Skip to main content
No credit card requiredTables and formulas preservedDocuments not used for training
OCR API

OCR API for documents that ordinary OCR breaks

Extract scans, multi-column layouts, tables, formulas, and handwriting into structured Markdown through one REST endpoint.

PDF + images · 50+ languages · No per-feature stacking

Use revocable keys and inspect usage headers on every production request.
curlbash
curl -X POST https://blazedocs.io/api/v1/convert \
  -H "Authorization: Bearer $BLAZEDOCS_API_KEY" \
  -F "file=@document.pdf"
Finally a PDF converter that outputs clean Markdown for my RAG pipeline.

Alex T. · Software engineer

50+
supported document languages
Before and after

Make the source usable before the next workflow

Before
Scanned document
Image-only pages and complex layouts contain pixels rather than selectable structured text.
After
Structured OCR

The API returns readable Markdown with headings, tables, lists, formulas, and correct reading order.

TextTablesHandwritingLanguages
Why BlazeDocs

Structure you can use—not another text dump

One request
POST a file with Bearer or x-api-key authentication and receive structured JSON immediately.
Production controls
Usage fields, rate-limit headers, stable error codes, batch processing, and idempotency support.
Markdown that is usable
Return headings, tables, formulas, images, and reading order—not an unstructured OCR text blob.
Product walkthrough

Watch OCR handle a difficult scan

See table cells, formulas, and reading order appear in the final Markdown.

Developer quickstart

Start with one copy-pasteable request

The examples use the production API response shape and work with the tools already in your stack.

curlbash
curl -X POST https://blazedocs.io/api/v1/convert \
  -H "Authorization: Bearer $BLAZEDOCS_API_KEY" \
  -F "file=@document.pdf"
Pricing

Simple page pricing

Tables, OCR, and Markdown are included instead of being billed as separate extraction features.

Starter works out to about $0.02/page

FAQ

Questions before you try it?

Answers about accuracy, pricing, security, and this workflow.

How accurate is BlazeDocs OCR?+

BlazeDocs uses Mistral AI OCR and preserves reading order, headings, tables, formulas, and lists. Clean text PDFs are near-perfect; difficult scans typically exceed 95% character accuracy.

How does BlazeDocs pricing work?+

The free plan includes three uploads per month with the first five pages of each file. Paid plans start at $9.99 per month for 500 pages, with API plans for production volume.

Are uploaded documents private?+

Documents are processed securely and are not used to train models. PDFs are handled in memory rather than permanently stored; review the security and privacy pages for current controls.

Which files can the OCR API process?+

The API accepts PDFs and common image formats, including PNG, JPG, WebP, GIF, and AVIF, plus DOCX and PPTX through the document endpoint.

Does pricing increase for tables and forms?+

BlazeDocs plans are based on processed pages; OCR, table extraction, and Markdown formatting are included rather than stacked as separate features.

Ready to make this document usable?

Try the workflow with your own document before deciding. No credit card required.