Paywary

Leaderboard / api.agentweather.io / endpoint

GET https://api.agentweather.io/v1/models/category/:name

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered all 10 probes in the last 7 days.
Category
Inference by llm, confidence 40%
Latest quote
$0.01 on Base to 0xA15c…F4Ec
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
4h ago
Next probe
2026-11-18 18:10 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
8w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactxrpl:0524C55…0000—rnFHPG…jrZZdefaultyes5h ago
cdpexactBase0x8335…2913$0.010xA15c…F4Ecdefaultyes5h 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
39h agoInference40%llmv1claude-haiku-5-5: The endpoint reports on AI model listings from the models.dev catalog (counts, price changes, new and removed models), which is closest to model metadata for LLMs, but it is not itself model output. Name suggests weather branding, yet the description clearly concerns AI model categories. Description is truncated, so confidence is moderate-low; 'other' is a plausible alternative.
42h agoUtility60%rulesv1rule utility matched "weather" in metadata

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
4h agofree402157 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string, accepts[2].amount_not_uint_string
10h agofree402225 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string, accepts[2].amount_not_uint_string
17h agofree402179 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
23h agofree402151 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
30h agofree402205 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
36h agofree402278 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
42h agofree402682 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
2d agofree402305 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
2d agofree402129 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
3d agofree402136 msv2option ok$0.010xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string