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.
#46 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Thai v1 · Pair Classification · Thai, F2LLM v2 1.7B scores 74.8 vs 74.9 — 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 1.7B is an open-weights embeddings & retrieval model from codefuse-ai, released Mar 2026.
EmbeddingGemma 300M (better), Qwen 3 Embedding 8B (open weights).