Paywary

Leaderboard / api.agent-preflight.com / endpoint

POST https://api.agent-preflight.com/v0.2/preflight/tool-call

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered all 11 probes in the last 7 days.
Category
Signal by llm, confidence 50%
Latest quote
$0.002 on Base to 0x75ea…2a8a
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 01:23 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
9w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0020x75ea…2a8adefaultyes5h 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
45h agoSignal50%llmv1claude-haiku-5-5: The endpoint returns a pre-execution decision (allow/deny style verdict) on a proposed tool call based on task, budget and history, which resembles a risk verdict rather than search or scraping since it does not execute the tool itself. Description is terse and the category is somewhat ambiguous, so confidence is moderate.
2d agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofree4021331 msv2yes$0.0020x75ea…2a8a—
10h agofree402428 msv2yes$0.0020x75ea…2a8a—
16h agofree402381 msv2yes$0.0020x75ea…2a8a—
23h agofree402511 msv2yes$0.0020x75ea…2a8a—
29h agofree4021122 msv2yes$0.0020x75ea…2a8a—
36h agofree402443 msv2yes$0.0020x75ea…2a8a—
42h agofree402788 msv2yes$0.0020x75ea…2a8a—
2d agofree4021058 msv2yes$0.0020x75ea…2a8a—
2d agofree402302 msv2yes$0.0020x75ea…2a8a—
3d agofree402324 msv2yes$0.0020x75ea…2a8a—
3d agofree402514 msv2yes$0.0020x75ea…2a8a—