Amharic OCR API
Read Amharic in Ge'ez script, where each of 200+ characters is a consonant-vowel syllable.
Result
Your Markdown or JSON shows up here.
What makes Amharic hard for OCR
- Over 200 syllable characters that differ by small marks
- Limited support in most OCR engines
- Ethiopic numerals and punctuation
Script: Ge'ez (Ethiopic) syllabary.
Call it from your code
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-flash",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Best models for Amharic text
1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.
google/gemini-flash3 credits / page2GPTGeneral vision model. Good at messy scans and following extraction instructions.openai/gpt11 credits / page3ClaudeGeneral vision model with careful reading of long, dense documents.anthropic/claude14 credits / page