Docling
free forever, permissive on both the code and the models, and nothing ever leaves your infrastructure.
the only entry where the privacy question is answered by architecture rather than by a policy page — and it publishes real accuracy figures while doing it.
ibm released docling under mit with the pretrained layout and tableformer models under cdla-permissive-2.0. two separate licences, both genuinely permissive, and you should know you're accepting two rather than one. the project now sits under the lf ai & data foundation.
the technical report gives numbers rather than adjectives: 93.6% accuracy on table-structure recognition for tableformer, and roughly 95.4% on simple tables and 90.1% on complex ones for layout detection, evaluated against a doclaynet-derived corpus. most vendors in this ranking publish no self-benchmark at all.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- document extraction apis
- pricing
- free
- website
- github.com
the only entry where the privacy question is answered by architecture rather than by a policy page — and it publishes real accuracy figures while doing it.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.
more document extraction apis
Unstructured
we checked this$30 / 1,000 pageszero data retention on every plan including the free one, and a bill that stops at $3,000 however much you send.
LlamaParse
we checked this$1.25 / 1,000 pagesthe cheapest hosted parsing here at basic tier, with the accurate mode priced nowhere.