Extract text from PDFs
for your application.
Send scanned or digital PDFs to POST /parse. Read the text field for search and indexing, or use markdown and page elements when your pipeline needs layout.
From PDF to searchable text
Preview a file in Studio, create an API key, then integrate the parse endpoint.
Text for document pipelines
Use recognized text in search, retrieval, and downstream processing.
Search indexes
Index reading-order text so your application can search scanned reports and forms.
Retrieval pipelines
Use markdown when headings and tables help you split document content into chunks.
Source previews
Use page elements and their locations to connect text to the original document.
Document queues
Use async or batch parsing to process incoming PDFs and poll jobs for results.
Inspect OCR text before you integrate
Upload a sample PDF in Studio and compare the recognized text against the source.
PDF to text API FAQ
Output fields, scans, formats, and pricing.
How do I extract plain text from a PDF?
Send a PDF to POST /parse with an ocr_model and your API key. Read text from the successful ParsedDocument response. If the request returns 202, poll the job URL for the result.
Does the API work with scanned PDFs?
Yes. The selected OCR model recognizes text in scanned pages. Faint scans, unusual fonts, and complex layouts can reduce recognition quality. Check important text against the source.
What is the difference between text and markdown?
The text field contains reading-order plain text. The markdown field adds best-effort formatting. Use pages and elements when you need structured layout or source locations.
Which file formats can I upload?
PDF, PNG, and JPEG files up to 50 MiB. Encrypted PDFs are rejected. Provider page limits vary by model.
How much does PDF text extraction cost?
Open-weight hosted OCR starts at $1 per 1,000 parsed pages. Other models have their own rates. New accounts get $10 in free credits. Schema extraction adds language-model token costs.
Where is the API example?
See the document parsing request and response, or follow the API reference for endpoint details.
Preview text extraction in Studio
Test a PDF, inspect its text, and create an API key for your integration. New accounts get $10 in free credits.