# Unsiloed AI services

> Unsiloed AI turns PDFs, Word documents, scans, images, slide decks and spreadsheets into structured output for language models and agents. Other formats are converted to PDF before submission. Parse returns a document as ordered Markdown and HTML chunks with segment types, bounding boxes, OCR text and confidence scores. Extract pulls the fields named in a JSON Schema out of a PDF, with a confidence score and a page citation on every value. Classify assigns a PDF or image to one of the categories supplied with the request, with a confidence score per page. Split cuts a bundled PDF into one file per category. Every operation is a job: the submit call returns a job id at once and the result call returns the output when the job finishes, usually within seconds to a few minutes. Documents are sent by URL. Usage is counted in pages of the submitted document: one PDF page, one image, one slide, or one block of 5,000 by 5,000 spreadsheet cells is one page.

4 services. Choose the one that matches your task from the list below, then open its page for the full price matrix, plans, how to call it, and the API reference. Open only the service you will call; each row already shows the price floor.

## Classify

Assigns a PDF or image to one of the categories supplied with the request, with a confidence score for the document and for each page. Documents longer than four pages are classified from their first four. Submit the document, then poll the job for the result. Usage is counted in pages of the submitted document.

- From $0.02 / page
- Billed by: page
- Plans: Pay per page (pay as you go), Credits, Growth (subscription + usage / month), Standard (subscription + usage / month)
- Service page: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/classify
- Service spec: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/classify/openapi.json

## Extract

Pulls the fields defined in a JSON Schema out of a PDF and returns typed values with a confidence score and an optional page citation for each one. Submit the document and the schema, then poll the job for the result. Usage is counted in pages of the submitted document.

- From $0.02 / page
- Billed by: page
- Plans: Pay per page (pay as you go), Credits, Growth (subscription + usage / month), Standard (subscription + usage / month)
- Service page: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/extract
- Service spec: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/extract/openapi.json

## Parse

Converts a PDF, DOCX, scan, JPEG, PNG or WEBP image, or PPTX deck into ordered Markdown and HTML chunks with segment types, bounding boxes, OCR text and confidence scores; a separate route handles Excel workbooks. Other formats are converted to PDF first. Submit the document by URL, then poll the job for the result. Usage is counted in pages of the submitted document.

- From $0.02 / page
- Billed by: page
- Plans: Pay per page (pay as you go), Credits, Growth (subscription + usage / month), Standard (subscription + usage / month)
- Service page: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/parse
- Service spec: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/parse/openapi.json

## Split

Cuts a bundled PDF into one PDF per category supplied with the request, classifying every page and returning a download link and a confidence score per output file. Submit the document, then poll the job for the result. Usage is counted in pages of the submitted document.

- From $0.02 / page
- Billed by: page
- Plans: Pay per page (pay as you go), Credits, Growth (subscription + usage / month), Standard (subscription + usage / month)
- Service page: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/split
- Service spec: https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/split/openapi.json

