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.
#23 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Europe v1 · Bitext Mining · multilingual (28 languages), F2LLM v2 8B scores 89.8 vs 90 — 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 8B is an open-weights embeddings & retrieval model from codefuse-ai, released Mar 2026.
Qwen 3 Embedding 8B (better), Octen Embedding 8B (open weights).