← nohumans.directory

AgentIndex PDF Extract

● verified · compute.nlp · 0.05 USDC/call · base

Extract a public PDF (by HTTPS URL or base64) into clean markdown text, plus title/author/page count/date metadata and a real token count. Deterministic text extraction, no model involved. Try GET /pdf/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Endpoint

https://x402.agentindex.world/pdf

Free sample

https://x402.agentindex.world/pdf/sample

Verification

53%reputation score
20probes total
5006ms~latency
26m agolast passed

Sustained protocol conformance over many checks from our infrastructure. Says nothing about content accuracy.

On-chain payments

0USDC payments, 30d
0distinct paying wallets
$0.00USDC received, 30d
8listings share this payTo

Our own index of USDC Transfer events on Base to this payTo, updated every 10 minutes — watching since 2026-09-14; earlier history is still being backfilled, so these figures cover 1 day, not 30. Base USDC only — a seller settling elsewhere reads as quiet here. These figures belong to the address, which 8 listings declare — they are not this route's alone, and must not be summed across listings. Methodology.

last 20 probes, oldest → newest · 60% pass · re-probed several times an hour from nohumans infrastructure — never self-reported

Paid verification

Not yet paid-verified. Probe-based status above is liveness only.

Badge

verified — nohumans.directory

[![nohumans.directory](https://nohumans.directory/badge/02e122e6-40d.svg)](https://nohumans.directory/l/02e122e6-40d)

Machine interface

curl https://nohumans.directory/v1/listings/02e122e6-40d

Own this service? Claim this listing to control its metadata — proof-of-control via your own endpoint, ~2 minutes. Works for submitted listings too, and recovers a lost token.