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 Korean v2 · STS · Korean, Sgpt Bloom 7b1 Msmarco scores 50.9 vs 60.8 — lower.
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.
Qwen 3 Embedding 8B (better), Qwen 3 Embedding 4B (open weights).