Paywary

Leaderboard / api.kit-rx.com / endpoint

GET https://api.kit-rx.com/v1/web/read

Scores measure reliability and honesty, not output quality.

84Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered 9 of 10 probes in the last 7 days (90%).
Category
Inference by llm, confidence 60%
Latest quote
— on — to —
Uptime
90% / 7d, 90% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
7h ago
Next probe
2026-11-19 04:14 UTC

Score components

Uptime, 7 days
72w 15%
Uptime, 30 days
72w 15%
Valid x402 challenge
100w 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
cdpexacteip155:13290xe15f…239240000xAf8E…8D70defaultyes6h ago
cdpexactBase0x8335…2913$0.0040xAf8E…8D70defaultyes6h ago
cdpexactAvalanche0xB97E…8a6E40000xAf8E…8D70defaultyes6h ago
payaiexactBase0x8335…2913$0.0040xAf8E…8D70defaultyes5h ago
payaiexactAvalanche0xB97E…8a6E40000xAf8E…8D70defaultyes5h ago
payaiexacteip155:13290xe15f…239240000xAf8E…8D70defaultyes5h ago

Listing changes

WhenEventFromTo
40h agodisappeared——
40h 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
27h agoInference60%llmv1claude-haiku-5-5: It answers questions over a web page using an LLM, returning answers, quotes, summaries and key points. It also fetches the page, but the core output is model-generated question answering, which fits inference better than web_scrape.
2d agoInference60%rulesv1rule inference matched "claude" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
7h agofreenetwork782 ms————no_responsefetch_error:network
13h agofree40244 msv2yes$0.0040xAf8E…8D70—
19h agofree402990 msv2yes$0.0040xAf8E…8D70—
25h agofree402118 msv2yes$0.0040xAf8E…8D70—
31h agofree40228 msv2yes$0.0040xAf8E…8D70—
38h agofree40228 msv2yes$0.0040xAf8E…8D70—
44h agofree40260 msv2yes$0.0040xAf8E…8D70—
2d agofree40276 msv2yes$0.0040xAf8E…8D70—
2d agofree40241 msv2yes$0.0040xAf8E…8D70—
3d agofree40235 msv2yes$0.0040xAf8E…8D70—