Blockchain Data · x402

PDF text extraction — extract text from a public digital PDF into page-numbered JSON fo…

PDF text extraction — extract text from a public digital PDF into page-numbered JSON for RAG (no OCR). $0.01 USDC Base or Algorand. Caps 20 pages / 5 MiB / 100k chars; source + text SHA-256. No passwords or table reconstruction. Failed extractions not settled.

by api.agentwork.run · discovered, not yet claimed by its owner · updated 2026-10-08

Mirrored from Coinbase's public x402 Bazaar. The description is the provider's own text and has not been reviewed here; the payment requirements are copied as published.

What it does

PDF text extraction — extract text from a public digital PDF into page-numbered JSON for RAG (no OCR). $0.01 USDC Base or Algorand. Caps 20 pages / 5 MiB / 100k chars; source + text SHA-256. No passwords or table reconstruction. Failed extractions not settled.

Tags: pdf · text-extraction · documents · rag · pdf-to-text · bazaar

Use with an agent

  1. Discover. Agents find this listing with GET https://bazaar.saylorinnovations.com/discovery/search?query=…, the MCP tool search_resources, or /discovery/resources.
  2. Inspect. Fetch /resources/29331.json for the price and payment options.
  3. Pay. Call GET https://api.agentwork.run/v1/pdf/read. The provider answers 402 with its payment requirements. An x402 client signs one of the options below and retries with PAYMENT-SIGNATURE.
  4. Execute. The provider returns 200 with the data. Agent Bazaar is not in the request path and never sees your payment.

For humans

You don't need an account or an API key; you need a wallet holding a small amount of USDC on Base, algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=, and an x402-capable client (see the examples below). Call the endpoint unpaid first to see exactly what it asks for.

Pricing & payment

Price
$0.01 / request
Protocol
x402 v2
Auth
No account or API key. Pay per request.
Networks
Base, algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=
Calls (30d)
2 · 2 unique payers (third-party data from the public x402 Bazaar)

x402 payment requirements

SchemeNetworkAssetAmountPay toTimeout
exactBase
eip155:8453
USDC$0.010x1cfC6489bC9703a2A49715b8a746D8c6075F3A80300s
exactalgorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=
algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=
3156670410000PFHYLVHX77ANNQVF67LK6EVYB34D5VDIUOWLOL5SX367M366DBLOQQAOCA300s
accepts[] (raw JSON)
[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0x1cfC6489bC9703a2A49715b8a746D8c6075F3A80",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "10000",
    "amountUsd": 0.01,
    "maxTimeoutSeconds": 300
  },
  {
    "scheme": "exact",
    "network": "algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=",
    "payTo": "PFHYLVHX77ANNQVF67LK6EVYB34D5VDIUOWLOL5SX367M366DBLOQQAOCA",
    "asset": "31566704",
    "amount": "10000",
    "maxTimeoutSeconds": 300
  }
]

Schemas

Output schema (JSON Schema)
{
  "properties": {
    "example": {
      "type": "object"
    },
    "type": {
      "type": "string"
    }
  },
  "required": [
    "type"
  ],
  "type": "object"
}
Example shape — generated from the schema, not a captured live response
{
  "example": {},
  "type": "string"
}

Examples

curl
curl "https://api.agentwork.run/v1/pdf/read"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid
JavaScript
const res = await fetch("https://api.agentwork.run/v1/pdf/read");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}
Python
import httpx
res = httpx.get("https://api.agentwork.run/v1/pdf/read")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header

Details

Provider
api.agentwork.run
Endpoint
https://api.agentwork.run/v1/pdf/read
Machine-readable
/resources/29331.json