$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.
#94 of 200 in Embeddings.
On MTEB English v2 · Pair Classification · English, Multilingual E5 Large scores 84.7 vs 84.8 — about the same.
Through the intfloat API.
Released 2024-02-08. 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.
Multilingual E5 Large is an open-weights embeddings & retrieval model from intfloat, released Feb 2024.
EmbeddingGemma 300M (cheaper), QZhou Embedding (open weights).
CheaperEmbeddingGemma 300MunstatedOpen+3%-80%$0.002Languages: not verifiedKOpenQZhou Embeddingunstated+9%——Languages: loses Esperanto, es, Estonian +88+1
CheaperBge Base En v1.5unstatedOpen+2%-50%$0.005Languages: loses Esperanto, es, Estonian +89iCheaperE5 Base v2unstatedOpensame-50%$0.005Languages: loses Esperanto, es, Estonian +89tCheaperGte BaseunstatedOpensame-50%$0.005Languages: loses Esperanto, es, Estonian +89
Qwen 3 Embedding 8BunstatedOpen+3%same$0.01Languages: not verified+1
NV Embed v2unstatedOpen+5%——Languages: loses Esperanto, es, Estonian +89+1aLGAI Embedding PreviewunstatedOpen+5%——Languages: loses Esperanto, es, Estonian +89+1