openai/gpt-5.6-luna · Model identity and integrity report
Last updated：Jul 30, 2026, 12:12 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)
127 runs · 98 hosts · 113 anomalies
Family-fingerprint consistency
openai 114 ███████████████████████░░ 90% (expected) unknown 13 ███░░░░░░░░░░░░░░░░░░░░░░ 10% (suspicious)
Observed V3 sub-model mapping
→ abstain 113 (89%) — low confidence → unknown 14 (11%) ⚠ mismatch
Capability score distribution (auxiliary)
0-49 ███████████████░░░░░░░░░░ 74 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 ███████░░░░░░░░░░░░░░░░░░ 33 90-100 ████░░░░░░░░░░░░░░░░░░░░░ 20
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.gjx88.com/v1 | 6 | 59 | 83% | — |
| https://happyapi.org/v1 | 4 | 55 | 75% | — |
| https://kuaipao.pro/v1 | 4 | 20 | 100% | — |
| https://api.ikuncode.cc/v1 | 3 | 89 | 100% | — |
| https://max.jojocode.com/v1 | 3 | 89 | 100% | — |
| https://api.slomerex.xyz/v1 | 3 | 61 | 100% | — |
| https://api.a6api.com/v1 | 2 | 47 | 100% | — |
| https://blankapi.com/v1 | 2 | 43 | 100% | — |
| https://api.bblabu.cn/v1 | 2 | 0 | 100% | — |
| https://hezu.ink/v1 | 2 | 0 | 50% | — |
| https://api.hanhegufei.online/v1 | 2 | 0 | 100% | — |
| https://ai.iagent.dev/v1 | 2 | 0 | 100% | — |
| https://api.sailapi.top/v1 | 2 | 0 | 100% | — |
| https://xixiapi.cc/v1 | 2 | 46 | 100% | — |
| https://api.shuaiapi.com/v1 | 2 | 0 | 100% | — |
| https://torchai.ai/v1 | 2 | 0 | 100% | — |
| https://api.aisz.mom/v1 | 2 | 0 | 100% | — |
| https://kuaipao.ai/v1 | 2 | 42 | 50% | — |
| https://api.xairouter.com/v1 | 1 | 89 | 100% | — |
| https://sub2api.apiship.ai/v1 | 1 | 87 | 100% | — |
| https://seekai.cc/v1 | 1 | 0 | 100% | — |
| https://ooioo.work/v1 | 1 | 0 | 0% | — |
| https://xm.aceapi.cc/v1 | 1 | 86 | 100% | — |
| https://api.ziyouxie.online/v1 | 1 | 86 | 100% | — |
| https://api.quya.org/v1 | 1 | 95 | 100% | — |
Recent anomalies
https://api.xairouter.com/v1Jul 30, 2026, 5:56 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub2api.apiship.ai/v1Jul 30, 2026, 5:03 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://seekai.cc/v1Jul 29, 2026, 10:27 PM
- Self-claimed model
- gpt-5-6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://xm.aceapi.cc/v1Jul 29, 2026, 2:25 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ziyouxie.online/v1Jul 29, 2026, 2:22 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.quya.org/v1Jul 29, 2026, 1:59 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Jul 29, 2026, 12:37 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ikuncode.cc/v1Jul 29, 2026, 9:19 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.gjx88.com/v1Jul 28, 2026, 3:28 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.gjx88.com/v1Jul 28, 2026, 3:25 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.gjx88.com/v1Jul 28, 2026, 2:36 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.gjx88.com/v1Jul 28, 2026, 1:45 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.gjx88.com/v1Jul 28, 2026, 1:28 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.0029.org/v1Jul 28, 2026, 2:43 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ikuncode.cc/v1Jul 27, 2026, 6:05 PM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://blankapi.com/v1Jul 27, 2026, 11:23 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.vectorengine.cn/v1Jul 27, 2026, 8:57 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.i9starflow.com/v1Jul 27, 2026, 8:22 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai.pite.chat/v1Jul 27, 2026, 6:13 AM
- Self-claimed model
- gpt-5.6-luna
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://max.jojocode.com/v1Jul 27, 2026, 5:06 AM
- 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 openai/gpt-5.6-luna. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.