Paywary

Leaderboard / api.mekongtradeintel.com / endpoint

POST https://api.mekongtradeintel.com/aiverdict

Scores measure reliability and honesty, not output quality.

91Payconfidence: medium
  • Listed only 1 day ago; new listings earn trust over 30 days.
  • Quoted a price different from the listed price on 2 of 7 comparable probes.
Category
Signal by llm, confidence 60%
Latest quote
$0.005 on Base to 0x198f…EA93
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
5m ago
Next probe
2026-11-18 05:48 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
86w 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$0.010x198f…EA93defaultyes2h 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
16h agoSignal60%llmv1claude-haiku-5-5: The endpoint returns an AI-written SAFE/RISKY/SCAM verdict on a token, which is a risk verdict. It also uses token safety screening (honeypot, tax, owner checks), which could map to crypto_market. The verdict framing fits signal best since the output is a risk judgment rather than raw safety data.
26h agoInference60%rulesv1rule inference matched "llm" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
5m agofree402825 msv2yes$0.010x198f…EA93price_changed
7h agofree4021074 msv2yes$0.0050x198f…EA93price_below_listingprice_mismatchprice_changed
13h agofree402792 msv2yes$0.010x198f…EA93—
19h agofree4024540 msv2yes$0.010x198f…EA93—
25h agofree4021054 msv2yes$0.010x198f…EA93price_changed
31h agofree402296 msv2yes$0.0050x198f…EA93price_below_listingprice_mismatchprice_changed
38h agofree402796 msv2yes$0.010x198f…EA93—
44h agofree402266 msv2yes$0.010x198f…EA93—