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.
#151 of 200 in Embeddings.
On MTEB English v2 · Retrieval · English, Speed Embedding 7B Instruct scores 39.1 vs 39.5 — about the same.
Released 2024-10-31. 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.
Speed Embedding 7B Instruct is an open-weights embeddings & retrieval model from Haon-Chen, released Oct 2024.
EmbeddingGemma 300M (better), Yuan Embedding 2.0 En (open weights).