DocuCleanse
## What is DocuCleanse? DocuCleanse is a high-performance, layout-aware PDF ingestion API built specifically for AI developers, RAG pipelines, and LLM applications. Standard PDF parsers destroy document structure — they scramble multi-column layouts, lose table relationships, and strip mathematical equations. DocuCleanse fixes all of this with a single POST request. ## What It Solves -…
1 subscribers
1.9/10 popularity
238 ms avg latency
25% success rate
4 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
DocuCleanse endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Parse PDF File /v1/parse-file |
Upload a PDF file and receive clean structured Markdown and JSON blocks. Supports native text extraction, OCR fallback for scanned pages, and RAG chunking. |
| POST |
Get PDF Metadata /v1/metadata |
Upload a PDF and extract metadata including title, author, page count, creation date and language. |
| POST |
Parse PDF from URL /v1/parse-url |
Pass a public URL pointing to a PDF. DocuCleanse downloads and parses it, returning clean Markdown and JSON blocks. |
| GET |
Health Check /v1/health |
Returns API status, version and uptime. Used for monitoring and availability checks. |
DocuCleanse pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | Free | — |
|
| PRO Recommended | $19 / month | — |
|
| ULTRA | $79 / month | — |
|
