verifier.org

multilingual-e5

microsoft's open multilingual embedding family, widely used as a baseline

#open-weights#multilingual

multilingual-e5 is listed here for coverage of the category. the entry is ours, not the vendor's: we have not tested it, there is no score, and no pricing is quoted because we have not read it off their own page on a date we can cite.

if you work on multilingual-e5, claim the listing through /submit and replace this with your own description.

the description above is supplied by the vendor and is not something we have tested. pricing is as they state it.

pricing
not stated

more embedding models

text-embedding-3-small

openai's cheaper embedding model, shortenable to fewer dimensions

#api#matryoshka

ColBERT

late-interaction retrieval that scores token by token rather than one vector

#late-interaction#research

Qwen3-Embedding-8B

we checked this$0.010 / 1m tokens on DeepInfra

apache-2.0, best open multilingual quality, and a tenth of a cent hosted

#multilingual-retrieval-w#the-bill-has-to-be-small

gemini-embedding-2

we checked this$0.20 / 1m text tokens

one vector space for text, images, audio and video

#retrieval-across-mixed-m