Paywary

Leaderboard / agentsvc.io / endpoint

POST https://agentsvc.io/api/v1/proxy/text-classify

Scores measure reliability and honesty, not output quality.

94Payconfidence: high
  • Listed only 3 days ago; new listings earn trust over 30 days.
  • Answered all 13 probes in the last 7 days.
Category
Inference by llm, confidence 85%
Latest quote
$0.002 on Base to 0x622e…4F27
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
37m ago
Next probe
2026-11-19 14:45 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
11w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0020x622e…4F27defaultyes3h ago
cdpexactSolanaEPjFWd…Dt1v20005JzPS5…77tgdefaultyes3h ago
cdpexactArbitrum0xaf88…583120000x622e…4F27defaultyes3h ago
payaiexactBase0x8335…2913$0.0020x622e…4F27defaultyes3h ago
cdpexactPolygon0x3c49…335920000x622e…4F27defaultyes3h 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
2d agoInference85%llmv1claude-haiku-5-5: The endpoint takes text and caller-defined labels and returns a best label with confidence and a reason, which is LLM-based classification, matching the model-output inference category rather than sentiment-specific signal or data transform.
3d agoData transform60%rulesv1rule data_transform matched "json schema" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
37m agofree402150 msv2yes$0.0020x622e…4F27—
7h agofree402154 msv2yes$0.0020x622e…4F27—
13h agofree402679 msv2yes$0.0020x622e…4F27—
20h agofree402155 msv2yes$0.0020x622e…4F27—
27h agofree402153 msv2yes$0.0020x622e…4F27—
33h agofree402153 msv2yes$0.0020x622e…4F27—
40h agofree402737 msv2yes$0.0020x622e…4F27—
46h agofree402689 msv2yes$0.0020x622e…4F27—
2d agofree402162 msv2yes$0.0020x622e…4F27—
2d agofree402153 msv2yes$0.0020x622e…4F27—
3d agofree402153 msv2yes$0.0020x622e…4F27—
3d agofree402154 msv2yes$0.0020x622e…4F27—
3d agofree402153 msv2yes$0.0020x622e…4F27—