API Documentation

Integrate Free OLM OCR into your applications with REST APIs, API key authentication, and AI client workflows.

API Key AuthenticationMultiple Upload MethodsREST API

Get API Key

Go to Settings

Choose Upload Method

Send PDFs or images as Base64 data URLs for synchronous OCR processing.

Start Processing

Send images or PDFs to the OCR API and receive structured text data.

OCR Processing

Extract text from images and PDFs.

POST /api/ocr

Method 1: Base64 Upload

{
  "fileName": "document.pdf",
  "mimeType": "application/pdf",
  "dataUrl": "data:application/pdf;base64,JVBERi0x..."
}

Method 2: Image Data URL Upload

{
  "fileName": "receipt.png",
  "mimeType": "image/png",
  "dataUrl": "data:image/png;base64,iVBORw0KGgo..."
}

Response

{
  "code": 0,
  "message": "ok",
  "data": {
    "text": "Extracted readable content...",
    "structured": {
      "text": "Extracted readable content...",
      "markdown": "# Document title",
      "tables": [],
      "language": "en",
      "warnings": []
    },
    "model": "deepseek-v3.2",
    "fileName": "document.pdf",
    "mimeType": "application/pdf",
    "bytes": 248120
  }
}

Authentication

Include your API key in requests.

Header Options

x-api-key: sk_your_api_key_here

Authorization: Bearer sk_your_api_key_here

Get API Key

AI Client Resources

Integration notes for AI agents and OCR client workflows.

REST Endpoint

POST /api/ocr

Synchronous Endpoint

Use /api/ocr for synchronous OCR

HTTPS Request

JSON over HTTPS POST
API key or signed-in session
PDF, JPEG, PNG, WebP
Text and structured JSON output

Available OCR Tool

Extract text from documents and images using OCR. Supports PDF files, JPEG, PNG, and WebP images. Send files as Base64 data URLs.

Client Integrations

Build your own OCR client or integrate Free OLM OCR into AI tools through the synchronous REST endpoint.

Call POST /api/ocr from server-side application code.
Authenticate with x-api-key or Authorization: Bearer.
Send PDF and image files as Base64 data URLs.
Use the response text or structured JSON in downstream AI workflows.

Code Examples

Ready-to-use code snippets.

Python

import base64
import requests

with open("document.pdf", "rb") as f:
    file_data = base64.b64encode(f.read()).decode()

response = requests.post(
    "https://www.freeolmocr.com/api/ocr",
    headers={"x-api-key": "sk_your_api_key"},
    json={
        "fileName": "document.pdf",
        "mimeType": "application/pdf",
        "dataUrl": f"data:application/pdf;base64,{file_data}",
    },
)

print(response.json()["data"]["text"])

cURL

IMAGE_DATA=$(base64 -i document.pdf)

curl -X POST https://www.freeolmocr.com/api/ocr \
  -H "x-api-key: sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d "{
    \"fileName\": \"document.pdf\",
    \"mimeType\": \"application/pdf\",
    \"dataUrl\": \"data:application/pdf;base64,$IMAGE_DATA\"
  }"

Need Help?

Get started quickly with our API or reach out for support.

Get API Key Contact Email Support