$0.01 per 1M tokens.
There is no free API; the cheapest paid price is $0.01 per 1M input tokens. The weights are open, so you can run it yourself.
#57 of 200 in Embeddings.
On MTEB Medical v1 · Clustering · English, Bge Large En v1.5 scores 35.4 vs 35.4 — about the same. It is 60% cheaper.
Through the BAAI API.
Released 2023-09-12. 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.
Bge Large En v1.5 is an open-weights embeddings & retrieval model from BAAI, released Sep 2023.
EmbeddingGemma 300M (cheaper), F2LLM 4B (open weights).
CheaperEmbeddingGemma 300MunstatedOpen+21%-80%$0.002Languages: not verifiedcOpenF2LLM 4Bunstated×2——Memory (4-bit): 0.2 GB → 2.4 GBsCheaperAll Mpnet Base v2unstatedOpen+9%-50%$0.005Max input: 1K tokens → 0K tokenssCheaperAll MiniLM L12 v2unstatedOpen+3%-50%$0.005Max input: 1K tokens → 0K tokenssCheaperAll MiniLM L6 v2unstatedOpen+3%-50%$0.005Max input: 1K tokens → 0K tokens
Qwen 3 Embedding 8BunstatedOpen+27%same$0.01Languages: not verified+1