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.
#98 of 200 in Embeddings.
On MTEB Polish v1 · STS · Polish, LLM2Vec Mistral 7B Instruct v2 Mntp Supervised scores 60.9 vs 61 — about the same.
Released 2024-04-09. 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.
LLM2Vec Mistral 7B Instruct v2 Mntp Supervised is an open-weights embeddings & retrieval model from McGill-NLP, released Apr 2024.
Multilingual E5 Large Instruct (better), Jina Embeddings v3 (open weights).