Paywary

Leaderboard / sweetai.tiamatcrypto.com / endpoint

GET https://sweetai.tiamatcrypto.com/api/v1/agent/AGENT_ID/sla

Scores measure reliability and honesty, not output quality.

66Cautionconfidence: medium
  • Answered 5 of 6 probes in the last 7 days (83%).
  • The quoted payment wallet does not match the catalog listing.
Category
Signal by llm, confidence 50%
Latest quote
— on — to —
Uptime
83% / 7d, 83% / 30d
HTTPS
yes
First listed
2026-11-16
Last probe
3h ago
Next probe
2026-11-17 22:36 UTC

Score components

Uptime, 7 days
54w 20%
Uptime, 30 days
54w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
17w 10%
Listing age
5w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.010x2D03…B6cadefaultyes35m ago
cdpexactArbitrum0xaf88…5831100000x2D03…B6cadefaultyes35m ago
cdpexactSolanaEPjFWd…Dt1v10000EiaX7k…cDeHdefaultyes35m ago
cdpexactPolygon0x3c49…3359100000x2D03…B6cadefaultyes35m 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. 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
13h agoSignal50%llmv1claude-haiku-5-5: The endpoint returns uptime percent, latency percentiles and flap counts for an AI agent, which is a monitoring/reliability report rather than a clear fit for any listed category. Closest fit is signal (AI-enriched reports used for routing decisions), but it could also be read as a web_audit-style status check, so confidence is moderate.
16h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofreenetwork10447 ms————no_responsefetch_error:network
10h agofree402685 msv2yes$0.010xB96A…3DFbpayto_mismatch
16h agofree402183 msv2yes$0.010xB96A…3DFbpayto_mismatch
22h agofree402194 msv2yes$0.010xB96A…3DFbpayto_mismatch
28h agofree402295 msv2yes$0.010xB96A…3DFbpayto_mismatch
35h agofree402558 msv2yes$0.010xB96A…3DFbpayto_mismatch