gpt56sol · Model identity and integrity report
Last updated：Sep 13, 2026, 5:26 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)
5000 runs · 1229 hosts · 4483 anomalies
Family-fingerprint consistency
openai 4539 ███████████████████████░░ 91% (expected) unknown 365 ██░░░░░░░░░░░░░░░░░░░░░░░ 7% (suspicious) anthropic 88 █░░░░░░░░░░░░░░░░░░░░░░░░ 2% (suspicious) google 3 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) deepseek 2 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) xai 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) zhipu 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) qwen 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ abstain 4463 (89%) — low confidence → unknown 535 (11%) ⚠ mismatch → openai/gpt-4o 1 ( 0%) ⚠ mismatch sim=0.64 → openai/gpt-5 1 ( 0%) ⚠ mismatch sim=0.83
Capability score distribution (auxiliary)
0-49 ███████████████████░░░░░░ 3765 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 130 70-89 █████░░░░░░░░░░░░░░░░░░░░ 1038 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 67
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.a6api.com/v1 | 509 | 19 | 90% | — |
| https://ai.boke.page/v1 | 182 | 54 | 90% | — |
| http://187.53.135.158:7101/v1 | 153 | 0 | 86% | — |
| https://www.airelay.pro/v1 | 86 | 0 | 95% | — |
| https://api.datacodex.net/v1 | 60 | 0 | 97% | — |
| https://api.ruikon.com/v1 | 60 | 0 | 77% | — |
| https://wawapii.com/v1 | 59 | 27 | 88% | — |
| https://api.790053500.com/v1 | 47 | 0 | 96% | — |
| https://api-cn.sanbailab.com/v1 | 44 | 0 | 98% | — |
| https://redirect.airelay.pro/v1 | 41 | 0 | 98% | — |
| https://www.piteai.com/v1 | 37 | 15 | 100% | — |
| https://api.gogoapi.cc/v1 | 34 | 7 | 100% | — |
| https://api.sanbailab.com/v1 | 32 | 0 | 100% | — |
| https://shu26.cfd/v1 | 31 | 0 | 100% | — |
| https://motomoto.lol/v1 | 31 | 41 | 87% | — |
| https://api.585dg.com/v1 | 31 | 0 | 97% | — |
| https://987xyz.com/v1 | 29 | 2 | 93% | — |
| http://40.160.13.47:8888/v1 | 28 | 0 | 100% | — |
| https://www.cctq.ai/v1 | 28 | 36 | 96% | — |
| https://a6api.com/v1 | 27 | 30 | 100% | — |
| https://fastvibe.dev/v1 | 27 | 9 | 81% | — |
| https://api.zeekai.cc/v1 | 27 | 9 | 93% | — |
| https://gateai.cc/v1 | 26 | 9 | 85% | — |
| https://vulcanapi.com/v1 | 25 | 17 | 96% | — |
| https://api.shenwenai.com/v1 | 25 | 31 | 92% | — |
Recent anomalies
https://x.ailzd.com/v1Sep 13, 2026, 5:09 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://yorhamc.com/v1Sep 13, 2026, 5:09 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ifapi.org/v1Sep 13, 2026, 5:09 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://codexapis.com/v1Sep 13, 2026, 5:03 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ginit.christmas/v1Sep 13, 2026, 5:03 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
http://40.160.13.47:8888/v1Sep 13, 2026, 5:01 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.datacodex.net/v1Sep 13, 2026, 5:00 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://redirect.airelay.pro/v1Sep 13, 2026, 4:58 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api-cn.sanbailab.com/v1Sep 13, 2026, 4:55 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ruikon.com/v1Sep 13, 2026, 4:54 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://direct-api.sanbailab.com/v1Sep 13, 2026, 4:53 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://redirect.airelay.pro/v1Sep 13, 2026, 4:51 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.chiyi.cc/v1Sep 13, 2026, 4:51 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Sep 13, 2026, 4:47 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Sep 13, 2026, 4:47 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gptg.cc/v1Sep 13, 2026, 4:46 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Sep 13, 2026, 4:46 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Sep 13, 2026, 4:44 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://wawapii.com/v1Sep 13, 2026, 4:44 PM
- Self-claimed model
- gpt-5.6-sol
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.datacodex.net/v1Sep 13, 2026, 4:43 PM
- 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 gpt56sol. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.