Image OCR

Extract text from an image (PNG/JPEG): returns the full text, overall confidence (0-100), and per-line bounding boxes. Send POST /api/image-ocr with no required fields (3 optional) and pay $0.01 per call over x402 or MPP (there is no free tier). It returns a JSON object with text, confidence, lang, lineCount, lines and 1 more.

Send either {image: base64} or {url: 'https://…'}. Pure-CPU Tesseract via tesseract.js - no upstream API, no keys. Default lang 'eng'; pass 'lang' (ISO 639-2) for others.

Category: Live public data · Tags: ocr image text-extraction tesseract scanned-document receipt extract text

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/api/image-ocr \
  -H "Content-Type: application/json" \
  -d '{"url":"https://agent402.tools/fixtures/sample-text.png"}'

Without payment this returns HTTP 402 Payment Required with the exact price for image-ocr; any x402 v2 or MPP client pays it and retries.

Example response

{
  "text": "Agent402 sample text for OCR.\nInvoice 402-0001 total 12.34 USD.",
  "confidence": 94,
  "lang": "eng",
  "lineCount": 2,
  "lines": [
    {
      "text": "Agent402 sample text for OCR.",
      "confidence": 94.34,
      "bbox": {
        "x0": 24,
        "y0": 29,
        "x1": 469,
        "y1": 60
      }
    },
    {
      "text": "Invoice 402-0001 total 12.34 USD.",
      "confidence": 96.31,
      "bbox": {
        "x0": 27,
        "y0": 81,
        "x1": 514,
        "y1": 106
      }
    }
  ],
  "source": "tesseract.js (Tesseract WASM, Apache-2.0)"
}

From an MCP client

catalog.call {
  "slug": "image-ocr",
  "params": {
    "url": "https://agent402.tools/fixtures/sample-text.png"
  }
}

The hosted connector at https://agent402.tools/mcp needs a payment for image-ocr; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.

Errors and behavior

• Every field is optional. An input the tool rejects returns an HTTP 4xx whose body carries error, tool, expected, required and example.
• A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
• Wallet-only: this tool reaches the network or stored state, so it has no proof-of-work tier. A prepaid card-credits key issued earlier (Authorization: Bearer a402_...) also pays it.
• A GET or HEAD to /api/image-ocr returns the same 402 quote, so the price can be read without a body.
• An Idempotency-Key header makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB is not replayed).

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/image-ocr", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "url": "https://agent402.tools/fixtures/sample-text.png"
  }),
});

Part of these workflows

Image OCR is one step in these 3 skill packs, each sold as a single call:

• Content extraction - Turn arbitrary URLs and PDFs into clean structured text - articles, page metadata, PDF pages, OCR'd images, browser-rendered SPAs.
• Document intelligence - Turn any PDF or image URL into structured data - metadata, extracted text, sliced page ranges, OCR for scanned docs, decoded barcodes / QR codes - without falling back to a vision LLM guess. Built for the messy 30% of documents where pdf-to-markdown alone returns nothing useful.
• Convert anything to markdown - Convert anything at a URL - HTML, PDF, or an image - to clean markdown. The 'I have a URL but it might be any content-type, give me markdown either way' workflow: HEAD-detect the content-type, branch to the right deterministic extractor (article extract for HTML, pdf-to-markdown for PDFs, OCR for images), and report token/word stats on the output so the caller can budget the result against an LLM context window.

Related tools