Paywary

Leaderboard / api.xynaptic.io / endpoint

GET https://api.xynaptic.io/v1/ai-health

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered all 11 probes in the last 7 days.
Category
Inference by llm, confidence 60%
Latest quote
$0.06 on Base to 0x4ff8…D5e9
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
31m ago
Next probe
2026-11-19 01:39 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
9w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactSolanaEPjFWd…Dt1v60000Aq6J1z…Ffeddefaultyes3h ago
cdpexactBase0x8335…2913$0.060x4ff8…D5e9defaultyes3h ago
cdpexactPolygon0x3c49…3359600000x3E39…F2C6defaultyes3h 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
36h agoInference60%llmv1claude-haiku-5-5: The endpoint takes a question and returns an LLM synthesis of official drug labels and health press, so model-generated output is central, though it also pulls openFDA data and news, making signal or web_search less apt.
46h agoInference60%rulesv1rule inference matched "llm" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
31m agofree402290 msv2yes$0.060x4ff8…D5e9—
8h agofree40296 msv2yes$0.060x4ff8…D5e9—
14h agofree40233 msv2yes$0.060x4ff8…D5e9—
20h agofree40228 msv2yes$0.060x4ff8…D5e9—
27h agofree40244 msv2yes$0.060x4ff8…D5e9—
33h agofree402180 msv2yes$0.060x4ff8…D5e9—
39h agofree40248 msv2yes$0.060x4ff8…D5e9—
45h agofree402190 msv2yes$0.060x4ff8…D5e9—
2d agofree402148 msv2yes$0.060x4ff8…D5e9—
2d agofree40229 msv2yes$0.060x4ff8…D5e9—
3d agofree40216 msv2yes$0.060x4ff8…D5e9—