Paywary

Leaderboard / agent.apiguru.app / endpoint

GET https://agent.apiguru.app/agent/v1/v2/product-reviews

Scores measure reliability and honesty, not output quality.

89Payconfidence: medium
  • Listed only 1 day ago; new listings earn trust over 30 days.
  • 2 probes got a response that was not a 402 payment challenge.
Category
Web scrape by llm, confidence 55%
Latest quote
$0.003 on Base to 0x766B…1422
Uptime
100% / 7d, 100% / 30d
HTTPS
yes
First listed
2026-11-16
Last probe
1h ago
Next probe
2026-11-17 23:48 UTC

Score components

Uptime, 7 days
100w 20%
Uptime, 30 days
100w 15%
Valid x402 challenge
71w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
6w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0030x766B…1422defaultyes5h ago
cdpexactPolygon0x3c49…335930000x766B…1422defaultyes5h ago
cdpexactArbitrum0xaf88…583130000x766B…1422defaultyes5h ago
cdpexactAvalanche0xB97E…8a6E30000x766B…1422defaultyes5h ago
payaiexactBase0x8335…2913$0.0030x766B…1422defaultyes5h ago

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. Delivery results do not affect scores yet.

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
5h agoWeb scrape55%llmv1claude-haiku-5-5: Returns Amazon product review content (ratings, review text, AI summary) for an ASIN, which is page-content retrieval of an e-commerce product rather than a clear fit for a named category. Closest matches are web_scrape (returns page content) or public_data; the commerce-product nature leans toward web_scrape, with moderate confidence.
21h agoInference60%rulesv1rule inference matched "sentiment analysis" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
1h agofree402568 msv2yes$0.0030x766B…1422—
8h agofree402553 msv2yes$0.0030x766B…1422—
14h agofree402589 msv2yes$0.0030x766B…1422—
20h agofree200534 ms—no——no_payment_requiredstatus_not_402
26h agofree402180 msv2yes$0.0030x766B…1422—
32h agofree402605 msv2yes$0.0030x766B…1422—
39h agofree200604 ms—no——no_payment_requiredstatus_not_402