OCR Image to Text API

Reads the text out of an image (scan, screenshot, photo) with Tesseract, returned with a mean confidence.

Updated

Agents read this page asGET /v1/ocr-image-to-text/schemafree: schema, examples, errors, price

Endpoint
POST /v1/ocr-image-to-text
Price
$0.005 per call
Timeout
45 s
max_timeout_seconds
66 (the whole call as the 402 envelope sells it: the timeout, plus payment verification and settlement around it)
Response cap
10 MB (10,485,760 bytes)
Family
Documents

When to use it

OCR needs a real engine and its language data AND a hardened fetch: an agent that pulls the image URL itself walks past every SSRF control, and carrying a WASM Tesseract plus a language model is not something an agent does per call.

Your source is GIF, JPEG, PNG, TIFF or WebP and you need plain text.

When not to use it

  • The input is over 10 MB (10,485,760 bytes): ocr-image-to-text answers too_large (413).
  • The destination needs more than 45 s to answer: the call ends with upstream_timeout (424).
  • The destination is on a private or local network: the network guard refuses it with blocked_target (403).

Parameters

One JSON body. The schema is free at GET /v1/ocr-image-to-text/schema.

FieldTypeRequiredDescription
urlstringyesAbsolute http(s) URL of the image, up to 2048 characters and 10 MB; redirects are followed, the bytes must be PNG, JPEG, TIFF, WebP or GIF by signature, and at most 40 megapixels.
langstringnoTesseract language model to read the text with; only languages whose data ships with the service are accepted, today eng (the default). One of: "eng". Default: "eng".

Limits

LimitValue
Largest source file10 MB (10,485,760 bytes)
Timeout45 s
Source formatsGIF, JPEG, PNG, TIFF, WebP
Output formatsplain text
Show the JSON Schema the handler validates against
JSON Schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "format": "uri",
      "description": "Absolute http(s) URL of the image, up to 2048 characters and 10 MB; redirects are followed, the bytes must be PNG, JPEG, TIFF, WebP or GIF by signature, and at most 40 megapixels."
    },
    "lang": {
      "default": "eng",
      "description": "Tesseract language model to read the text with; only languages whose data ships with the service are accepted, today eng (the default).",
      "type": "string",
      "enum": [
        "eng"
      ]
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

Example

The published example, verbatim: the request and the response it returns.

Request
POST /v1/ocr-image-to-text
content-type: application/json
payment-signature: <base64 x402 payload>

{
  "url": "https://grist.tools/samples/images/ocr-scan.png",
  "lang": "eng"
}

Without the payment-signature header the call answers 402 with the payment requirements, including this endpoint's price and its max_timeout_seconds, so the deadline is known before anything is paid. The payment is verified before the handler runs and settled only after it succeeds, so a call refused by the gate, or one that fails inside the handler, is never settled. The single case we cannot state for you is a settlement call that fails without answering: the error message says so when that is what happened.

Response200 OK
200 OK
payment-response: <base64 settlement receipt>

{
  "source_url": "https://grist.tools/samples/images/ocr-scan.png",
  "lang": "eng",
  "image_format": "png",
  "text": "SAMPLE SCAN FOR OCR\nSECOND LINE 2026\n",
  "confidence": 86
}

Sample file: images/ocr-scan.png. 1-bit black-on-white PNG with two uppercase lines drawn from a hand-written 5x7 bitmap font: SAMPLE SCAN FOR OCR and SECOND LINE 2026.

In the sample itself: its IHDR chunk declares 556 by 100 pixels, 1-bit greyscale and no interlacing. The chunks run IHDR, IDAT and IEND. The returned text runs to 3 lines, 1 blank one among them, and its longest line, "SAMPLE SCAN FOR OCR", holds 19 characters. Its first line reads "SAMPLE SCAN FOR OCR" and its last "SECOND LINE 2026". Split on whitespace, it yields 7 tokens over 2 non-blank lines.

Response fields

FieldTypeIn the example
source_urlstring"https://grist.tools/samples/images/ocr-scan.png"
langstring"eng"
image_formatstring"png"
textstring"SAMPLE SCAN FOR OCR SECOND LINE 2026 "
confidencenumber86

Deterministic: the same input returns the same output. Clock-derived fields, when present, are declared in the response.

Call it from code

The client reads the 402, signs the payment and retries on its own.

// ocr-image-to-text: $0.005 per call, paid in USD Coin on eip155:8453 via x402
// Install: npm install @x402/fetch@2 @x402/evm@2 viem@2
// Save as client.mjs (ES module, Node 18+), export EVM_PRIVATE_KEY with the paying wallet's key in your shell, then run: node client.mjs
// The wrapper reads the 402 (payment-required), signs and retries with payment-signature.
import { wrapFetchWithPayment, x402Client, decodePaymentResponseHeader } from '@x402/fetch'
import { ExactEvmScheme } from '@x402/evm/exact/client'
import { privateKeyToAccount } from 'viem/accounts'

const account = privateKeyToAccount(process.env.EVM_PRIVATE_KEY)
const client = new x402Client().register('eip155:8453', new ExactEvmScheme(account))
const fetchWithPayment = wrapFetchWithPayment(fetch, client)

const body = {
  "url": "https://grist.tools/samples/images/ocr-scan.png",
  "lang": "eng"
}

const res = await fetchWithPayment('https://grist.tools/v1/ocr-image-to-text', {
  method: 'POST',
  headers: { 'content-type': 'application/json' },
  body: JSON.stringify(body),
})
console.log(res.status, await res.json())
const settle = res.headers.get('payment-response')
if (settle) console.log(decodePaymentResponseHeader(settle).transaction)

Errors

Every error is typed JSON. Only a successful call is settled.

CodeHTTPWhen
invalid_input400The body does not match the schema on this page. Nothing is charged. The body does not match the schema; its fields are url and lang.
blocked_target403The destination is refused by the network guard: a disallowed address, or, for HTTP requests, a scheme other than http/https, a port other than 80/443, or credentials in the URL.
unreachable_target424The destination you named did not resolve or refused the connection.
upstream_timeout424The destination you named did not answer before the declared timeout for this endpoint expired.
unsupported_content_type415The destination returned a type this endpoint does not handle. The source is not a type ocr-image-to-text reads; it reads GIF, JPEG, PNG, TIFF and WebP.
too_large413The response exceeded the size cap while streaming, or decompressed at more than the allowed ratio.
unprocessable422The bytes arrived but could not be processed, for instance a malformed document.
internal500Our fault, and in almost every case nothing is charged. The exceptions come after the call has run and the settlement call was made: the message "The work was done but settlement could not be completed", and the messages starting with "Payment settlement returned". There, whether the payment moved is unknown to us as well. The payment moves at most once: its nonce is single-use and settlement is idempotent, so a retry with it is never charged twice. A retry is normally refused with a 402: replay_consumed, an expiry reason, or a reason saying the nonce was already used once the transfer is on-chain. Only if our server restarted before the transfer was final can a retry run the call again. Even then, the payment moves at most once. To see whether it was settled, read the EIP-3009 authorizationState of its nonce on-chain; to call again, sign a new payment.
rate_limited429Too many calls from the same payer, or too many calls towards the same destination domain. Nothing is charged.
concurrency_limit,
registry_at_capacity,
upstream_unavailable
503We could not serve the call right now. Retryable: wait the number of seconds in the retry-after header, then repeat the call. concurrency_limit and registry_at_capacity mean we were at capacity: the call did not run. You can send the same payment again if its validBefore is still far enough away to cover another call. If it is not, the retry gets a 402 authorization_validity_too_short: sign a new payment. upstream_unavailable means our internal service failed or did not answer in time: the call may already have run and the payment may have been settled. A retry with the same payment can get a 402 whose error field says why. authorization_validity_too_short: too little time is left before validBefore to cover another call. This check comes before the replay check, so it does not tell whether the first payment was settled. replay_consumed (the payment was used and may have been settled) or replay_exhausted (too many attempts): sign a new payment. replay_in_flight: the first call is still running, so wait and do not pay again. invalid_exact_evm_nonce_already_used: the transfer is already on-chain, so this payment cannot move again. Sign a new payment. An authorization can be settled only once, since its nonce is single-use. To see whether it was settled, read the EIP-3009 authorizationState of its nonce on-chain.
misconfigured503The service is not configured to serve calls. The call did not run and nothing is charged. It needs a fix on our side, so there is no retry delay to wait for.

Input that is rejected before the tool runs (malformed JSON, schema mismatch, body over the size limit) is never charged.

Conversions

Ready-made calls to this API, one page each.

ConversionRecorded sampleSourceOutput
GIF to plain textimages/pair-note.gif1.9 KB37 bytes
JPEG to plain textimages/pair-note.jpg5.2 KB37 bytes
PNG to plain textimages/ocr-scan.png7 KB37 bytes
TIFF to plain textimages/pair-note.tiff3.6 KB37 bytes
WebP to plain textimages/pair-note.webp248 bytes37 bytes

Questions

How much does a call to the OCR Image to Text API cost?

$0.005 per call, paid in USD Coin on Base via x402. There is no account and no API key: the price is in the 402 answer, before anything is paid.

What is the timeout of ocr-image-to-text?

The endpoint itself runs for at most 45 s. max_timeout_seconds in the 402 answer is 66: that covers the whole call, including payment verification and settlement around it.

How large can a response from ocr-image-to-text be?

The response-size cap is 10 MB (10,485,760 bytes).

Is the ocr-image-to-text input schema free to read?

Yes. GET https://grist.tools/v1/ocr-image-to-text/schema returns the input schema for free, paid endpoints included.

What happens if a call to ocr-image-to-text fails?

The payment is verified before the handler runs and settled only after it succeeds, so a call refused by the gate, or one that fails inside the handler, is never settled. The single case that cannot be stated in advance is a settlement call that fails without answering: the error message says so when that is what happened.

What does ocr-image-to-text return?

A JSON object with 5 top-level fields: source_url, lang, image_format, text and confidence. The example on this page is a real call over images/ocr-scan.png.