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.
#29 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB English v2 · Pair Classification · English, F2LLM v2 4B scores 85.1 vs 85.2 — about the same.
Released 2026-03-09. It is the current version in its line.
Yes, the weights are open (Apache-2.0 licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
F2LLM v2 4B is an open-weights embeddings & retrieval model from codefuse-ai, released Mar 2026.
EmbeddingGemma 300M (better), QZhou Embedding (open weights).