claudehaiku45thinking · Model identity and integrity report

Name: claudehaiku45thinking relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 9:37 AM · Data window: past 90 days

Measured results (90 days)

1 runs · 1 hosts · 1 anomalies

Family-fingerprint consistency

  anthropic        1  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → anthropic/claude-opus-4.6                1 (100%) ⚠ mismatch sim=0.67

Capability score distribution (auxiliary)

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

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://yourapi.cn/v1	1	74	0%	anthropic/claude-opus-4.6 (1)

Recent anomalies

https://yourapi.cn/v1Jul 2, 2026, 4:03 AM

Self-claimed model: claude-haiku-4-5-20251001-thinking
V2 predicted family: anthropic
V3 best match: anthropic/claude-opus-4.6 (sim 0.67)
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 claudehaiku45thinking. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →