OCR API
Extract text from any document.
Production-grade OCR powered by PaddleOCR, DeepSeek OCR, and olmOCR. Extract text from scanned documents, receipts, invoices, handwritten notes, and screenshots. Send an image, get structured text back. Multiple models for different accuracy and speed trade-offs.
QUICK START
Integrate in minutes.
from openai import OpenAI
client = OpenAI(
base_url="https://api.runcrate.ai/v1",
api_key="rc_live_YOUR_API_KEY",
)
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-OCR",
messages=[
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "https://example.com/receipt.png"}},
{"type": "text", "text": "Extract all text from this receipt."},
],
}
],
)
print(response.choices[0].message.content)AVAILABLE MODELS
Models you can use today.
| Model | Provider | Price | Detail |
|---|---|---|---|
| deepseek-ai/DeepSeek-OCR | DeepSeek | Per-token | High-accuracy document text extraction |
| PaddleOCR/PaddleOCR-VL-0.9B | PaddlePaddle | Per-token | Ultra-lightweight 0.9B, fast processing |
| allenai/olmOCR-2 | Allen AI | Per-token | Research-grade OCR accuracy |
WHY RUNCRATE
Built for production.
Multi-Format Support
Process scanned PDFs, photos of documents, screenshots, receipts, invoices, business cards, and handwritten notes with high accuracy.
Structured Extraction
Beyond raw text: extract structured data like line items, totals, dates, and addresses. Combine OCR with LLM understanding for intelligent parsing.
80+ Languages
Recognize text in 80+ languages including CJK characters, Arabic, Cyrillic, and mixed-language documents.
Vision Model Pipeline
Use vision-language models for OCR tasks. Send an image with a text prompt to control extraction format, language, and output structure.
FAQ