FAQ
How do Fire-PDF and Document Parsing relate?
Section titled “How do Fire-PDF and Document Parsing relate?”Fire-PDF is the PDF parsing engine. Document Parsing is the Firecrawl capability that parses documents (PDF/Word/Excel) and returns Markdown. This site consolidates usage patterns and best practices across both.
Should I use fast or auto?
Section titled “Should I use fast or auto?”- use
fastfor text-native PDFs - use
autowhen you’re unsure or have mixed PDFs - use
ocrfor obvious scans/photos
See: PDF Parsing Modes
Why is body text missing?
Section titled “Why is body text missing?”Scanned/image-heavy PDFs often have no text layer. Switch to ocr and sample with maxPages.
See: Scanned PDFs & OCR
What about broken tables?
Section titled “What about broken tables?”Scanned tables are harder. Isolate table-heavy PDFs into a dedicated strategy and keep regression examples.
See: Tables & Formulas
How do I control cost?
Section titled “How do I control cost?”Use maxPages and route by document type when you process PDFs at scale.
See: Performance & Cost