openai/gpt-5.4-pro · Model identity and integrity report

Name: openai/gpt-5.4-pro relay integrity probe aggregate
Creator: BazaarLink

Last updated：Jul 30, 2026, 11:19 AM · Data window: past 90 days

Measured results (90 days)

5 runs · 3 hosts · 5 anomalies

Family-fingerprint consistency

  openai           5  █████████████████████████  100% (expected)

Observed V3 sub-model mapping

  → openai/gpt-5.4                           3 (60%) ⚠ mismatch sim=0.85
  → openai/gpt-4.1                           2 (40%) ⚠ mismatch sim=0.75

Capability score distribution (auxiliary)

  0-49     █████████████████████████    5
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Family match	Most common V3 match
https://api.zetatechs.com/v1	2	100%	openai/gpt-5.4 (2)
https://api.vectorengine.ai/v1	2	100%	openai/gpt-4.1 (2)
https://api.gpteamservices.com/v1	1	100%	openai/gpt-5.4 (1)

Recent anomalies

https://api.gpteamservices.com/v1Jun 7, 2026, 9:08 AM

Self-claimed model: gpt-5.4-pro
V2 predicted family: openai
V3 best match: openai/gpt-5.4 (sim 0.82)
Verdict: Sub-model downgrade

https://api.zetatechs.com/v1Jun 7, 2026, 9:01 AM

Self-claimed model: gpt-5.4-pro
V2 predicted family: openai
V3 best match: openai/gpt-5.4 (sim 0.82)
Verdict: Sub-model downgrade

https://api.vectorengine.ai/v1May 29, 2026, 9:17 AM

Self-claimed model: gpt-5.4-pro
V2 predicted family: openai
V3 best match: openai/gpt-4.1 (sim 0.75)
Verdict: Sub-model downgrade

https://api.zetatechs.com/v1May 29, 2026, 9:10 AM

Self-claimed model: gpt-5.4-pro
V2 predicted family: openai
V3 best match: openai/gpt-5.4 (sim 0.93)
Verdict: Sub-model downgrade

https://api.vectorengine.ai/v1May 29, 2026, 9:08 AM

Self-claimed model: gpt-5.4-pro
V2 predicted family: openai
V3 best match: openai/gpt-4.1 (sim 0.75)
Verdict: Sub-model downgrade

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming openai/gpt-5.4-pro. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →