openai/gpt-5.5 · Model identity and integrity report
Last updated：Jul 30, 2026, 12:15 PM · Data window: past 90 days
Verification capability — fingerprint reference available
- Family
- openai
- V3 sub-model reference
- Available ✓
- Checks
- 知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數
- Family-fingerprint coverage
- 52 weighted rules · 8 feature categories
Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.
Measured results (90 days)
4984 runs · 1662 hosts · 4398 anomalies
Family-fingerprint consistency
openai 4546 ███████████████████████░░ 91% (expected) unknown 279 ██░░░░░░░░░░░░░░░░░░░░░░░ 6% (suspicious) anthropic 138 █░░░░░░░░░░░░░░░░░░░░░░░░ 3% (suspicious) google 11 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) zhipu 10 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ abstain 4160 (83%) — low confidence → unknown 420 ( 8%) ⚠ mismatch → openai/gpt-5.5 192 ( 4%) ✓ correct sim=0.95 → openai/gpt-5.4 178 ( 4%) ⚠ mismatch sim=0.95 → openai/gpt-5.2 12 ( 0%) ⚠ mismatch sim=0.93 → openai/gpt-5.4-mini 9 ( 0%) ⚠ mismatch sim=0.90 → openai/gpt-5-mini 3 ( 0%) ⚠ mismatch sim=0.77 → openai/gpt-5.3-codex 3 ( 0%) ⚠ mismatch sim=0.98 → anthropic/claude-fable-5 2 ( 0%) ⚠ mismatch sim=0.78 → openai/gpt-4.1 2 ( 0%) ⚠ mismatch sim=0.74 → openai/gpt-5 1 ( 0%) ⚠ mismatch sim=0.83 → google/gemini-3.1-pro-preview 1 ( 0%) ⚠ mismatch sim=0.76 → anthropic/claude-opus-4.7 1 ( 0%) ⚠ mismatch sim=0.94
Capability score distribution (auxiliary)
0-49 █████████░░░░░░░░░░░░░░░░ 1744 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 101 70-89 █████████░░░░░░░░░░░░░░░░ 1747 90-100 ███████░░░░░░░░░░░░░░░░░░ 1392
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://token.dialoguedui.com/v1 | 117 | 71 | 93% | openai/gpt-5.4 (3) |
| https://ai-pixel.online/v1 | 43 | 67 | 98% | — |
| https://ai.input.im/v1 | 42 | 45 | 98% | openai/gpt-5.4 (5) |
| https://www.packyapi.com/v1 | 34 | 28 | 38% | — |
| https://sub2.congmingai.com/v1 | 33 | 63 | 94% | openai/gpt-5.5 (4) |
| https://mdkj.lol/v1 | 30 | 56 | 93% | openai/gpt-5.5 (2) |
| https://sub2api.luchikey.com/v1 | 30 | 84 | 100% | openai/gpt-5.5 (1) |
| https://jojocode.com/v1 | 27 | 48 | 100% | openai/gpt-5.4 (6) |
| https://lingsuan.top/v1 | 27 | 55 | 89% | openai/gpt-5.5 (2) |
| https://api.aisz.mom/v1 | 27 | 70 | 96% | openai/gpt-5.5 (2) |
| https://ai2.hhhl.cc/v1 | 26 | 70 | 88% | — |
| https://bobdong.cn/v1 | 26 | 84 | 92% | openai/gpt-5.5 (1) |
| https://new.sharedchat.cc/codex | 25 | 3 | 0% | — |
| https://www.codexapis.com/v1 | 25 | 70 | 100% | — |
| https://zz1cc.cc.cd/v1 | 25 | 67 | 100% | openai/gpt-5.5 (1) |
| https://api.ikuncode.cc/v1 | 24 | 66 | 96% | openai/gpt-5.4 (1) |
| https://yunwu.ai/v1 | 22 | 60 | 95% | openai/gpt-5.4 (2) |
| https://ciyuan.fast/v1 | 22 | 30 | 91% | openai/gpt-5.4 (1) |
| https://api.mouubox.com/v1 | 22 | 67 | 100% | openai/gpt-5.4 (3) |
| https://aiapi1.cc.cd/v1 | 22 | 47 | 82% | — |
| https://a6api.com/v1 | 21 | 71 | 100% | openai/gpt-5.4 (1) |
| https://bmapi.020212.xyz/v1 | 21 | 56 | 86% | openai/gpt-5.4 (1) |
| https://modcon.top/v1 | 20 | 76 | 95% | — |
| https://vsllm.com/v1 | 20 | 51 | 75% | openai/gpt-5.5 (1) |
| https://us.pinai-cn.com/v1 | 20 | 81 | 100% | — |
Recent anomalies
https://yuesub.qxy.one/v1Jul 30, 2026, 11:15 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub2api.apiship.ai/v1Jul 30, 2026, 9:51 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.entropicecho.com/v1Jul 30, 2026, 9:36 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://wawapii.com/v1Jul 30, 2026, 9:11 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://chinallmapi.com/v1Jul 30, 2026, 9:07 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 0.93)
- Verdict
- Sub-model downgrade
https://api.aijws.com/v1Jul 30, 2026, 8:09 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://cccctoken.com/api/v1Jul 30, 2026, 5:51 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://zz.caijiyun.top/v1Jul 30, 2026, 1:52 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://fakelagforever.space/v1Jul 29, 2026, 6:50 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://fakelagforever.space/v1Jul 29, 2026, 5:35 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.apikl.ai/v1Jul 29, 2026, 5:29 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://fakelagforever.space/v1Jul 29, 2026, 5:28 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://fakelagforever.space/v1Jul 29, 2026, 4:36 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://fakelagforever.space/v1Jul 29, 2026, 4:26 PM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub.sailapi.top/v1Jul 29, 2026, 11:28 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://gpt.ecxwxz.top/v1Jul 29, 2026, 9:19 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://apizh.net/v1Jul 29, 2026, 7:58 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.ai2any.space/v1Jul 29, 2026, 2:51 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.yintu.cc/v1Jul 29, 2026, 2:30 AM
- Self-claimed model
- gpt-5.5
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://teio.me/v1Jul 28, 2026, 3:50 PM
- Self-claimed model
- gpt-5.5
- 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 openai/gpt-5.5. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.