HUGEpdf.io / quickstart

Run your first PDF in one agent command.

1. Give This To Your Agent

Process this PDF with https://hugepdf.io/llms.txt
[PDF URL or local file]
[what you want extracted]

Example:

Process this PDF with https://hugepdf.io/llms.txt
https://example.com/catalog.pdf
Extract every product into JSON with sku, name, description, and price.

2. What The Agent Will Do

1. Submit the PDF.
2. Receive an exact page count and price quote.
3. Optionally preview page 1.
4. Pay the exact invoice from a funded Sui wallet.
5. Claim the payment.
6. Monitor progress.
7. Download results.json and page-level artifacts.
8. Retry failed pages if needed.

3. Price

$0.03 per processed page. No account. No API key. No sales call.
Need a wallet? Go to onboard. Use a fresh low-balance wallet for agent payments.

10 pages  -> $0.30
100 pages -> $3.00
500 pages -> $15.00

4. Fast Path For Software Agents

The first API response is designed to be paid by software: job_id, output_token, exact invoice amount, payment address, deadline, preview URL, status URL, and outputs manifest URL.

Payment deadline: 15 seconds. HugePDF is built for agents with funded wallets.

5. Preview Capability

Not sure about quality? The agent can request a first-page preview before paying for full processing:

GET /api/jobs/{job_id}/preview?token={output_token}

Preview lets the agent inspect first-page extraction quality before paying for the full document.

6. Human Status Page

Every job also has a browser status page: https://hugepdf.io/jobs/{job_id}

7. Machine Spec

Agents should follow https://hugepdf.io/llms.txt. Humans can inspect https://hugepdf.io/llms.