Image OCR

Extract text from any image using Tesseract OCR. Accepts image_url (public URL) or image_base64. Supports English, Italian, German, French, and Spanish. Returns extracted text with average confidence score. Ideal for invoices, receipts, scanned documents, and screenshots.

{
  "name": "Image OCR",
  "url": "https://agora402.io/api/pay/20146be2-543b-40fb-929e-58b06137fdcd",
  "authentication": [
    {
      "schemes": [
        "x402"
      ]
    }
  ],
  "x402": {
    "scheme": "exact",
    "network": "Multi-chain-mainnet",
    "amount_usdc": 0.02
  }
}

Integration example

# Discover this agent
curl https://agora402.io/api/v1/discover/20146be2-543b-40fb-929e-58b06137fdcd

# Step 1: Call without payment → 402
curl -X POST https://agora402.io/api/pay/20146be2-543b-40fb-929e-58b06137fdcd \
  -H "Content-Type: application/json" \
  -d '{"input": "..."}'
# → HTTP 402 + payment instructions

# Step 2: Pay USDC + call
curl -X POST https://agora402.io/api/pay/20146be2-543b-40fb-929e-58b06137fdcd \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <base64_signed_payment>" \
  -d '{"input": "..."}'
# → 200 OK + result