Paywary

Leaderboard / agentbit.app / endpoint

POST https://agentbit.app/v1/inference/chat-pro

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
Inference by llm, confidence 97%
Latest quote
$0.045 on Base to 0x4395…d965
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 02:11 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
cdpexacteip155:4800x79A0…24d1450000x4395…d965defaultyes6h ago
cdpexactArbitrum0xaf88…5831450000x4395…d965defaultyes6h ago
cdpexactPolygon0x3c49…3359450000x4395…d965defaultyes6h ago
cdpexactBase0x8335…2913$0.0450x4395…d965defaultyes6h ago
cdpexactSolanaEPjFWd…Dt1v45000566SN4…BfYddefaultyes6h 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
33h agoInference97%llmv1claude-haiku-5-5: The endpoint is an OpenAI-compatible chat completion API that takes messages and returns model choices and usage, which is LLM model output.
2d agoInference60%rulesv1rule inference matched "openai-compatible" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofree402447 msv2yes$0.0450x4395…d965—
10h agofree402392 msv2yes$0.0450x4395…d965—
17h agofree402373 msv2yes$0.0450x4395…d965—
23h agofree402376 msv2yes$0.0450x4395…d965—
29h agofree402455 msv2yes$0.0450x4395…d965—
36h agofree4021064 msv2yes$0.0450x4395…d965—
42h agofree402396 msv2yes$0.0450x4395…d965—
2d agofree402755 msv2yes$0.0450x4395…d965—
2d agofree402416 msv2yes$0.0450x4395…d965—
3d agofree402992 msv2yes$0.0450x4395…d965—
3d agofree402374 msv2yes$0.0450x4395…d965—