← Back to model

gpt6luna · Model identity and integrity report

Last updated：Sep 26, 2026, 10:01 AM · 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)

1917 runs · 62 hosts · 1828 anomalies

Family-fingerprint consistency

  openai         1833  ████████████████████████░   96% (expected)
  unknown         80  █░░░░░░░░░░░░░░░░░░░░░░░░    4% (suspicious)
  anthropic        4  ░░░░░░░░░░░░░░░░░░░░░░░░░    0% (suspicious)

Observed V3 sub-model mapping

  → abstain                                1766 (92%) — low confidence
  → unknown                                 91 ( 5%) ⚠ mismatch
  → openai/gpt-5.6-luna                     29 ( 2%) ⚠ mismatch sim=0.99
  → openai/gpt-5.5                          17 ( 1%) ⚠ mismatch sim=0.83
  → openai/gpt-5.4                          13 ( 1%) ⚠ mismatch sim=0.87
  → anthropic/claude-opus-4.6                1 ( 0%) ⚠ mismatch sim=0.83

Capability score distribution (auxiliary)

  0-49     █████████████████████████  1917
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Family match	Most common V3 match
https://aiapi.asia/v1	1427	97%	openai/gpt-5.6-luna (1)
https://nb.tw.cn/v1	197	91%	openai/gpt-5.5 (14)
https://api.a6api.com	113	96%	openai/gpt-5.6-luna (25)
https://api.a6api.com/v1	39	92%	openai/gpt-5.6-luna (1)
https://ccapi.ztxfkw.top/v1	31	100%	—
https://openrouter.ai/api/v1	21	100%	—
https://api.inferhub.dev/v1	6	100%	—
https://api.teamorouter.com/v1	6	33%	—
https://n-cf.tokeness.dev/v1	5	100%	—
https://api.experientiallabs.ai/v1	3	100%	—
https://ai.fujcloud.com/v1	3	100%	—
https://api.sta1n.site/v1	2	100%	openai/gpt-5.6-luna (1)
https://www.sharellm.net/v1	2	50%	openai/gpt-5.5 (1)
https://router.bynara.id/v1	2	100%	—
https://api.nbhooks.my.id/v1	2	0%	—
https://a6.a6api.com/v1	2	100%	—
https://api.chiyi.cc/v1	2	100%	—
https://api.wikivibe.ru/v1	2	100%	—
https://api.apinex.bond/v1	2	0%	—
https://api.gpt.ge/v1	2	100%	—
https://4router.net/v1	2	100%	—
https://wawapii.com/v1	2	100%	—
https://api.ikhdev.xyz/v1	2	0%	—
https://api.vleee.net/v1	2	50%	—
https://n.tokeness.dev/v1	2	100%	—

Recent anomalies

https://n-cf.tokeness.dev/v1Sep 26, 2026, 8:06 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://amosis.lol/v1Sep 26, 2026, 8:02 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.a6api.comSep 26, 2026, 7:41 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.a6api.comSep 26, 2026, 7:28 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 1.00)
Verdict: Sub-model downgrade

https://api.a6api.comSep 26, 2026, 7:21 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 1.00)
Verdict: Sub-model downgrade

https://api.a6api.comSep 26, 2026, 7:13 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://openagentic.id/api/v1Sep 26, 2026, 6:59 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.a6api.comSep 26, 2026, 6:56 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 0.85)
Verdict: Sub-model downgrade

https://api.a6api.com/v1Sep 26, 2026, 6:48 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 1.00)
Verdict: Sub-model downgrade

https://api.a6api.comSep 26, 2026, 6:47 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 1.00)
Verdict: Sub-model downgrade

https://api.a6api.comSep 26, 2026, 6:39 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.sta1n.site/v1Sep 26, 2026, 6:36 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.a6api.comSep 26, 2026, 6:32 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 1.00)
Verdict: Sub-model downgrade

https://api.a6api.comSep 26, 2026, 6:11 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.a6api.comSep 26, 2026, 5:07 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://www.poke2api.com/v1Sep 26, 2026, 4:44 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.sta1n.site/v1Sep 26, 2026, 4:33 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: openai/gpt-5.6-luna (sim 1.00)
Verdict: Sub-model downgrade

https://nb.tw.cn/v1Sep 26, 2026, 3:26 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://nb.tw.cn/v1Sep 26, 2026, 3:26 AM

Self-claimed model: gpt-6-luna
V2 predicted family: openai
V3 best match: —
Verdict: V3 low confidence · Abstain

https://nb.tw.cn/v1Sep 26, 2026, 3:26 AM

Self-claimed model: gpt-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 gpt6luna. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →