Paywary

Leaderboard / api.jubjubapp.com / endpoint

POST https://api.jubjubapp.com/v2/paid/purchase_metadata

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 1 day ago; new listings earn trust over 30 days.
  • Answered all 7 probes in the last 7 days.
Category
Inference by llm, confidence 55%
Latest quote
$0.012 on Base to 0xD3b2…3dC8
Uptime
100% / 7d, 100% / 30d
HTTPS
yes
First listed
2026-11-16
Last probe
21m ago
Next probe
2026-11-17 23:49 UTC

Score components

Uptime, 7 days
100w 20%
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
5w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0120xD3b2…3dC8defaultyes4h ago

Listing changes

WhenEventFromTo
4h agodescription_changedUnlocks all structured metadata for a single piece of content: full questions answered, complete training caption, cinematographic analysis, provenance score, entity extraction, and chapter markers. Idempotent within 24 hours. Call this before purchase_content. Payment is distributed to the content's rights holders on-chain; JubJub retains a 3% platform fee. Browse the full catalogue and search it for free at JubJub's MCP: https://api.jubjubapp.com/v2/mcpStructured metadata for one piece of creator media on JubJub: the questions it answers, a training caption, cinematographic analysis, a provenance confidence score, extracted entities and chapter markers. Suited to training sets, search indexes and recommendations. Idempotent per wallet for 24 hours. No media file is delivered. Paid on-chain to the rights holders, less a 3% platform fee. Free catalogue search: JubJub's MCP at https://api.jubjubapp.com/v2/mcp

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. Delivery results do not affect scores yet.

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
4h agoInference55%llmv1claude-haiku-5-5: The endpoint returns AI-style generated analysis of a media item (training caption, Q&A, cinematographic analysis, entity extraction, chapter markers), which fits model output. It is not a clear match for any other category, and the listing does not state the underlying model or method, so confidence is moderate.
4h agoOther40%rulesv1rule none matched "" in none
21h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
21m agofree402680 msv2yes$0.0120xD3b2…3dC8—
7h agofree402523 msv2yes$0.0120xD3b2…3dC8—
13h agofree402451 msv2yes$0.0120xD3b2…3dC8—
19h agofree4021162 msv2yes$0.0120xD3b2…3dC8—
25h agofree402331 msv2yes$0.0120xD3b2…3dC8—
32h agofree402384 msv2yes$0.0120xD3b2…3dC8—
38h agofree402382 msv2yes$0.0120xD3b2…3dC8—