$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.
#78 of 200 in Embeddings.
On MTEB Law v1 · Mean over task types · multilingual (3 languages), Gte Large scores 41.2 vs 41.2 — about the same.
Through the thenlper API.
Released 2023-07-27. 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.
Gte Large is an open-weights embeddings & retrieval model from thenlper, released Jul 2023.
Bge Base En v1.5 (cheaper), Multilingual E5 Large Instruct (better), Octen Law 8B v1 (open weights).