Paywary

Leaderboard / kristo-intelligence-api.onrender.com / endpoint

GET https://kristo-intelligence-api.onrender.com/api/bot-status

Scores measure reliability and honesty, not output quality.

74Cautionconfidence: medium
  • The payment wallet changed in the last 7 days, which caps the verdict at caution until it has been stable for a week.
  • The payment wallet changed 3 times in the last 30 days.
Category
Other by llm, confidence 50%
Latest quote
$0.005 on Base to 0xB4Fc…C844
Uptime
100% / 7d, 100% / 30d
HTTPS
yes
First listed
2026-11-16
Last probe
4h ago
Next probe
2026-11-17 10:26 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
0w 10%
Listing age
4w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
payaiexactBase0x8335…2913$0.0050xB4Fc…C844defaultyes1h ago
cdpexactBase0x8335…2913$0.0050xB4Fc…C844defaultyes2h ago

Listing changes

WhenEventFromTo
11h agodescription_changedTelegram sales bot status: heartbeat, subscribers, processed commands and service wallet state — updated live.Telegram bot status and bot health for this service: heartbeat, subscribers, processed commands and service wallet state — updated live. Useful when an agent has just taken a signal from this service and needs to know the engine behind it is alive.
11h agopayto_changed0xd4cdA900839c0feD4374EE37EA0dbe8E4C6fd08f0xB4FcF8ef52b5DC275924AeD2baE94FE6cb7fC844
11h agopayto_changed0xd4cdA900839c0feD4374EE37EA0dbe8E4C6fd08f0xB4FcF8ef52b5DC275924AeD2baE94FE6cb7fC844

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
7h agoOther50%llmv1claude-haiku-5-5: The endpoint reports heartbeat, uptime and health of the service's own Telegram bot, which does not match any listed category cleanly. It is closest to a service status check, so 'other' fits best with moderate confidence.
11h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
4h agofree402159 msv2yes$0.0050xB4Fc…C844—
10h agofree402106 msv2yes$0.0050xB4Fc…C844—
16h agofree40267 msv2yes$0.0050xB4Fc…C844payto_mismatchpayto_changed
23h agofree40246 msv2yes$0.0050xd4cd…d08f—
29h agofree40266 msv2yes$0.0050xd4cd…d08f—