dOCR

San Francisco, United States

One API for document data and web screenshots.

dOCR is one API for two jobs: turning documents into structured data, and turning web pages into images. For extraction, you send a document — a PDF, image, scan, or Word file — and dOCR returns structured JSON with the fields you need, not raw OCR text, across 15+ built-in document types (invoices, receipts, bank statements, pay stubs, W-2s, 1099s, driver's licenses, passports, utility bills) plus custom types. For screenshots, you send a URL or raw HTML and dOCR renders it to PNG, JPEG, WebP, AVIF, TIFF, or PDF — with device presets, full-page capture, dark mode, ad/cookie blocking, element clipping, caching, async delivery, and signed URLs. Both run on the same API key, the same webhooks, and the same unified credits. Powered by vision LLMs (Claude Opus, Gemini) and a headless browser — no pipelines to build or maintain. Free tier: 100 credits/month.

1 person in their team

Speaks English

Sortlist member since 2026

No review yetBe the first to write one

Compare to other agencies

Services

1 service offered by dOCR

Service name

Experience level

Related reviews

Starting from

Description

dOCR provides one API for two jobs: turning documents into structured JSON and turning web pages into screenshots or PDFs. Powered by vision LLMs (Claude Opus, Gemini) and a headless browser, dOCR handles invoices, receipts, IDs, statements, W-2s, 1099s, custom documents, and renders any URL or HTML to PNG/JPEG/WebP/AVIF/TIFF/PDF with device presets, caching, signed URLs, and webhooks. Free tier: 100 credits/month.

Learn more about Artificial Intelligence

Reviews

No review for dOCR yet

Worked with dOCR?

Share your experience with us.

Write a review

Contact

Contact details of dOCR

Details

HeadquarterCalifornia Street, San Francisco, CA, USA