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.
#145 of 200 in Embeddings.
On MTEB Medical v1 · Clustering · English, Embedder 100p scores 38.1 vs 38.2 — about the same.
Released 2023-07-24. 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.
Embedder 100p is an open-weights embeddings & retrieval model from deepfile, released Jul 2023.
EmbeddingGemma 300M (better), F2LLM 4B (open weights).
BetterEmbeddingGemma 300MunstatedOpen+13%—$0.002cOpenF2LLM 4Bunstated+87%——Memory (4-bit): 0.2 GB → 2.4 GB
BetterQwen 3 Embedding 8BunstatedOpen+18%—$0.01Memory (4-bit): 0.2 GB → 4.5 GB
Jina Embeddings v5 Text NanounstatedOpen+9%—$0.02