BazaarLinkBazaarLink
Sign in
← Back to model

minimax/minimax-m3 · Model identity and integrity report

Last updatedJul 30, 2026, 11:23 AM · Data window: past 90 days

Measured results (90 days)

10 runs · 8 hosts · 10 anomalies

Family-fingerprint consistency

  anthropic       10  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  8 (80%) — low confidence
  → anthropic/claude-opus-4.7                1 (10%) ⚠ mismatch sim=0.67
  → unknown                                  1 (10%) ⚠ mismatch

Capability score distribution (auxiliary)

  0-49     ██████████████████░░░░░░░    7
  50-69    █████░░░░░░░░░░░░░░░░░░░░    2
  70-89    ███░░░░░░░░░░░░░░░░░░░░░░    1
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

HostRunsAverage scoreFamily matchMost common V3 match
https://api.183399.xyz/v13410%
https://windhub.cc/v11740%
https://www.nengpa.com/v1100%anthropic/claude-opus-4.7 (1)
https://api.tokenrouter.com/v1100%
https://api.minimax.chat/v11360%
https://www.tokenfreeperday.com/v1100%
https://ai.kot.gg/v11370%
https://aiproxy.xin/cosphere/v1100%

Recent anomalies

https://windhub.cc/v1Jul 30, 2026, 9:35 AM
Self-claimed model
minimax-m3
V2 predicted family
anthropic
V3 best match
Verdict
Family mismatch
https://api.183399.xyz/v1Jul 24, 2026, 4:50 PM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
V3 low confidence · Abstain
https://api.183399.xyz/v1Jul 18, 2026, 2:17 PM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
V3 low confidence · Abstain
https://api.183399.xyz/v1Jul 18, 2026, 4:47 AM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
V3 low confidence · Abstain
https://www.nengpa.com/v1Jul 12, 2026, 9:37 AM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
anthropic/claude-opus-4.7 (sim 0.67)
Verdict
Full swap
https://api.tokenrouter.com/v1Jul 6, 2026, 9:47 AM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
V3 low confidence · Abstain
https://api.minimax.chat/v1Jun 29, 2026, 9:30 PM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
V3 low confidence · Abstain
https://www.tokenfreeperday.com/v1Jun 27, 2026, 2:09 AM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
Family mismatch
https://ai.kot.gg/v1Jun 14, 2026, 7:03 PM
Self-claimed model
MiniMax-M3
V2 predicted family
anthropic
V3 best match
Verdict
V3 low confidence · Abstain
https://aiproxy.xin/cosphere/v1Jun 4, 2026, 7:30 AM
Self-claimed model
minimax-m3
V2 predicted family
anthropic
V3 best match
Verdict
Family mismatch

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming minimax/minimax-m3. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.