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.
#117 of 200 in Embeddings.
On MTEB Europe v1 · Bitext Mining · multilingual (28 languages), Bekko Embedding v1 A8m scores 87.2 vs 87.3 — about the same.
Released 2026-07-28. It is the current version in its line.
Yes, the weights are open (MIT licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Bekko Embedding v1 A8m is an open-weights embeddings & retrieval model from hotchpotch, released Jul 2026.
Qwen 3 Embedding 8B (better), Octen Embedding 8B (open weights).
BetterQwen 3 Embedding 8BunstatedOpen+7%—$0.01Memory (4-bit): 0.1 GB → 4.5 GBOOpenOcten Embedding 8B+7%——Memory (4-bit): 0.1 GB → 4.5 GBiBetterMultilingual E5 Large InstructunstatedOpen+4%—$0.01Max input: 8K tokens → 1K tokens+1
BetterJina Embeddings v5 Text NanounstatedOpen+3%—$0.02
KaLM Embedding Gemma3 12B 2511Open+6%——Memory (4-bit): 0.1 GB → 7.1 GB
Llama Embed Nemotron 8BOpen+6%——Memory (4-bit): 0.1 GB → 4.5 GB