Leaderboard / intel.degenscan.io / endpoint
GET https://intel.degenscan.io/v1/ai/cheapest
Scores measure reliability and honesty, not output quality.
- Listed only 3 days ago; new listings earn trust over 30 days.
- Answered all 12 probes in the last 7 days.
- Category
- Inference by llm, confidence 60%
- Latest quote
- $0.001 on Base to 0x21f4…1a94
- 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
- 2026-11-19 07:54 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.001 | 0x21f4…1a94 | default | yes | 6h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 1000 | GptpyP…Rhez | default | yes | 6h 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 |
|---|---|---|---|---|---|
| 46h ago | Inference | 60% | llm | v1 | claude-haiku-5-5: The endpoint recommends the cheapest LLM matching capability filters and ranks models by per-token price, so it returns model-selection output about LLMs rather than market data. The tags and 'market data' wording point toward finance, but the substance is LLM model metadata, which fits inference best. |
| 2d ago | Inference | 60% | rules | v1 | rule inference matched "llm" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 4h ago | free | 402 | 98 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 10h ago | free | 402 | 77 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 18h ago | free | 402 | 90 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 24h ago | free | 402 | 96 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 30h ago | free | 402 | 93 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 37h ago | free | 402 | 109 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 43h ago | free | 402 | 84 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 2d ago | free | 402 | 277 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 2d ago | free | 402 | 231 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 3d ago | free | 402 | 104 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 3d ago | free | 402 | 91 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |
| 3d ago | free | 402 | 76 ms | v2 | yes | $0.001 | 0x21f4…1a94 | — |