Paywary

Leaderboard / slamlink-ai-main-50fbb45.d2.zuplo.dev / endpoint

GET https://slamlink-ai-main-50fbb45.d2.zuplo.dev/chain/tokens/trending

Scores measure reliability and honesty, not output quality.

90Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Quoted a price different from the listed price on 2 of 9 comparable probes.
Category
Chain read by llm, confidence 60%
Latest quote
$0.001 on Base to 0xd850…f111
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
57m ago
Next probe
2026-11-18 12:02 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
78w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
7w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
payaiexactBase0x8335…2913$0.0062440xd850…f111defaultyes2h ago
cdpexactBase0x8335…2913$0.0010xd850…f111defaultyes2h 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
30h agoChain read60%llmv1claude-haiku-5-5: The endpoint returns tokens ranked by the increase in active wallets across a blockchain over a time window, which is on-chain activity data. It is not a price or market snapshot, so chain_read fits best, though crypto_market is a plausible alternative.
33h agoChain read60%rulesv1rule chain_read matched "/chain/" in metadata

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
57m agofree402353 msv1yes$0.0010xd850…f111protocol_v1price_below_listingprice_mismatch
7h agofree402637 msv1yes$0.0010xd850…f111protocol_v1price_below_listingprice_mismatch
14h agofree402363 msv1yes$0.0010xd850…f111protocol_v1
21h agofree402372 msv1yes$0.0010xd850…f111protocol_v1
27h agofree402515 msv1yes$0.0010xd850…f111protocol_v1
33h agofree402509 msv1yes$0.0010xd850…f111protocol_v1
39h agofree402418 msv1yes$0.0010xd850…f111protocol_v1
45h agofree402370 msv1yes$0.0010xd850…f111protocol_v1
2d agofree402606 msv1yes$0.0010xd850…f111protocol_v1