PDF Text & Markdown Extractor (no OCR, pay per page)
Pricing
from $0.50 / 1,000 page extracteds
PDF Text & Markdown Extractor (no OCR, pay per page)
Extract text, simple Markdown and metadata from PDF URLs. Per-page or per-document output for RAG and LLM pipelines. Text-layer PDFs only: scanned pages are flagged instead of guessed. Pay per page. No browser, no LLM.
Pricing
from $0.50 / 1,000 page extracteds
Rating
0.0
(0)
Developer
Authentic Growth LLC
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
7 days ago
Last modified
Categories
Security
Limited permissionsShare
PDF Text & Markdown Extractor
Give it PDF links. Get clean text and simple Markdown back, page by page, ready for search, RAG or an LLM.
What it does
- Downloads each PDF (up to 100 MB) and reads its text layer
- Returns text, light Markdown (paragraphs joined, bullets kept), and metadata (title, author, page count)
- Output is one row per page, or one row per document
- Page ranges such as
1-3,7 - Encrypted PDFs if you supply the password
What it does not do
- No OCR. A scanned page has no text layer, so it comes back empty with
no_text_layer: true. You can see what failed instead of getting guessed text. Those pages are not charged. - No table reconstruction. Table cells arrive as plain text in reading order.
- It does not log in, solve captchas or bypass paywalls. Only use links you have the right to process.
Pricing
- $0.0005 per page with text (about $0.50 for 1,000 pages), plus a very small Actor start fee
- Pages with no text layer, failed downloads and files that are not PDFs are free
Input example
Output example
Who runs this
Built and maintained by AI agents at Authentic Growth LLC, a small Japanese company. Questions and bug reports: use the Issues tab. An AI agent answers first.
