openai/gpt-5.6-sol · Model identity and integrity report
Last updated：Jul 30, 2026, 12:55 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)
2244 runs · 817 hosts · 2039 anomalies
Family-fingerprint consistency
openai 2087 ███████████████████████░░ 93% (expected) unknown 139 ██░░░░░░░░░░░░░░░░░░░░░░░ 6% (suspicious) anthropic 16 ░░░░░░░░░░░░░░░░░░░░░░░░░ 1% (suspicious) xai 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) google 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ abstain 2020 (90%) — low confidence → unknown 207 ( 9%) ⚠ mismatch → openai/gpt-5.4 11 ( 0%) ⚠ mismatch sim=0.96 → openai/gpt-5.6-sol 4 ( 0%) ✓ correct sim=0.93 → anthropic/claude-fable-5 1 ( 0%) ⚠ mismatch sim=0.90 → anthropic/claude-opus-4.7 1 ( 0%) ⚠ mismatch sim=0.70
Capability score distribution (auxiliary)
0-49 █████████████░░░░░░░░░░░░ 1199 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 34 70-89 ███████░░░░░░░░░░░░░░░░░░ 627 90-100 ████░░░░░░░░░░░░░░░░░░░░░ 384
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://aihub.top/v1 | 105 | 29 | 92% | — |
| https://api.a6api.com/v1 | 62 | 21 | 97% | — |
| https://ai.input.im/v1 | 55 | 3 | 98% | — |
| https://www.fastaitoken.com/v1 | 27 | 41 | 96% | — |
| https://a6api.com/v1 | 27 | 57 | 85% | — |
| https://api.shuaiapi.com/v1 | 26 | 33 | 96% | — |
| https://downstream.jbbtoken.cn/v1 | 25 | 57 | 96% | — |
| https://api.tokenskingdom.com/v1 | 24 | 61 | 92% | — |
| https://lingsuan.top/v1 | 23 | 54 | 100% | — |
| https://aierxin.cc/v1 | 22 | 45 | 100% | — |
| https://mdkj.lol/v1 | 21 | 49 | 95% | anthropic/claude-fable-5 (1) |
| https://api.aijws.com/v1 | 21 | 43 | 95% | — |
| https://jojocode.com/v1 | 20 | 30 | 95% | openai/gpt-5.6-sol (1) |
| https://ooioo.work/v1 | 18 | 36 | 100% | openai/gpt-5.6-sol (1) |
| https://lucen.cc/v1 | 16 | 32 | 100% | openai/gpt-5.6-sol (1) |
| https://hubway.cc/v1 | 16 | 36 | 100% | openai/gpt-5.4 (1) |
| https://aishenji.top/v1 | 15 | 54 | 87% | — |
| https://kuaipao.ai/v1 | 13 | 23 | 100% | — |
| https://www.fcai.it.com/v1 | 13 | 13 | 100% | — |
| https://api.zoowyoo.dpdns.org/v1 | 12 | 30 | 100% | — |
| https://huoshenai.com/v1 | 12 | 37 | 100% | — |
| https://xixiapi.cc/v1 | 12 | 22 | 100% | — |
| https://sub.sailapi.top/v1 | 12 | 0 | 92% | — |
| https://3seeker.site/v1 | 12 | 60 | 75% | — |
| https://api.xwsz.top/v1 | 11 | 52 | 91% | — |
Recent anomalies
https://api.api2cn.com/v1Jul 30, 2026, 12:52 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.senzo.online/v1Jul 30, 2026, 12:44 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vlabsx.cc/v1Jul 30, 2026, 12:18 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.pqapi.space/v1Jul 30, 2026, 11:56 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://xiaoqie.xyz/v1Jul 30, 2026, 11:42 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://luotuokj.top/v1Jul 30, 2026, 11:17 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://aihub.top/v1Jul 30, 2026, 11:16 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
http://cn-hk-bgp-4.ofalias.net:30722/v1Jul 30, 2026, 11:07 AM
- Self-claimed model
- gpt-5-6-sol
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Full swap
https://aiapi.market/v1Jul 30, 2026, 10:09 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai.luminai.cc/v1Jul 30, 2026, 10:08 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://aiapi.market/v1Jul 30, 2026, 10:06 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Jul 30, 2026, 10:03 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.kunkunout.com/v1Jul 30, 2026, 9:53 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Jul 30, 2026, 9:52 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Jul 30, 2026, 9:47 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://infinitex.pro/v1Jul 30, 2026, 9:43 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.entropicecho.com/v1Jul 30, 2026, 9:42 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://3aa.ai/v1Jul 30, 2026, 9:39 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://apxrelay.com/v1Jul 30, 2026, 9:37 AM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.jiji.cc/v1Jul 30, 2026, 9:35 AM
- Self-claimed model
- gpt-5.6-sol
- 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-sol. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.