Paywary

Leaderboard / api.vextorium.com / endpoint

POST https://api.vextorium.com/v1/llm-token-count

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
Utility by llm, confidence 55%
Latest quote
$0.003 on Base to 0xb9f0…1aCf
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
2m ago
Next probe
2026-11-18 05:22 UTC

Score components

Uptime, 7 days
100w 15%
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
6w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0030xb9f0…1aCfdefaultyes1h ago
cdpexactSolanaEPjFWd…Dt1v3000HcjfmZ…3pz2defaultyes1h ago
cdpexactxrpl:0524C55…0000—rEac5r…pNCpdefaultyes1h ago
cdpexacteip155:100x0b2C…Ff8530000xb9f0…1aCfdefaultyes1h ago
cdpexactxrpl:0XRP2310rEac5r…pNCpdefaultyes1h ago
cdpexactPolygon0x3c49…335930000xb9f0…1aCfdefaultyes1h ago
cdpexacteip155:50420x3600…000030000xb9f0…1aCfdefaultyes1h 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
22h agoUtility55%llmv1claude-haiku-5-5: The endpoint counts tokens in a supplied text using tokenizer libraries and returns counts and estimates for budgeting LLM calls. It is a small deterministic computation tool, so utility fits best. It could also be seen as data_transform, but utility is closer to a practical helper, and inference is not appropriate since no model output is generated.
26h agoInference60%rulesv1rule inference matched "gpt-4" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
2m agofree402212 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
6h agofree402610 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
13h agofree402209 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
19h agofree402340 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
25h agofree402593 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
31h agofree402232 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
38h agofree402511 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string
44h agofree402203 msv2option ok$0.0030xb9f0…1aCfmalformed_challenge
accepts[2].amount_not_uint_string