← Back to model

qwen38maxfree · Model identity and integrity report

Name: qwen38maxfree relay integrity probe aggregate
Creator: BazaarLink

Last updated：Aug 17, 2026, 5:49 PM · Data window: past 90 days

Measured results (90 days)

7 runs · 1 hosts · 7 anomalies

Family-fingerprint consistency

  qwen             7  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → qwen/qwen3-max                           4 (57%) ⚠ mismatch sim=0.65
  → abstain                                  3 (43%) — low confidence

Capability score distribution (auxiliary)

  0-49     ██████████████████████░░░    6
  50-69    ████░░░░░░░░░░░░░░░░░░░░░    1
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://api.tokenrouter.com/v1	7	8	0%	qwen/qwen3-max (4)

Recent anomalies

https://api.tokenrouter.com/v1Aug 17, 2026, 5:17 PM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: qwen/qwen3-max (sim 0.62)
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 17, 2026, 9:40 AM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: qwen/qwen3-max (sim 0.63)
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 17, 2026, 8:57 AM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: —
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 16, 2026, 9:07 PM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: qwen/qwen3-max (sim 0.68)
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 16, 2026, 4:10 PM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: qwen/qwen3-max (sim 0.65)
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 16, 2026, 12:52 PM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: —
Verdict: Full swap

https://api.tokenrouter.com/v1Aug 16, 2026, 12:36 PM

Self-claimed model: qwen/qwen3.8-max-free
V2 predicted family: qwen
V3 best match: —
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 qwen38maxfree. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →