Paywary

Leaderboard / api.rentaipower.app / endpoint

POST https://api.rentaipower.app/v1/chat/completions

Scores measure reliability and honesty, not output quality.

90Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Quoted a price different from the listed price on 4 of 9 comparable probes.
Category
Inference by llm, confidence 97%
Latest quote
$0.001 on Base to 0x3Bab…a521
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
1h ago
Next probe
2026-11-18 12:11 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
78w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
7w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0020x3Bab…a521defaultyes3h ago

Listing changes

WhenEventFromTo
34h agodescription_changedOpenAI-compatible chat completion with openai/gpt-oss-20b (open-weight, Apache 2.0). Send a messages array like the OpenAI Chat Completions API; get one non-streaming answer of up to 1024 tokens. Supports reasoning and multilingual text. Pay per request in USDC, no API key or account. You are charged only when a non-empty answer is returned.Ternary Bonsai 27B by PrismML: a ternary (1.58-bit) compressed build of Qwen3.6-27B (Apache 2.0) that keeps most of the original quality, served from dedicated Apple Silicon hardware. Good reasoning and coding. Text only. OpenAI-compatible chat completions: Accepts a messages array and returns one non-streaming answer of up to 1024 tokens. Pay per request in USDC, no API key or account. You are charged only when a non-empty answer is returned.

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
30h agoInference97%llmv1claude-haiku-5-5: The endpoint is an OpenAI-compatible chat completions API accepting a messages array and returning LLM-generated text, which is squarely the inference category.
34h agoInference60%rulesv1rule inference matched "openai-compatible" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
1h agofree402652 msv2yes$0.0010x3Bab…a521price_below_listingprice_mismatch
8h agofree402746 msv2yes$0.0010x3Bab…a521price_below_listingprice_mismatch
14h agofree402882 msv2yes$0.0010x3Bab…a521price_below_listingprice_mismatch
21h agofree402677 msv2yes$0.0010x3Bab…a521price_below_listingprice_mismatchprice_changed
27h agofree402704 msv2yes$0.0020x3Bab…a521—
33h agofree402577 msv2yes$0.0020x3Bab…a521—
39h agofree402613 msv2yes$0.0020x3Bab…a521—
46h agofree402640 msv2yes$0.0020x3Bab…a521—
2d agofree402642 msv2yes$0.0020x3Bab…a521—