Leaderboard / cyre.dev / endpoint
GET https://cyre.dev/api/mintalike
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 11 probes in the last 7 days.
- Category
- Crypto market data by llm, confidence 60%
- Latest quote
- $0.002 on Base to 0x9Ff2…a712
- 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 00:58 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Solana | EPjFWd…Dt1v | 2000 | 9iubAp…fCVS | default | yes | 5h ago |
| cdp | exact | Base | 0x8335…2913 | $0.002 | 0x9Ff2…a712 | 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 |
|---|---|---|---|---|---|
| 45h ago | Crypto market data | 60% | llm | v1 | claude-haiku-5-5: The endpoint checks whether a token mint address or ticker resembles known tokens before a swap, which is token safety screening on crypto assets. That fits crypto_market, which includes token safety, though the lookalike-detection purpose is somewhat specific and the listing is not fully explicit about the return format. |
| 2d ago | Crypto price | 50% | rules | v1 | rule crypto_price matched "in:symbol" in metadata |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 3h ago | free | 402 | 184 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 10h ago | free | 402 | 111 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 17h ago | free | 402 | 166 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 23h ago | free | 402 | 89 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 29h ago | free | 402 | 105 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 36h ago | free | 402 | 146 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 42h ago | free | 402 | 106 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 2d ago | free | 402 | 139 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 2d ago | free | 402 | 252 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 3d ago | free | 402 | 110 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |
| 3d ago | free | 402 | 108 ms | v2 | yes | $0.002 | 0x9Ff2…a712 | — |