NewPage Search API — cut 97% token cost. Learn moreGet verifiable answers
Get verifiable answers
from complex documents
Document AI for precision, traceability, and context.
Introducing Page Search API
Page Search API finds the relevant pages for each question in about a second, so your LLM reads only those, not the whole PDF.
- 97%
- less token cost
- ~1s
- a question, more accurate than SOTA vector search
Introducing Page Extract API
Extract the data out of any PDF: describe the fields you want in a JSON Schema, and get them back from the document.
- 60%
- lower cost than the next best
- #1
- in accuracy on ExtractBench
{
"holdings": [
{
"issuer": "10X GENOMICS INC",
"value": 21415529
},
… 3,062 more
]
}