openai/gpt-5.6-terra · 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)
375 runs · 238 hosts · 351 anomalies
Family-fingerprint consistency
openai 352 ████████████████████████░ 94% (expected) unknown 15 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious) anthropic 8 █░░░░░░░░░░░░░░░░░░░░░░░░ 2% (suspicious)
Observed V3 sub-model mapping
→ abstain 345 (92%) — low confidence → unknown 25 ( 7%) ⚠ mismatch → openai/gpt-5.4 4 ( 1%) ⚠ mismatch sim=1.00 → openai/gpt-5.6-sol 1 ( 0%) ⚠ mismatch sim=0.95
Capability score distribution (auxiliary)
0-49 █████████░░░░░░░░░░░░░░░░ 140 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 9 70-89 ███████░░░░░░░░░░░░░░░░░░ 104 90-100 ████████░░░░░░░░░░░░░░░░░ 122
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://vsllm.com/v1 | 7 | 62 | 86% | — |
| https://ooioo.work/v1 | 6 | 57 | 100% | — |
| https://wawapii.com/v1 | 6 | 54 | 83% | — |
| https://api.aijws.com/v1 | 6 | 89 | 67% | — |
| https://sub.vcnovb.cn/v1 | 6 | 77 | 83% | openai/gpt-5.6-sol (1) |
| https://aihub.top/v1 | 5 | 54 | 60% | — |
| https://api.a6api.com/v1 | 5 | 34 | 100% | — |
| https://ai2.hhhl.cc/v1 | 5 | 75 | 100% | — |
| https://apiclaude.cc/v1 | 4 | 91 | 100% | — |
| https://api.zeekai.cc/v1 | 4 | 92 | 100% | — |
| https://cpa.xiejiang.us.ci/v1 | 4 | 91 | 100% | — |
| https://codex.hiyo.top/v1 | 4 | 43 | 100% | — |
| https://chiyicn.com/v1 | 4 | 64 | 100% | openai/gpt-5.4 (1) |
| https://www.codexapis.com/v1 | 3 | 93 | 100% | — |
| https://www.micuapi.ai/v1 | 3 | 29 | 100% | — |
| https://api.0029.org/v1 | 3 | 91 | 100% | — |
| https://api.xiejiang.de5.net/v1 | 3 | 94 | 100% | — |
| https://otokapi.com/v1 | 3 | 93 | 100% | — |
| https://aixoras.com/v1 | 3 | 88 | 100% | — |
| https://aierxin.cc/v1 | 3 | 90 | 100% | — |
| https://qiutian.live/v1 | 3 | 55 | 100% | — |
| https://kuaipao.ai/v1 | 3 | 83 | 100% | — |
| https://new.984275579.xyz/v1 | 3 | 30 | 100% | — |
| https://ai.furry.vg/v1 | 3 | 71 | 100% | — |
| https://api.vectorengine.ai/v1 | 3 | 86 | 100% | — |
Recent anomalies
https://api.kunkunout.com/v1Jul 30, 2026, 10:04 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub2api.apiship.ai/v1Jul 30, 2026, 9:42 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.entropicecho.com/v1Jul 30, 2026, 9:29 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://apxrelay.com/v1Jul 30, 2026, 9:15 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://tokan.top/v1Jul 30, 2026, 8:48 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.univibe.cc/openai/v1Jul 30, 2026, 1:43 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub2api.lyclyc.xyz/v1Jul 30, 2026, 1:18 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ooioo.work/v1Jul 30, 2026, 12:06 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.bbe.to/v1Jul 29, 2026, 5:56 PM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://www.cyai.club/v1Jul 29, 2026, 2:45 PM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://deepkey.top/v1Jul 29, 2026, 2:29 PM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://beefapi.com/v1Jul 29, 2026, 2:27 PM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.pureai.quest/v1Jul 29, 2026, 12:59 PM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.autofish.club/v1Jul 29, 2026, 11:37 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.codexapis.com/v1Jul 29, 2026, 11:16 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://apiclaude.cc/v1Jul 29, 2026, 11:14 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ooioo.work/v1Jul 29, 2026, 3:28 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.aiyundu.top/v1Jul 29, 2026, 3:16 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://wawapii.com/v1Jul 29, 2026, 2:41 AM
- Self-claimed model
- gpt-5.6-terra
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gpt.gptzzz.xyz/v1Jul 29, 2026, 2:09 AM
- Self-claimed model
- gpt-5.6-terra
- 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-terra. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.