Paywary

Leaderboard / media.gedx402.com / endpoint

POST https://media.gedx402.com/v1/vision/:model

Scores measure reliability and honesty, not output quality.

70Cautionconfidence: medium
  • Responded without asking for payment on 9 probes; it may no longer be an x402 endpoint.
  • Listed only 2 days ago; new listings earn trust over 30 days.
Category
Inference by llm, confidence 80%
Latest quote
— on — to —
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
1h ago
Next probe
2026-11-18 12:26 UTC

Score components

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

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.010xb3C2…2Ab6defaultyes3h 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
31h agoInference80%llmv1claude-haiku-5-5: The endpoint runs a vision-language model (Moondream) to answer questions, caption, point and detect objects in an image, returning model-generated text. This is model output rather than a web scrape, image generation, or classic computer vision signal, so inference is the closest fit, with moderate confidence given the detection and pointing tasks.
34h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
1h agofree400194 ms—no——unexpected_status:400status_not_402
8h agofree400559 ms—no——unexpected_status:400status_not_402
14h agofree40083 ms—no——unexpected_status:400status_not_402
21h agofree400209 ms—no——unexpected_status:400status_not_402
27h agofree400871 ms—no——unexpected_status:400status_not_402
33h agofree400604 ms—no——unexpected_status:400status_not_402
39h agofree400777 ms—no——unexpected_status:400status_not_402
46h agofree400532 ms—no——unexpected_status:400status_not_402
2d agofree4001006 ms—no——unexpected_status:400status_not_402