moonshotai/kimi-k2.6 · Model identity and integrity report
Last updated：Jul 30, 2026, 12:07 PM · Data window: past 90 days
Measured results (90 days)
13 runs · 9 hosts · 13 anomalies
Family-fingerprint consistency
anthropic 11 █████████████████████░░░░ 85% (suspicious) openai 2 ████░░░░░░░░░░░░░░░░░░░░░ 15% (suspicious)
Observed V3 sub-model mapping
→ abstain 8 (62%) — low confidence → unknown 3 (23%) ⚠ mismatch → anthropic/claude-fable-5 1 ( 8%) ⚠ mismatch sim=1.00 → anthropic/claude-opus-4.7 1 ( 8%) ⚠ mismatch sim=0.95
Capability score distribution (auxiliary)
0-49 █████████████████░░░░░░░░ 9 50-69 ██████░░░░░░░░░░░░░░░░░░░ 3 70-89 ██░░░░░░░░░░░░░░░░░░░░░░░ 1 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://cheapyun.cc.cd/v1 | 2 | 0 | 0% | — |
| https://ai2.18.show/v1 | 2 | 35 | 0% | anthropic/claude-fable-5 (1) |
| https://freeapi.514179.xyz/v1 | 2 | 34 | 0% | — |
| https://api.iamhc.cn/v1 | 2 | 0 | 0% | — |
| https://my.ai.3fl.top/v1 | 1 | 0 | 0% | — |
| https://omaleai.qzz.io/v1 | 1 | 0 | 0% | — |
| https://glm-relayapi.top/v1 | 1 | 68 | 0% | — |
| https://api.moonshot.cn/v1 | 1 | 54 | 0% | — |
| https://api.aikeybest.cn/v1 | 1 | 0 | 0% | anthropic/claude-opus-4.7 (1) |
Recent anomalies
https://my.ai.3fl.top/v1Jul 23, 2026, 5:04 PM
- Self-claimed model
- kimi-k2.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://cheapyun.cc.cd/v1Jul 7, 2026, 10:01 AM
- Self-claimed model
- moonshotai/kimi-k2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://cheapyun.cc.cd/v1Jul 7, 2026, 9:12 AM
- Self-claimed model
- Kimi-K2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://omaleai.qzz.io/v1Jul 6, 2026, 10:30 AM
- Self-claimed model
- kimi-k2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://glm-relayapi.top/v1Jul 5, 2026, 8:39 AM
- Self-claimed model
- kimi-k2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai2.18.show/v1Jul 3, 2026, 7:12 AM
- Self-claimed model
- Kimi-K2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ai2.18.show/v1Jul 3, 2026, 7:08 AM
- Self-claimed model
- kimi-K2.6
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-fable-5 (sim 1.00)
- Verdict
- Full swap
https://freeapi.514179.xyz/v1Jun 26, 2026, 7:36 AM
- Self-claimed model
- Kimi-k2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://freeapi.514179.xyz/v1Jun 26, 2026, 6:52 AM
- Self-claimed model
- Kimi-k2.6
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.iamhc.cn/v1Jun 25, 2026, 3:49 AM
- Self-claimed model
- Kimi-K2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://api.moonshot.cn/v1Jun 21, 2026, 3:26 PM
- Self-claimed model
- kimi-k2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://api.iamhc.cn/v1Jun 13, 2026, 2:18 PM
- Self-claimed model
- Kimi-K2.6
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- Family mismatch
https://api.aikeybest.cn/v1May 25, 2026, 4:55 PM
- Self-claimed model
- kimi-k2.6
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.7 (sim 0.95)
- 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 moonshotai/kimi-k2.6. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.