gpt56luna · Model identity and integrity report
Last updated：Sep 13, 2026, 7:42 PM · Data window: past 90 days
Verification capability — fingerprint reference available
- Family
- openai
- V3 sub-model reference
- Available ✓
- Checks
- 知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數
- Family-fingerprint coverage
- 52 weighted rules · 8 feature categories
Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.
Measured results (90 days)
1335 runs · 605 hosts · 1111 anomalies
Family-fingerprint consistency
openai 1125 █████████████████████░░░░ 84% (expected) unknown 173 ███░░░░░░░░░░░░░░░░░░░░░░ 13% (suspicious) anthropic 32 █░░░░░░░░░░░░░░░░░░░░░░░░ 2% (suspicious) deepseek 4 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) zhipu 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ abstain 1103 (83%) — low confidence → unknown 227 (17%) ⚠ mismatch → openai/gpt-5.2 4 ( 0%) ⚠ mismatch sim=0.87 → openai/gpt-5 1 ( 0%) ⚠ mismatch sim=0.79
Capability score distribution (auxiliary)
0-49 ███████████████░░░░░░░░░░ 794 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 24 70-89 ████████░░░░░░░░░░░░░░░░░ 418 90-100 ██░░░░░░░░░░░░░░░░░░░░░░░ 99
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.a6api.com/v1 | 91 | 31 | 92% | — |
| https://wawapii.com/v1 | 26 | 43 | 81% | — |
| https://aihub.top/v1 | 20 | 54 | 100% | — |
| https://a6api.com/v1 | 19 | 43 | 84% | — |
| https://ai.furry.vg/v1 | 19 | 58 | 84% | — |
| http://187.53.135.158:7101/v1 | 17 | 0 | 76% | — |
| https://vyceai.com/v1 | 14 | 35 | 64% | — |
| https://www.juapi.net/v1 | 13 | 18 | 77% | — |
| https://sharellm.cn/v1 | 13 | 27 | 46% | — |
| https://aihub.dog/v1 | 11 | 0 | 100% | — |
| https://www.cctq.ai/v1 | 10 | 34 | 90% | — |
| https://www.daseinai.xyz/v1 | 10 | 34 | 100% | — |
| https://ai.kaiplay.my.id/v1 | 10 | 70 | 50% | — |
| https://blankapi.com/v1 | 10 | 78 | 100% | — |
| https://api.gjx88.com/v1 | 10 | 71 | 90% | — |
| https://api.apinex.bond/v1 | 9 | 0 | 33% | — |
| https://api.athn.cc/v1 | 9 | 47 | 100% | — |
| https://www.hejuapi.com/v1 | 8 | 41 | 88% | — |
| https://ai.input.im/v1 | 8 | 41 | 50% | — |
| https://api.247kan.com/v1 | 8 | 39 | 100% | — |
| https://aishenji.top/v1 | 7 | 24 | 71% | — |
| https://api.inferhub.dev/v1 | 7 | 51 | 100% | — |
| https://cn.codeapi.icu/v1 | 7 | 62 | 100% | — |
| https://api.ccode.vip/v1 | 7 | 22 | 14% | — |
| https://code28.ccwu.cc/v1 | 7 | 24 | 100% | — |
Recent anomalies
https://api.wikivibe.ru/v1Sep 13, 2026, 7:26 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.chunxiao.pro/v1Sep 13, 2026, 4:32 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://code.conpera.ai/v1Sep 13, 2026, 3:51 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub.wanzhao.top/v1Sep 13, 2026, 2:23 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vulcanapi.com/v1Sep 13, 2026, 2:20 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Sep 13, 2026, 1:48 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gpt.api456.me/v1Sep 13, 2026, 11:42 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://artio.top/v1Sep 13, 2026, 9:30 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.binzzz.xyz/v1Sep 13, 2026, 9:30 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://token.kechuai.com/v1Sep 13, 2026, 8:59 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gatecheap.vn/v1Sep 13, 2026, 6:58 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://artio.top/v1Sep 13, 2026, 4:30 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://wawapii.com/v1Sep 13, 2026, 2:28 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.seldon-ai.com/v1Sep 12, 2026, 11:41 PM
- Self-claimed model
- openai/gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.string.ink/v1Sep 12, 2026, 4:56 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.the5288.com/v1Sep 12, 2026, 3:18 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub2api.aimeta.store/v1Sep 12, 2026, 1:56 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.getunikey.ai/v1Sep 12, 2026, 1:51 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://miaoai.live/v1Sep 12, 2026, 1:34 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.hyperouters.com/apiSep 12, 2026, 1:08 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming gpt56luna. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.