Leaderboard / agent.apiguru.app / endpoint
GET https://agent.apiguru.app/agent/v1/v2/product-reviews
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- 2 probes got a response that was not a 402 payment challenge.
- Category
- Web scrape by llm, confidence 55%
- Latest quote
- $0.003 on Base to 0x766B…1422
- 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
- 4h ago
- Next probe
- 2026-11-18 18:59 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.003 | 0x766B…1422 | default | yes | 6h ago |
| cdp | exact | Polygon | 0x3c49…3359 | 3000 | 0x766B…1422 | default | yes | 6h ago |
| cdp | exact | Arbitrum | 0xaf88…5831 | 3000 | 0x766B…1422 | default | yes | 6h ago |
| cdp | exact | Avalanche | 0xB97E…8a6E | 3000 | 0x766B…1422 | default | yes | 6h ago |
| payai | exact | Base | 0x8335…2913 | $0.003 | 0x766B…1422 | default | yes | 5h 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.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 27h ago | Web scrape | 55% | llm | v1 | claude-haiku-5-5: Returns Amazon product review content (ratings, review text, AI summary) for an ASIN, which is page-content retrieval of an e-commerce product rather than a clear fit for a named category. Closest matches are web_scrape (returns page content) or public_data; the commerce-product nature leans toward web_scrape, with moderate confidence. |
| 43h ago | Inference | 60% | rules | v1 | rule inference matched "sentiment analysis" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 4h ago | free | 402 | 550 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 10h ago | free | 402 | 532 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 17h ago | free | 402 | 520 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 23h ago | free | 402 | 568 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 29h ago | free | 402 | 553 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 36h ago | free | 402 | 589 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 42h ago | free | 200 | 534 ms | — | no | — | — | no_payment_requiredstatus_not_402 |
| 2d ago | free | 402 | 180 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 2d ago | free | 402 | 605 ms | v2 | yes | $0.003 | 0x766B…1422 | — |
| 3d ago | free | 200 | 604 ms | — | no | — | — | no_payment_requiredstatus_not_402 |