Text Recognition API

Overview

The Text Recognition API extracts text from image files with high precision, specifically optimized for Chinese and English text recognition. It returns the recognized text in plain text format, making it ideal for daily documents, screenshots, and general text extraction tasks.

This API uses a unified JSON request format, accepting either URL references or base64-encoded image data.

Authentication

The API supports two authentication methods:

API Key: Pass your API key as a query parameter ?key=YOUR_API_KEY

Extract Text from Image

Extract text from an image file using high-precision text recognition technology, optimized for Chinese and English languages.

Request

POST /api/text-recognition

Parameters:

Parameter	Type	Required	Description
document	object	Yes	Document object
document.type	string	Yes	Fixed value "image_url"
document.image_url	string	Yes	Image URL or base64 data
filename	string	No	Filename (recommended for base64 data)
key	string	No	API key (query parameter, optional for logged-in users)

Supported Languages:

Chinese (中文)
English (English)

Examples:

Using Image URL:

curl -X POST "https://llmocr.com/api/text-recognition?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "document": {
      "type": "image_url",
      "image_url": "https://llmocr.com/image.jpg"
    }
  }'

Using Base64 Image Data:

curl -X POST "https://llmocr.com/api/text-recognition?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "document": {
      "type": "image_url",
      "image_url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEAYABgAAD..."
    },
    "filename": "document.jpg"
  }'

Response

Success Response (200):

{
  "id": "12345",
  "filename": "document.jpg",
  "content": "This is the extracted text content from the image.\n\n这是从图像中提取的文本内容。",
  "format": "text",
  "timestamp": 1640995200000,
  "payload": "https://llmocr.com/api/text-recognition?key=YOUR_API_KEY"
}

Response Fields:

Field	Type	Description
id	string	Unique identifier for the processed document
filename	string	Original filename of the processed image
content	string	Extracted text content in plain text format
format	string	Output format (always "text" for this API)
timestamp	number	Processing timestamp in milliseconds
payload	string	API endpoint used for processing

Error Responses:

Status Code	Description
400	Bad Request - Invalid input parameters
401	Unauthorized - Invalid or missing API key
403	Forbidden - Insufficient quota or permissions
429	Too Many Requests - Rate limit exceeded
500	Internal Server Error - Processing failed

Error Response Format:

{
  "statusText": "Error description"
}

Supported Image Formats

JPEG (.jpg, .jpeg)
PNG (.png)
GIF (.gif)
WebP (.webp)

Rate Limits

Free tier: 30 requests per month
Basic tier: 1,000 requests per month
Pro tier: 5,000 requests per month
Ultra tier: Unlimited requests

Image Requirements

Maximum file size: 10MB
Minimum resolution: 100x100 pixels
Maximum resolution: 4000x4000 pixels
Supported formats: JPEG, PNG, GIF, WebP

Best Practices

Image Quality: Use high-resolution images with clear text for better accuracy
Text Contrast: Ensure good contrast between text and background
Image Orientation: Make sure text is properly oriented (not rotated)
File Size: Optimize image size for faster processing while maintaining quality
Error Handling: Always implement proper error handling for API responses

SDK Examples

JavaScript/Node.js

const response = await fetch('https://llmocr.com/api/text-recognition?key=YOUR_API_KEY', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    document: {
      type: 'image_url',
      image_url: 'https://example.com/image.jpg'
    }
  })
});
 
const result = await response.json();
console.log(result.content);

Python

import requests
 
url = "https://llmocr.com/api/text-recognition"
params = {"key": "YOUR_API_KEY"}
data = {
    "document": {
        "type": "image_url",
        "image_url": "https://example.com/image.jpg"
    }
}
 
response = requests.post(url, params=params, json=data)
result = response.json()
print(result["content"])

LLMOCR

API Documentation

Quick Start