Reducto
APIDocument parsing and extraction API that turns complex files into LLM-ready JSON
- Access
- API key
About
Hosted API that parses PDFs, scans, spreadsheets and Office files into layout-aware chunks, and extracts, splits, classifies and fills documents. Aimed at teams feeding documents to LLMs and RAG. New accounts get $150 of free usage; on-prem and VPC are Enterprise only.
What you can do with it
- Parse PDFs and scans into chunks with tables, figures and bounding boxes for RAG
- Extract fields into JSON from a schema, with citations back to the page
- Split long document packets and classify each section before processing
Get started
- Sign up in Reducto Studio
- Create an API key under API Keys
Example
curl -X POST "https://platform.reducto.ai/parse" \
-H "Authorization: Bearer $REDUCTO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"input":"https://cdn.reducto.ai/samples/fidelity-example.pdf"}'Details
- Hosting
- Hosted service, Self-hosted
- Available in
- Worldwide
- Official SDKs
- Python, JavaScript/TypeScript, Go
- MCP server
- Remote