OCR Document Parsing

documents

Serving

OCR and document parsing: turn an image or PDF into extracted text with layout hints. POST /v1/ocr with a document (or raw text) in the body and get the extracted text and metrics as one JSON object. Deterministic on clean inputs at a fixed engine version. Pay per request in USDC; no account, no API key.

Endpoint: POST https://agent.pocket.network/v1/ocr-document-parsing/v1/ocr
Price per call: $0.005 USD
Networks payable on: Base (eip155:8453), Tempo (eip155:4217)
Protocol: rest

Calling it

The first call returns 402 Payment Required with the terms. Sign for those terms and retry the same request with the payment attached.

Example request

A real, working call — the request the service card verifies against.

curl -X POST https://agent.pocket.network/v1/ocr-document-parsing/v1/ocr \
  -H 'content-type: application/json' \
  -d '{"text":"Invoice from Acme Corp, total $42.00, dated 2026-01-15."}'

Example response

The response this call returned, captured 2026-09-21 23:48:29 UTC.

{
  "portal": {
    "provenance": "third-party-supplier",
    "serviceId": "ocr-document-parsing",
    "schemaCheck": "unchecked"
  },
  "data": {
    "kind": "text-parse",
    "pages_hint": 1,
    "chars": 55,
    "lines": 1,
    "words": 8,
    "note": "text-mode layout stats; binary OCR needs tesseract on host (adapter pending)",
    "engine": "layout-v1",
    "deterministic": true,
    "as_of": "2026-09-21"
  }
}

Try it

Make one real paid call from your own wallet — about $0.005 on Base (eip155:8453). The wallet signs; nothing here holds a key. You'll see exactly what the service answers.

No browser wallet found. Install MetaMask, Rabby, or Coinbase Wallet to try a call here.

EndpointRequest body

Supported methods

Methods the registry lists for this service. The portal forwards any call as sent; the supplier decides what it answers, and a delivered answer is settled.

Methods OCR Document Parsing accepts, and whether each reads or writes.
Method	Effect
`GET /v1/health`	read
`GET /v1/version`	read
`POST /v1/ocr`	read

Schemas

Published by the service itself. The example above is generated from these.

Request schema

{
  "type": "object",
  "description": "Provide a document to OCR or raw text; input lives in the body since callers cannot send headers.",
  "properties": {
    "image": {
      "type": "string",
      "description": "Base64-encoded image."
    },
    "pdf": {
      "type": "string",
      "description": "Base64-encoded PDF."
    },
    "text": {
      "type": "string",
      "description": "Raw text (bypasses OCR)."
    }
  },
  "required": []
}

Response schema

{
  "type": "object",
  "description": "For POST /v1/ocr, a JSON object with the extracted text, character count (`chars`), and layout hints. The exact shape is the service's own and is not pinned here; errors return a JSON object with an `error` field, and the GET routes return their own small JSON documents."
}