Paywary

Leaderboard / agentdata-api.sander-van-aard.workers.dev / endpoint

POST https://agentdata-api.sander-van-aard.workers.dev/doc/markdown

Scores measure reliability and honesty, not output quality.

88Payconfidence: medium
  • 4 probes got a response that was not a 402 payment challenge.
  • Listed only 2 days ago; new listings earn trust over 30 days.
Category
Other by llm, confidence 15%
Latest quote
— on — to —
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
3h ago
Next probe
2026-11-19 02:21 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
64w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
9w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen

Listing changes

WhenEventFromTo
28h agodisappeared——

Paid probes

No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.

Delivery checks

Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.

No delivery checks yet. They run inside the weekly paid probe.

Classification history

Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.

WhenCategoryConfidenceMethodVersionEvidence
28h agoOther15%llmv1claude-haiku-5-5: The listing has no service name, description, tags, or example inputs. The host and path '/doc/markdown' hint at documentation returned as markdown, which could be a scrape-like endpoint, but the listing says too little to classify it confidently.
28h agoDocument50%rulesv1rule document matched "doc" in metadata
33h agoDocument95%llmv1claude-haiku-5-5: The endpoint converts uploaded or linked documents (PDF, DOCX, XLSX, HTML and similar) into LLM-ready markdown or plain text, which is file conversion, so it fits the document category.
2d agoDocument60%rulesv1rule document matched "pdf" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofree40033 ms—no——unexpected_status:400status_not_402
10h agofree40026 ms—no——unexpected_status:400status_not_402
17h agofree40056 ms—no——unexpected_status:400status_not_402
23h agofree40030 ms—no——unexpected_status:400status_not_402
30h agofree40297 msv2yes$0.050xb0ae…2099—
36h agofree40249 msv2yes$0.050xb0ae…2099—
42h agofree402110 msv2yes$0.050xb0ae…2099—
2d agofree40265 msv2yes$0.050xb0ae…2099—
2d agofree40258 msv2yes$0.050xb0ae…2099—
3d agofree40232 msv2yes$0.050xb0ae…2099—
3d agofree40213 msv2yes$0.050xb0ae…2099—