Speed Embedding 7B Instruct

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 JMTEB v2 · Clustering · Japanese, Speed Embedding 7B Instruct scores 43.8 vs 43.9 — 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), F2LLM v2 14B (open weights).