document extraction apis

priced per thousand pages so the numbers actually compare, and checked on the two things that decide it — what a 'page' costs when it has a table on it, and whether your contracts train someone's model.

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

Docling

we checked thisfree

free forever, permissive on both the code and the models, and nothing ever leaves your infrastructure.

#anyone-processing-docume#which-in-this-category-i

Unstructured

we checked this$30 / 1,000 pages

zero data retention on every plan including the free one, and a bill that stops at $3,000 however much you send.

#teams-handling-sensitive

LlamaParse

we checked this$1.25 / 1,000 pages

the cheapest hosted parsing here at basic tier, with the accurate mode priced nowhere.

#rag-pipelines-doing-high

Mistral OCR

we checked this$4 / 1,000 pages

a clean flat rate that quietly doubled in june.

#straightforward-bulk-con#predictable-rate-matters

Reducto

we checked this$15 / 1,000 pages

the best table extraction here, proven on a benchmark it built and published rather than one it cites.

#dense-financial#scientific-documents-whe

this page is deliberately short: a handful of document extraction apis 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 →