Document OCR APIs

About Document OCR on EmpirioLabs

Browse the Document OCR models available on EmpirioLabs and call them through one API with pay-as-you-go pricing.

Document OCR models (1)

LightOnOCR-3 4B

Document OCR that reads PDFs and images into structured Markdown, page by page, with tables, math, charts, image regions, and layout.

How to call Document OCR models

LightOnOCR-3 4B reads PDFs and images through POST /v1/ocr and returns each page as Markdown. Send the PDF's URL in document with the model id lightonocr-3-4b, and list zero-based page numbers in pages to process only those pages. An image works the same way with {"type": "image_url", "image_url": "https://..."}, and either URL can be a base64 data URI. The response lists each page in pages with its index, markdown, images, tables, and dimensions; usage_info.pages_processed counts the pages processed. A request still running after a few minutes returns a job_id to poll at GET /v1/jobs/{job_id}, and a Prefer: respond-async header asks for the job id at once. Swap the model id for any model above. Get an API key from the EmpirioLabs dashboard.

curl https://api.empiriolabs.ai/v1/ocr \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lightonocr-3-4b",
    "document": {
      "type": "document_url",
      "document_url": "https://arxiv.org/pdf/2412.13663"
    },
    "pages": [0, 1],
    "include_image_base64": false
  }'

Document OCR APIs: common questions

How many Document OCR model APIs does EmpirioLabs offer?

EmpirioLabs lists 1 Document OCR model APIs, including LightOnOCR-3 4B. Each model has its own dedicated API page with live pricing, parameters, and a quickstart.

How are Document OCR APIs priced on EmpirioLabs?

Every Document OCR model is billed pay as you go, with no monthly minimum. The exact rate card lives on each model's page and always matches what the API charges.

Do I need to be a developer to use Document OCR models?

No. Every model here runs in the EmpirioLabs playground, a friendly in-browser interface where you can set the options and see results without writing any code. When you are ready to automate, the same model is available through the API.

Other model categories