gpt54 · Model identity and integrity report
Last updated:Jul 30, 2026, 10:16 AM · Data window: past 90 days
Measured results (90 days)
552 runs · 351 hosts · 531 anomalies
Family-fingerprint consistency
openai 524 ████████████████████████░ 95% (suspicious) unknown 21 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious) anthropic 4 ░░░░░░░░░░░░░░░░░░░░░░░░░ 1% (suspicious) zhipu 2 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) deepseek 1 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ openai/gpt-5.4 398 (72%) ⚠ mismatch sim=0.97 → abstain 105 (19%) — low confidence → unknown 33 ( 6%) ⚠ mismatch → openai/gpt-5.4-mini 8 ( 1%) ⚠ mismatch sim=0.94 → openai/gpt-5.2 3 ( 1%) ⚠ mismatch sim=0.82 → openai/gpt-5-mini 2 ( 0%) ⚠ mismatch sim=0.78 → deepseek/deepseek-v4-flash 1 ( 0%) ⚠ mismatch sim=0.84 → openai/gpt-5.5 1 ( 0%) ⚠ mismatch sim=0.79 → openai/gpt-4.1 1 ( 0%) ⚠ mismatch sim=0.74
Capability score distribution (auxiliary)
0-49 ██████████░░░░░░░░░░░░░░░ 224 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 8 70-89 ███████░░░░░░░░░░░░░░░░░░ 162 90-100 ███████░░░░░░░░░░░░░░░░░░ 158
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://ai.input.im/v1 | 10 | 62 | 0% | openai/gpt-5.4 (5) |
| https://jojocode.com/v1 | 9 | 19 | 0% | openai/gpt-5.4 (8) |
| https://api.euzhi.com/v1 | 7 | 87 | 0% | openai/gpt-5.4 (7) |
| https://code.shoestravel.xin/v1 | 6 | 79 | 0% | openai/gpt-5.4 (2) |
| https://api.apig.codes/v1 | 6 | 91 | 0% | openai/gpt-5.4 (4) |
| https://www.moyu.info/v1 | 6 | 90 | 0% | openai/gpt-5.4 (6) |
| https://tokenapi.link/v1 | 5 | 34 | 0% | openai/gpt-5.4 (4) |
| https://ciyuan.fast/v1 | 5 | 32 | 0% | openai/gpt-5.4 (1) |
| https://2api.1314mc.net/v1 | 5 | 62 | 0% | openai/gpt-5.4 (4) |
| https://vip.auto-code.net/v1 | 5 | 72 | 0% | openai/gpt-5.4 (5) |
| https://zyrus.aitoken.credit/v1 | 4 | 92 | 0% | openai/gpt-5.4 (2) |
| https://yunwu.ai/v1 | 4 | 45 | 0% | openai/gpt-5.4 (4) |
| https://cf-fast.cctq.ai/v1 | 4 | 44 | 0% | openai/gpt-5.4 (3) |
| https://a6api.com/v1 | 4 | 92 | 0% | openai/gpt-5.4 (3) |
| https://aicanapi.com/v1 | 4 | 45 | 0% | openai/gpt-5.4 (2) |
| https://ai.furry.vg/v1 | 4 | 85 | 0% | openai/gpt-5.4 (3) |
| https://api.wudi987.com/v1 | 4 | 65 | 0% | openai/gpt-5.4 (2) |
| https://leleapi.top/v1 | 4 | 88 | 0% | openai/gpt-5.4 (3) |
| https://truecodex.x7go.top/v1 | 4 | 69 | 0% | openai/gpt-5.4 (2) |
| https://codex.ciii.club/v1 | 3 | 58 | 0% | openai/gpt-5.4 (1) |
| https://ai-api.kkidc.com/v1 | 3 | 31 | 0% | openai/gpt-5.4 (2) |
| https://api.aiapipay.com/v1 | 3 | 89 | 0% | openai/gpt-5.4 (2) |
| https://botcf.com/v1 | 3 | 61 | 0% | openai/gpt-5.4 (3) |
| https://api.wluvyh.cloud/v1 | 3 | 50 | 0% | openai/gpt-5.4 (1) |
| https://muyuan.do/v1 | 3 | 36 | 0% | openai/gpt-5.4-mini (1) |
Recent anomalies
https://sub2api.apiship.ai/v1Jul 30, 2026, 10:03 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://api.apikl.ai/v1Jul 29, 2026, 5:12 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://api.tokeneasy.com.cn/v1Jul 28, 2026, 7:10 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://api.tokeneasy.com.cn/v1Jul 28, 2026, 7:00 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://mixai.cc/v1Jul 26, 2026, 6:09 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://mixai.cc/v1Jul 26, 2026, 6:06 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://jojocode.com/v1Jul 25, 2026, 9:13 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://sub2api.crazybunqnq.com/v1Jul 25, 2026, 5:19 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- deepseek
- V3 best match
- deepseek/deepseek-v4-flash (sim 0.85)
- Verdict
- Full swap
https://omnixai.cn/v1Jul 25, 2026, 3:44 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.bytecatcode.org/v1Jul 23, 2026, 9:21 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://llm-api.net/v1Jul 22, 2026, 2:38 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://codex.ciii.club/v1Jul 21, 2026, 9:09 PM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.taidesk.com/tai-ai/v1Jul 21, 2026, 7:34 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4-mini (sim 0.88)
- Verdict
- Full swap
https://tokenapi.link/v1Jul 21, 2026, 7:33 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
http://154.9.224.59:8080/v1Jul 21, 2026, 6:52 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://aihub.top/v1Jul 20, 2026, 6:39 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://docode.cc/v1Jul 20, 2026, 2:35 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://ai-api.kkidc.com/v1Jul 18, 2026, 11:43 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://ai-api.kkidc.com/v1Jul 18, 2026, 11:40 AM
- Self-claimed model
- gpt-5.4
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://ai-api.kkidc.com/v1Jul 18, 2026, 11:22 AM
- Self-claimed model
- gpt-5.4
- 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 gpt54. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.