# Text Extract OCR - Core.Today AI API

> Simple, massively-used OCR (91M+ runs) — extracts text from an image with a single input and returns plain text. Great default for receipts, screenshots, and scanned documents at just 1 credit.

- **Provider**: OCR
- **Model ID**: abiruyt/text-extract-ocr
- **Category**: Image Generation
- **Credits**: 1 per image
- **Speed**: Fast
- **Quality**: Standard

## Features
- One input, plain-text output
- 91M+ runs — battle-tested
- 1 credit per image — ideal for bulk
- Works on receipts, screenshots, documents

## Use Cases
- Receipt and invoice digitization
- Screenshot text extraction
- Scanned document processing
- Data entry automation
- Search indexing of image text

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **image**: string - Image to extract text from

## Examples

### Receipt OCR
Extract all text from a receipt photo
```json
{
  "model": "abiruyt/text-extract-ocr",
  "input": {
    "image": "https://example.com/receipt.jpg"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- At 1 credit per image, run it across entire archives cheaply
- Best on clear, high-contrast text; retake blurry photos for better results
- For structured questions about an image (not just raw text), use moondream2 or BLIP

## Documentation
https://replicate.com/abiruyt/text-extract-ocr