Document Extract
by x402.hydratrader.ai in Documents & files
Extract JSON from a PDF or long document into your schema, with a verified source quote and page number for every field. Public PDF/HTML URL or pasted text, up to 40 pages. $0.30 USDC on Base via x402. No API key. Text PDFs only (no OCR); no login/paywall sources.
https://x402.hydratrader.ai/v1/document-extract- Price
- $0.3
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 821 ms
- 1.0 s slowest 5%
- Last check
- Passed
- 2 h ago, next any minute now
Reliability
How to call it
POST https://x402.hydratrader.ai/v1/document-extract
Each call costs $0.3 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://x402.hydratrader.ai/v1/document-extract
content-type: application/json
{
"client_ref": "demo-1",
"schema": {
"properties": {
"author": {
"type": "string"
},
"category": {
"type": "string"
},
"published": {
"type": "string"
},
"rfc_number": {
"type": "integer"
},
"title": {
"type": "string"
}
},
"required": [
"rfc_number",
"title"
],
"type": "object"
},
"source": {
"type": "public_url",
"url": "https://www.rfc-editor.org/rfc/pdfrfc/rfc2119.txt.pdf"
}
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
client_ref | string | No | |
instructions | string | No | Optional formatting hints (e.g. 'amounts in USD') |
pages | string | No | Optional PDF page selection like '1-20,25' (≤40 pages; required when the PDF has >40 pages) |
schema | object | Yes | JSON Schema (type=object) for the record you want; 1–40 top-level properties; nested objects/arrays allowed |
source | object | Yes |
Example response
The provider's example. We can't check it without paying.
Example response, 75 lines
{
"client_ref": "demo-1",
"confidence": 0.95,
"coverage": 1,
"data": {
"author": "S. Bradner",
"category": "Best Current Practice",
"published": "March 1997",
"rfc_number": 2119,
"title": "Key words for use in RFCs to Indicate Requirement Levels"
},
"endpoint": "document-extract",
"evidence": {
"author": {
"confidence": 0.95,
"page": 1,
"quote": "S. Bradner"
},
"category": {
"confidence": 0.95,
"page": 1,
"quote": "Category: Best Current Practice"
},
"published": {
"confidence": 0.95,
"page": 1,
"quote": "March 1997"
},
"rfc_number": {
"confidence": 0.95,
"page": 1,
"quote": "Request for Comments: 2119"
},
"title": {
"confidence": 0.95,
"page": 1,
"quote": "Key words for use in RFCs to Indicate Requirement Levels"
}
},
"missing": [],
"next_tasks": [
{
"endpoint": "https://x402.hydratrader.ai/v1/summarize",
"example_body": {
"client_ref": "demo-1",
"input": "{\"rfc_number\":2119,…}"
},
"method": "POST",
"price_usd": "0.01",
"task": "summarize",
"why": "Short plain-language reading of the extracted record"
}
],
"ok": true,
"schema_valid": true,
"source_meta": {
"chars": 9000,
"pages_read": 3,
"pages_total": 3,
"sha256": "…",
"truncated": false,
"type": "pdf",
"url": "https://www.rfc-editor.org/rfc/pdfrfc/rfc2119.txt.pdf"
},
"usage": {
"input_tokens": 3600,
"latency_ms": 6000,
"llm_calls": 1,
"model": "grok-4.20-0309-non-reasoning",
"model_cost_est_usdc": "0.0051",
"output_tokens": 250,
"price_usdc": "0.30"
},
"warnings": []
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.3.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://x402.hydratrader.ai/v1/document-extract' \
-H 'content-type: application/json' \
--data-raw '{"client_ref":"demo-1","schema":{"properties":{"author":{"type":"string"},"category":{"type":"string"},"published":{"type":"string"},"rfc_number":{"type":"integer"},"title":{"type":"string"}},"required":["rfc_number","title"],"type":"object"},"source":{"type":"public_url","url":"https://www.rfc-editor.org/rfc/pdfrfc/rfc2119.txt.pdf"}}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://x402.hydratrader.ai/v1/document-extract' \
-H 'content-type: application/json' \
--data-raw '{"client_ref":"demo-1","schema":{"properties":{"author":{"type":"string"},"category":{"type":"string"},"published":{"type":"string"},"rfc_number":{"type":"integer"},"title":{"type":"string"}},"required":["rfc_number","title"],"type":"object"},"source":{"type":"public_url","url":"https://www.rfc-editor.org/rfc/pdfrfc/rfc2119.txt.pdf"}}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.3 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.3" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.3 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402.hydratrader.ai%2Fv1%2Fdocument-extract&method=POST
const res = await pay("https://x402.hydratrader.ai/v1/document-extract", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"client_ref": "demo-1",
"schema": {
"properties": {
"author": {
"type": "string"
},
"category": {
"type": "string"
},
"published": {
"type": "string"
},
"rfc_number": {
"type": "integer"
},
"title": {
"type": "string"
}
},
"required": [
"rfc_number",
"title"
],
"type": "object"
},
"source": {
"type": "public_url",
"url": "https://www.rfc-editor.org/rfc/pdfrfc/rfc2119.txt.pdf"
}
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.3 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.3"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://x402.hydratrader.ai/v1/document-extract",
json={
"client_ref": "demo-1",
"schema": {
"properties": {
"author": {
"type": "string",
},
"category": {
"type": "string",
},
"published": {
"type": "string",
},
"rfc_number": {
"type": "integer",
},
"title": {
"type": "string",
},
},
"required": [
"rfc_number",
"title",
],
"type": "object",
},
"source": {
"type": "public_url",
"url": "https://www.rfc-editor.org/rfc/pdfrfc/rfc2119.txt.pdf",
},
},
)
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 2 h ago | Passed | 402 | 965 ms | $0.3 |
| 6 h ago | Passed | 402 | 703 ms | $0.3 |
| 10 h ago | Passed | 402 | 898 ms | $0.3 |
| 14 h ago | Passed | 402 | 756 ms | $0.3 |
| 18 h ago | Passed | 402 | 717 ms | $0.3 |
Show 10 older checks
| 22 h ago | Passed | 402 | 681 ms | $0.3 |
| 26 h ago | Passed | 402 | 972 ms | $0.3 |
| 30 h ago | Passed | 402 | 1.0 s | $0.3 |
| 34 h ago | Passed | 402 | 791 ms | $0.3 |
| 37 h ago | Passed | 402 | 905 ms | $0.3 |
| 41 h ago | Passed | 402 | 765 ms | $0.3 |
| 44 h ago | Passed | 402 | 790 ms | $0.3 |
| 2 days ago | Passed | 402 | 881 ms | $0.3 |
| 2 days ago | Passed | 402 | 878 ms | $0.3 |
| 2 days ago | Passed | 402 | 777 ms | $0.3 |