte Qwen2 7B Instruct (open weights).
BetterJina Embeddings v5 Text NanounstatedOpen+7%—$0.02
OpenGte Qwen2 7B Instructunstated+24%——iBetterE5 Mistral 7B InstructunstatedOpen+4%—$0.022Memory (4-bit): 4.2 GB → 4.3 GB