API pricing
Document OCR API pricing: free pages and Page Packs
Start with free developer pages. Scale with Page Packs you buy by card, or dedicated high-volume enterprise contracts.
These are the same prices as on the main pricing page. There is one set of plans and Page Packs.
Start building for free
Free pages every month
Any signed-in FastOCR account can create an API key and start right away. The Free plan includes 20 free pages per month, shared with PDFs on the website. Paid plans share their Document OCR allowance with the API too. No upfront credit card or separate API subscription required.
Resets monthly. Check what is left with GET /v1/balance.
Documents and bank statements: 2 documents at once; 10 with a contract or 10,000+ pages bought.
Very large documents may take longer to start.
Page Packs
One-time Page Packs for document text extraction and searchable PDF creation in 100+ languages (/v1/documents). A PDF uses one page per PDF page; a PNG, JPG, JPEG, GIF, WebP and BMP image uses one page. Buy them on the pricing page; the pages are added when the payment clears and never expire. The same packs work on the website. A document that runs out of pages fails with buy_pages. After you buy pages, call /start again on the same document.
- 500 pages$4.99
- 2,500 pages$19.99
- 10,000 pages$69.99
- 25,000 pages$149
- 100,000 pages$499
Larger packs cost less per page.
Buy pagesBank Statement Packs
Bank statements (/v1/bank-statements) use statement pages, the same balance as the website converter. Your first 50 statement pages are free, whether you start on the website or with an API key. After that, buy a one-time pack on the bank statement page; pages never expire. See the Bank Statement API.
- 100 pages$4.99
- 500 pages$24.99
- 2,000 pages$79.99
- 10,000 pages$299
- 50,000 pages$999
One page balance
Pages you buy work on the website and through the API (api.fastocr.org/v1): Page Packs for documents, Bank Statement Packs for statements. Monthly pages from a Pro plan stay on the website. See the pricing page for plans and limits.
Compare
OCR APIs compared: what each one returns
Google Cloud Vision and Amazon Textract send back JSON, and you rebuild the text from it yourself. Neither makes a searchable PDF. Azure's Read model and OCR.space can return one. FastOCR returns plain text and a searchable PDF for every PDF and image, in 100+ languages, and all you set up is one API key. Facts as of November 2026.
| FastOCRDocument OCR API | Google Cloud VisionDocument Text Detection | Amazon TextractDetect Document Text | Azure Document IntelligenceRead model | OCR.spaceOCR API | |
|---|---|---|---|---|---|
| What you get back | Plain text and a searchable PDF, ready to use | JSON. The text sits in fullTextAnnotation next to bounding boxes for every word, and you parse it yourself | JSON. A list of Block objects (pages, lines, words) with their geometry, which you stitch back into text | JSON with the text, lines, words and their positions | JSON with the plain text, plus a searchable PDF when you ask for one |
| Searchable PDF | Yes, for every PDF and image | No | No | Yes, for PDF input, with the Read model on API version 2024-11-30. No extra charge | Yes, on every plan. Free-plan PDFs carry an OCR.space watermark |
| Setup | Sign in and create one API key. No cloud account, card or storage bucket | A Google Cloud project with billing on, the Vision API enabled and credentials. Longer PDFs go through async batch annotation, which reads from and writes JSON to a Cloud Storage bucket | An AWS account with billing and IAM credentials. Multi-page PDFs go through the async API, which reads the file from an S3 bucket | An Azure subscription and a Document Intelligence resource, then its key and endpoint | Register for a free API key by email |
| Free tier | 20 pages a month for every account | First 1,000 units a month, on a billing-enabled account | New AWS customers only, through AWS Free Tier credits. See provider | F0: 500 pages a month, and only the first 2 pages of each document | 25,000 requests a month; 1 MB files, 3 PDF pages |
| Files and languages | PDF, PNG, JPG, JPEG, GIF, WebP and BMP; 100+ languages, detected automatically | Images, PDF and TIFF; see the provider for its language list | JPEG, PNG, PDF and TIFF; English, French, German, Italian, Portuguese and Spanish | PDF, JPEG, PNG, BMP, TIFF, HEIF and Office files; hundreds of printed languages | PNG, JPG, GIF, TIFF, BMP and PDF; 33 languages on Engine 2 |
| Source |
Need sustained high volume or custom contracts?
We support custom deployment requirements, volume discounting, and enterprise agreements.
- Volume-tiered pricing discounts
- Higher concurrency & rate limits
- Custom uptime and turnaround SLAs
- Invoicing via Stripe & direct bank transfer
- Dedicated integration engineering support