embedding models

ranked on price per million tokens, what the dimensions cost you in storage, and which licences actually permit commercial use.

5 listed · 5 researched by us · featured first, then most upvoted

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

text-embedding-3-large

we checked this$0.13 / 1m tokens

the default everyone reaches for, and it is showing its age

#teams-already-on-the-ope#no-new-vendor

voyage-4-large

we checked this$0.12 / 1m tokens

cheaper than OpenAI, four times the context, and a reranker to match

#retrieval-focused-teams-#reranking-pair-from-one-

Cohere Embed v4

we checked thisnot published per token

128k of context, text and pdfs in one space, and no published price

#long-document#pdf-retrieval-where-a-12

this page is deliberately short: a handful of embedding models we looked at properly, rather than everything that exists. if you build one that belongs here, a free listing takes two minutes and $50 pins it to the top of this page.

add a tool →