Paywary

Leaderboard / verdict.kechlab.com / endpoint

POST https://verdict.kechlab.com/v1/transcribe

Scores measure reliability and honesty, not output quality.

85Payconfidence: medium
  • Quoted a price different from the listed price on 12 of 12 comparable probes.
  • Listed only 3 days ago; new listings earn trust over 30 days.
Category
Document by llm, confidence 85%
Latest quote
$0.0104 on Base to 0xb36c…54Eb
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
3h ago
Next probe
2026-11-19 08:00 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
50w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
10w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.01180xb36c…54Ebdefaultyes5h 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 agoDocument85%llmv1claude-haiku-5-5: The endpoint transcribes audio recordings into JSON transcripts with speaker labels and language detection, which matches the document category covering transcription and file conversion, rather than inference, since its output is a speech-to-text transcript instead of model-generated text. The description is truncated but the purpose is clear.
2d agoInference60%rulesv1rule inference matched "transcript" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofree402538 msv2yes$0.01040xb36c…54Ebprice_below_listingprice_mismatchprice_changed
9h agofree402991 msv2yes$0.01050xb36c…54Ebprice_below_listingprice_mismatchprice_changed
16h agofree4021249 msv2yes$0.01070xb36c…54Ebprice_below_listingprice_mismatch
22h agofree4021390 msv2yes$0.01070xb36c…54Ebprice_below_listingprice_mismatchprice_changed
29h agofree402484 msv2yes$0.01080xb36c…54Ebprice_below_listingprice_mismatchprice_changed
35h agofree402602 msv2yes$0.01060xb36c…54Ebprice_below_listingprice_mismatchprice_changed
42h agofree402909 msv2yes$0.01070xb36c…54Ebprice_below_listingprice_mismatchprice_changed
2d agofree402594 msv2yes$0.01080xb36c…54Ebprice_below_listingprice_mismatchprice_changed
2d agofree4021407 msv2yes$0.01090xb36c…54Ebprice_below_listingprice_mismatchprice_changed
3d agofree402706 msv2yes$0.01070xb36c…54Ebprice_below_listingprice_mismatch
3d agofree4021411 msv2yes$0.01070xb36c…54Ebprice_below_listingprice_mismatchprice_changed
3d agofree402615 msv2yes$0.01080xb36c…54Ebprice_below_listingprice_mismatch