Paywary

Leaderboard / getnightshift.tech / endpoint

GET https://getnightshift.tech/api/v1/swarm/order

Scores measure reliability and honesty, not output quality.

35Avoidconfidence: medium
  • Responded without asking for payment on 7 probes; it may no longer be an x402 endpoint.
  • Answered 7 of 10 probes in the last 7 days (70%).
Category
Commerce by llm, confidence 50%
Latest quote
— on — to —
Uptime
70% / 7d, 70% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
3h ago
Next probe
2026-11-18 18:42 UTC

Score components

Uptime, 7 days
25w 15%
Uptime, 30 days
25w 15%
Valid x402 challenge
0w 15%
Price honesty
n/aexcluded
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
8w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$30x989D…5a36defaultyes5h 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
33h agoCommerce50%llmv1claude-haiku-5-5: The endpoint orders paid agent-swarm work (building websites, research reports, audits, contracts) via a quote-and-order flow with USDC payment and refunds, which is a marketplace/service ordering pattern rather than any single data or inference category. Commerce fits best as a service-purchase marketplace, though the work deliverables overlap with inference and web_audit, so confidence is moderate.
42h agoInference60%rulesv1rule inference matched "llm" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofree503671 ms—no——server_errorstatus_not_402
10h agofree503157 ms—no——server_errorstatus_not_402
16h agofree503650 ms—no——server_errorstatus_not_402
23h agofree404183 ms—no——not_foundstatus_not_402
29h agofree404691 ms—no——not_foundstatus_not_402
35h agofree404663 ms—no——not_foundstatus_not_402
42h agofree404677 ms—no——not_foundstatus_not_402
2d agofree404691 ms—no——not_foundstatus_not_402
2d agofree404163 ms—no——not_foundstatus_not_402
3d agofree404199 ms—no——not_foundstatus_not_402