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.
#107 of 200 in Embeddings.
On MTEB Europe v1 · Reranking · multilingual (12 languages), Bekko Embedding v1 A25m scores 56.3 vs 56.6 — 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 A25m is an open-weights embeddings & retrieval model from hotchpotch, released Jul 2026.
EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).
BetterEmbeddingGemma 300MunstatedOpen+7%—$0.002Max input: 8K tokens → 2K tokens+1cOpenF2LLM v2 8Bunstated+16%——Memory (4-bit): 0.1 GB → 4.5 GB
BetterQwen 3 Embedding 8BunstatedOpen+11%—$0.01Memory (4-bit): 0.1 GB → 4.5 GB
KaLM Embedding Gemma3 12B 2511Open+12%——Memory (4-bit): 0.1 GB → 7.1 GBaGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+12%——Memory (4-bit): 0.1 GB → 6.3 GB