kimik27code · Model identity and integrity report

Name: kimik27code relay integrity probe aggregate
Creator: BazaarLink

Last updated：Aug 10, 2026, 11:26 AM · Data window: past 90 days

Measured results (90 days)

5 runs · 5 hosts · 5 anomalies

Family-fingerprint consistency

  anthropic        4  ████████████████████░░░░░   80% (suspicious)
  openai           1  █████░░░░░░░░░░░░░░░░░░░░   20% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  2 (40%) — low confidence
  → anthropic/claude-sonnet-5                1 (20%) ⚠ mismatch sim=0.70
  → unknown                                  1 (20%) ⚠ mismatch
  → anthropic/claude-opus-4.7                1 (20%) ⚠ mismatch sim=0.72

Capability score distribution (auxiliary)

  0-49     ██████████░░░░░░░░░░░░░░░    2
  50-69    █████░░░░░░░░░░░░░░░░░░░░    1
  70-89    ██████████░░░░░░░░░░░░░░░    2
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
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)
https://freeapi.514179.xyz/v1	1	66	0%	—
https://0api.qzz.io/v1	1	0	0%	anthropic/claude-opus-4.7 (1)

Recent anomalies

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

https://freeapi.514179.xyz/v1Jun 26, 2026, 6:56 AM

Self-claimed model: Kimi-k2.7-code
V2 predicted family: anthropic
V3 best match: —
Verdict: Family mismatch

https://0api.qzz.io/v1Jun 20, 2026, 2:00 AM

Self-claimed model: kimi-k2.7-code
V2 predicted family: anthropic
V3 best match: anthropic/claude-opus-4.7 (sim 0.72)
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.

Test an endpoint yourself →