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

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

Last updated：Jul 30, 2026, 12:17 PM · Data window: past 90 days

Measured results (90 days)

8 runs · 3 hosts · 6 anomalies

Family-fingerprint consistency

  openai           6  ███████████████████░░░░░░   75% (expected)
  unknown          2  ██████░░░░░░░░░░░░░░░░░░░   25% (suspicious)

Observed V3 sub-model mapping

  → openai/gpt-5.2                           6 (75%) ⚠ mismatch sim=0.83
  → unknown                                  2 (25%) ⚠ mismatch

Capability score distribution (auxiliary)

  0-49     ██████░░░░░░░░░░░░░░░░░░░    2
  50-69    ██████████░░░░░░░░░░░░░░░    3
  70-89    ██████████░░░░░░░░░░░░░░░    3
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://api.quotaflow.ai/openai/v1	3	55	67%	openai/gpt-5.2 (2)
https://www.moyu.info/v1	3	68	100%	openai/gpt-5.2 (3)
https://api.quotaflow.ai/v1	2	40	50%	openai/gpt-5.2 (1)

Recent anomalies

https://api.quotaflow.ai/v1Jun 24, 2026, 7:27 AM

Self-claimed model: gpt-5.4-nano
V2 predicted family: openai
V3 best match: openai/gpt-5.2 (sim 0.86)
Verdict: Sub-model downgrade

https://api.quotaflow.ai/openai/v1Jun 22, 2026, 8:19 AM

Self-claimed model: gpt-5.4-nano
V2 predicted family: openai
V3 best match: openai/gpt-5.2 (sim 0.89)
Verdict: Sub-model downgrade

https://api.quotaflow.ai/openai/v1Jun 22, 2026, 6:38 AM

Self-claimed model: gpt-5.4-nano
V2 predicted family: openai
V3 best match: openai/gpt-5.2 (sim 0.84)
Verdict: Sub-model downgrade

https://www.moyu.info/v1May 22, 2026, 10:00 AM

Self-claimed model: gpt-5.4-nano
V2 predicted family: openai
V3 best match: openai/gpt-5.2 (sim 0.80)
Verdict: Sub-model downgrade

https://www.moyu.info/v1May 22, 2026, 9:01 AM

Self-claimed model: gpt-5.4-nano
V2 predicted family: openai
V3 best match: openai/gpt-5.2 (sim 0.68)
Verdict: Sub-model downgrade

https://www.moyu.info/v1May 22, 2026, 7:28 AM

Self-claimed model: gpt-5.4-nano
V2 predicted family: openai
V3 best match: openai/gpt-5.2 (sim 0.92)
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-nano. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →