gemini31pro · Model identity and integrity report
Last updated：Sep 13, 2026, 5:26 PM · Data window: past 90 days
Measured results (90 days)
21 runs · 19 hosts · 19 anomalies
Family-fingerprint consistency
google 16 ███████████████████░░░░░░ 76% (suspicious) anthropic 3 ████░░░░░░░░░░░░░░░░░░░░░ 14% (suspicious) unknown 2 ███░░░░░░░░░░░░░░░░░░░░░░ 10% (suspicious)
Observed V3 sub-model mapping
→ abstain 7 (33%) — low confidence → google/gemini-3.1-pro-preview 6 (29%) ⚠ mismatch sim=0.79 → unknown 4 (19%) ⚠ mismatch → google/gemini-3.1-flash-lite-preview 3 (14%) ⚠ mismatch sim=0.88 → google/gemini-3.6-flash 1 ( 5%) ⚠ mismatch sim=0.79
Capability score distribution (auxiliary)
0-49 ████████████████░░░░░░░░░ 13 50-69 █████░░░░░░░░░░░░░░░░░░░░ 4 70-89 █████░░░░░░░░░░░░░░░░░░░░ 4 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://www.xinxiwang.org/v1 | 2 | 28 | 0% | — |
| https://nexaxis.ai/v1 | 2 | 38 | 0% | google/gemini-3.1-pro-preview (1) |
| https://gatecheap.vn/v1 | 1 | 0 | 0% | google/gemini-3.1-flash-lite-preview (1) |
| https://codecraftapi.com/v1 | 1 | 0 | 0% | — |
| https://www.20170428.cloud/v1 | 1 | 82 | 0% | — |
| https://llm-coding.space/v1 | 1 | 80 | 0% | — |
| https://ai.kscsnkli.site/v1 | 1 | 21 | 0% | — |
| https://api2.68886868.xyz/v1 | 1 | 0 | 0% | google/gemini-3.1-pro-preview (1) |
| https://www.ggwk1.online/v1 | 1 | 0 | 0% | google/gemini-3.1-flash-lite-preview (1) |
| https://api.relaycore.cn/v1 | 1 | 0 | 0% | google/gemini-3.6-flash (1) |
| https://tian-shu.org/v1 | 1 | 0 | 0% | — |
| https://api.1314mc.net/v1 | 1 | 0 | 0% | google/gemini-3.1-pro-preview (1) |
| https://speed.toter.me/v1 | 1 | 63 | 0% | — |
| https://www.huanapi.com/v1 | 1 | 0 | 0% | google/gemini-3.1-pro-preview (1) |
| https://api.42w.shop/v1 | 1 | 66 | 0% | — |
| https://api.rua.chat/v1 | 1 | 0 | 0% | google/gemini-3.1-pro-preview (1) |
| https://api.supxh.xin/v1 | 1 | 0 | 0% | — |
| https://openai.chatnewai.com/v1 | 1 | 73 | 0% | google/gemini-3.1-flash-lite-preview (1) |
| https://azemm.cc/v1 | 1 | 67 | 0% | google/gemini-3.1-pro-preview (1) |
Recent anomalies
https://gatecheap.vn/v1Sep 13, 2026, 10:56 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-flash-lite-preview (sim 0.76)
- Verdict
- Full swap
https://www.20170428.cloud/v1Aug 22, 2026, 8:20 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://llm-coding.space/v1Aug 22, 2026, 8:06 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- Family mismatch
https://www.xinxiwang.org/v1Aug 16, 2026, 6:22 AM
- Self-claimed model
- [企业]gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- Full swap
https://www.xinxiwang.org/v1Aug 16, 2026, 6:10 AM
- Self-claimed model
- [企业]gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- Family mismatch
https://api2.68886868.xyz/v1Aug 8, 2026, 11:42 AM
- Self-claimed model
- [不稳定渠道] gemini-3.1-pro
- V2 predicted family
- anthropic
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.80)
- Verdict
- Full swap
https://www.ggwk1.online/v1Aug 7, 2026, 6:02 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-flash-lite-preview (sim 0.93)
- Verdict
- Full swap
https://api.relaycore.cn/v1Aug 2, 2026, 11:43 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.6-flash (sim 0.79)
- Verdict
- Full swap
https://tian-shu.org/v1Aug 2, 2026, 5:43 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.1314mc.net/v1Aug 2, 2026, 5:23 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.80)
- Verdict
- Full swap
https://nexaxis.ai/v1Aug 2, 2026, 1:07 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed.toter.me/v1Jul 19, 2026, 10:04 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- Family mismatch
https://nexaxis.ai/v1Jul 3, 2026, 6:29 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.80)
- Verdict
- Full swap
https://www.huanapi.com/v1Jul 3, 2026, 7:24 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.80)
- Verdict
- Full swap
https://api.42w.shop/v1Jul 1, 2026, 1:11 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- Family mismatch
https://api.rua.chat/v1Jun 27, 2026, 12:52 PM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.80)
- Verdict
- Full swap
https://api.supxh.xin/v1Jun 20, 2026, 6:28 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- —
- Verdict
- Family mismatch
https://openai.chatnewai.com/v1Jun 19, 2026, 9:56 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-flash-lite-preview (sim 0.95)
- Verdict
- Full swap
https://azemm.cc/v1Jun 18, 2026, 5:40 AM
- Self-claimed model
- gemini-3.1-pro
- V2 predicted family
- V3 best match
- google/gemini-3.1-pro-preview (sim 0.76)
- Verdict
- Full swap
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming gemini31pro. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.