There is no per-unit API price: API price not public.
There is no free API. The weights are open, so you can run it yourself.
#111 of 200 in Embeddings.
On ChemTEB · Pair Classification · multilingual (13 languages), F2LLM v2 160M scores 62.7 vs 64.9 — lower.
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 160M is an open-weights embeddings & retrieval model from codefuse-ai, released Mar 2026.
Text Embedding 3 Large (better), F2LLM v2 8B (open weights).
BetterText Embedding 3 Largeunstated+4%—$0.13Max input: 41K tokens → 8K tokens+1cOpenF2LLM v2 8Bunstated+23%——Memory (4-bit): 0.1 GB → 4.5 GBcBetterF2LLM v2 14BunstatedOpen+28%——Memory (4-bit): 0.1 GB → 8.4 GBcBetterF2LLM v2 4BunstatedOpen+18%——Memory (4-bit): 0.1 GB → 2.4 GBcBetterF2LLM v2 1.7BunstatedOpen+9%——Memory (4-bit): 0.1 GB → 1 GB