Paywary

Leaderboard / marketplaceforaiagents.com / endpoint

GET https://marketplaceforaiagents.com/api/public/v1/amazon-search

Scores measure reliability and honesty, not output quality.

67Cautionconfidence: medium
  • Quoted a price different from the listed price on 5 of 5 comparable probes.
  • 4 probes got a response that was not a 402 payment challenge.
Category
Web search by llm, confidence 60%
Latest quote
$0.005 on Base to 0x05e8…b7b7
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
1h ago
Next probe
2026-11-18 12:34 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
56w 15%
Price honesty
0w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
7w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0030x05e8…b7b7defaultyes3h 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. 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
18h agoWeb search60%llmv1claude-haiku-5-5: The endpoint takes a product query and returns Amazon listings with ASIN, price and rating, which is a search over a marketplace's listings. It is closest to web_search, though it is a product catalog search rather than general web search, so confidence is moderate.
34h agoPublic data60%rulesv1rule public_data matched "amazon" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
1h agofree402947 msv2yes$0.0050x05e8…b7b7price_above_listingprice_mismatch
7h agofree2005816 ms—no——no_payment_requiredstatus_not_402
14h agofree4022349 msv2yes$0.0050x05e8…b7b7price_above_listingprice_mismatch
20h agofree4021526 msv2yes$0.0050x05e8…b7b7price_above_listingprice_mismatch
27h agofree2003459 ms—no——no_payment_requiredstatus_not_402
33h agofree2006855 ms—no——no_payment_requiredstatus_not_402
39h agofree4021633 msv2yes$0.0050x05e8…b7b7price_above_listingprice_mismatch
45h agofree4021551 msv2yes$0.0050x05e8…b7b7price_above_listingprice_mismatch
2d agofree2006249 ms—no——no_payment_requiredstatus_not_402