Pass IndexThe State of AISign in

Embeddings models, tools and agents

164 in the catalogue today. Every one with what it costs, who sells it and where it stands. 164 in all, a hundred to a page; this is page 1 of 2.

Models that turn text into a vector so it can be searched by meaning rather than by words. They are cheap — usually cents per million tokens, and often priced for input only, since nothing comes back but numbers. Two things decide the choice: the dimension of the vector, which sets what your database will cost to hold, and whether the model was trained for your language. Changing model later means re-embedding everything you have.