There is no per-unit API price: price not verified.
#109 of 200 in Embeddings.
On MTEB English v2 · Pair Classification · English, E5 Large scores 85.9 vs 86 — about the same.
Released 2022-12-26. 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.
E5 Large is an open-weights embeddings & retrieval model from intfloat, released Dec 2022.
Bge En Icl (better), QZhou Embedding (open weights).
BetterBge En IclunstatedOpen+3%—$0.01Languages: not verified+1KOpenQZhou Embeddingunstated+8%——Memory (4-bit): 0.2 GB → 4.2 GBiBetterE5 Mistral 7B InstructunstatedOpen+3%—$0.022Memory (4-bit): 0.2 GB → 4.3 GBVBetterVoyage Large 2 Instructunstated+6%—$0.12Languages: not verifiedjBetterIngot 8B R3unstated+9%——Languages: not verified
NV Embed v2unstatedOpen+3%——Memory (4-bit): 0.2 GB → 4.7 GBaLGAI Embedding PreviewunstatedOpen+3%——Memory (4-bit): 0.2 GB → 4.3 GB