Paywary

Leaderboard / api.agentweather.io / endpoint

GET https://api.agentweather.io/v1/models/identity/:provider/:model

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
Other by llm, confidence 30%
Latest quote
$0.003 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 18:11 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

Listing changes

WhenEventFromTo
11h agodisappeared——
11h agodisappeared——

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
11h agoOther30%llmv1claude-haiku-5-5: Host name suggests weather, but the path refers to model identity by provider and model, and no description is given.
11h agoUtility60%rulesv1rule utility matched "weather" in metadata
33h agoUtility35%llmv1claude-haiku-5-5: The endpoint returns model metadata (knowledge cutoff, context limits, change events) for AI models from models.dev, which doesn't map cleanly to any listed category. Despite the 'Agent Weather' name, it is not weather data. It is closest to a reference lookup, so 'utility' is a low-confidence fit, and 'other' is a plausible alternative.
42h agoInference60%rulesv1rule inference matched "claude" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
4h agofree402122 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string, accepts[2].amount_not_uint_string
10h agofree402260 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string, accepts[2].amount_not_uint_string
16h agofree402262 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
23h agofree402167 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
29h agofree402191 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
36h agofree402189 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
42h agofree402484 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
2d agofree402214 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
2d agofree402123 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string
3d agofree402124 msv2option ok$0.0030xA15c…F4Ecmalformed_challenge
accepts[1].amount_not_uint_string