Paywary

Leaderboard / rtt.phoenix-ai.work / endpoint

GET https://rtt.phoenix-ai.work/api/v1/preflight

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered all 9 probes in the last 7 days.
Category
Crypto market data by llm, confidence 50%
Latest quote
$0.01 on Base to 0xbb96…44Ab
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 12:07 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 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$0.010xbb96…44Abdefaultyes2h ago
cdpexactArbitrum0xaf88…5831100000xbb96…44Abdefaultyes2h ago
cdpexactPolygon0x3c49…3359100000xbb96…44Abdefaultyes2h 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 agoCrypto market data50%llmv1claude-haiku-5-5: The endpoint judges whether a blockchain transaction is safe to send by checking observed network state and returning PASS/DEGRADED/FAIL. It is closest to token/transaction safety checks under crypto_market, though it relies on on-chain state (chain_read) and the description is somewhat generic about what is inspected.
33h agoPublic data60%rulesv1rule public_data matched "flight" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
57m agofree402115 msv2yes$0.010xbb96…44Ab—
7h agofree402822 msv2yes$0.010xbb96…44Ab—
14h agofree402194 msv2yes$0.010xbb96…44Ab—
20h agofree402110 msv2yes$0.010xbb96…44Ab—
26h agofree402175 msv2yes$0.010xbb96…44Ab—
33h agofree402300 msv2yes$0.010xbb96…44Ab—
39h agofree402293 msv2yes$0.010xbb96…44Ab—
45h agofree402287 msv2yes$0.010xbb96…44Ab—
2d agofree402118 msv2yes$0.010xbb96…44Ab—