openrouter/auto · Model identity and integrity report
Last updated：Jul 30, 2026, 12:14 PM · Data window: past 90 days
Measured results (90 days)
3 runs · 3 hosts · 3 anomalies
Family-fingerprint consistency
openai 2 █████████████████░░░░░░░░ 67% (suspicious) qwen 1 ████████░░░░░░░░░░░░░░░░░ 33% (suspicious)
Observed V3 sub-model mapping
→ abstain 2 (67%) — low confidence → qwen/qwen3-next-80b-a3b-instruct 1 (33%) ⚠ mismatch sim=0.61
Capability score distribution (auxiliary)
0-49 █████████████████░░░░░░░░ 2 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 ████████░░░░░░░░░░░░░░░░░ 1 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.hcnsec.cn/v1 | 1 | 0 | 0% | — |
| https://luna-ai.shop/v1 | 1 | 78 | 0% | qwen/qwen3-next-80b-a3b-instruct (1) |
| https://api.iamhc.cn/v1 | 1 | 0 | 0% | — |
Recent anomalies
https://api.hcnsec.cn/v1Jul 23, 2026, 9:57 PM
- Self-claimed model
- auto
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://luna-ai.shop/v1Jul 11, 2026, 2:59 AM
- Self-claimed model
- auto
- V2 predicted family
- qwen
- V3 best match
- qwen/qwen3-next-80b-a3b-instruct (sim 0.61)
- Verdict
- Full swap
https://api.iamhc.cn/v1Jun 14, 2026, 6:37 PM
- Self-claimed model
- auto
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming openrouter/auto. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.