kimik27code · Model identity and integrity report
Last updated：Sep 26, 2026, 11:36 AM · Data window: past 90 days
Measured results (90 days)
16 runs · 14 hosts · 13 anomalies
Family-fingerprint consistency
anthropic 9 ██████████████░░░░░░░░░░░ 56% (suspicious) openai 3 █████░░░░░░░░░░░░░░░░░░░░ 19% (suspicious) unknown 3 █████░░░░░░░░░░░░░░░░░░░░ 19% (suspicious) zhipu 1 ██░░░░░░░░░░░░░░░░░░░░░░░ 6% (suspicious)
Observed V3 sub-model mapping
→ abstain 11 (69%) — low confidence → unknown 3 (19%) ⚠ mismatch → anthropic/claude-opus-4.6 1 ( 6%) ⚠ mismatch sim=0.73 → anthropic/claude-sonnet-5 1 ( 6%) ⚠ mismatch sim=0.70
Capability score distribution (auxiliary)
0-49 ███████████████████░░░░░░ 12 50-69 ██░░░░░░░░░░░░░░░░░░░░░░░ 1 70-89 █████░░░░░░░░░░░░░░░░░░░░ 3 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://llm.goaichat.top/v1 | 2 | 40 | 0% | — |
| https://router.lobakmerah.my.id/v1 | 2 | 11 | 0% | — |
| https://tokenhub.mandao.com/v1 | 1 | 0 | 0% | — |
| https://bandelbanget.xyz/v1 | 1 | 0 | 0% | — |
| https://api.lmuai.com/v1 | 1 | 0 | 0% | — |
| https://api.inferhub.dev/v1 | 1 | 0 | 0% | anthropic/claude-opus-4.6 (1) |
| https://api.a6api.com/v1 | 1 | 0 | 0% | — |
| https://sharellm.cn/v1 | 1 | 41 | 0% | — |
| https://api.airforce/v1 | 1 | 0 | 0% | — |
| https://na.o0kam1.dev/v1 | 1 | 68 | 0% | — |
| https://ai-gateway-production-df56.up.railway.app/v1 | 1 | 8 | 0% | — |
| https://api.moonshot.cn/v1 | 1 | 0 | 0% | — |
| https://api.cosmoshub.tech/v1 | 1 | 77 | 0% | — |
| https://api.hcnsec.cn/v1 | 1 | 70 | 0% | anthropic/claude-sonnet-5 (1) |
Recent anomalies
https://tokenhub.mandao.com/v1Sep 18, 2026, 9:33 AM
- Self-claimed model
- Kimi/Kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://bandelbanget.xyz/v1Sep 9, 2026, 12:15 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.lmuai.com/v1Sep 9, 2026, 9:05 AM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.inferhub.dev/v1Sep 6, 2026, 7:07 PM
- Self-claimed model
- ali/kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.6 (sim 0.73)
- Verdict
- Full swap
https://llm.goaichat.top/v1Sep 6, 2026, 3:41 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.a6api.com/v1Sep 6, 2026, 1:50 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sharellm.cn/v1Sep 5, 2026, 6:24 AM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.airforce/v1Aug 27, 2026, 5:31 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- zhipu
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://na.o0kam1.dev/v1Aug 23, 2026, 5:38 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://llm.goaichat.top/v1Aug 22, 2026, 3:24 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.moonshot.cn/v1Aug 10, 2026, 9:28 AM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.cosmoshub.tech/v1Aug 3, 2026, 3:09 AM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.hcnsec.cn/v1Jul 15, 2026, 5:11 PM
- Self-claimed model
- kimi-k2.7-code
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-5 (sim 0.70)
- 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 kimik27code. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.