gpt53codexspark · Model identity and integrity report
Last updated：Jul 30, 2026, 11:54 AM · Data window: past 90 days
Measured results (90 days)
17 runs · 15 hosts · 17 anomalies
Family-fingerprint consistency
openai 14 █████████████████████░░░░ 82% (suspicious) anthropic 3 █████░░░░░░░░░░░░░░░░░░░░ 18% (suspicious)
Observed V3 sub-model mapping
→ abstain 9 (53%) — low confidence → openai/gpt-5.2 5 (29%) ⚠ mismatch sim=0.89 → openai/gpt-5.4 2 (12%) ⚠ mismatch sim=0.96 → anthropic/claude-opus-4.5 1 ( 6%) ⚠ mismatch sim=0.67
Capability score distribution (auxiliary)
0-49 █████████░░░░░░░░░░░░░░░░ 6 50-69 ███░░░░░░░░░░░░░░░░░░░░░░ 2 70-89 █████████████░░░░░░░░░░░░ 9 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://sarang.id/v1 | 2 | 62 | 0% | anthropic/claude-opus-4.5 (1) |
| https://sub2.congmingai.com/v1 | 2 | 77 | 0% | openai/gpt-5.2 (1) |
| http://43.165.184.73:8080/v1 | 1 | 73 | 0% | — |
| https://api.DKBY.com/v1 | 1 | 76 | 0% | openai/gpt-5.2 (1) |
| https://aitokenyes.com/v1 | 1 | 86 | 0% | openai/gpt-5.4 (1) |
| https://api.sarang.id/v1 | 1 | 0 | 0% | — |
| https://zhiyuanapis.top/v1 | 1 | 75 | 0% | — |
| https://sub.rkshadow.com/v1 | 1 | 0 | 0% | openai/gpt-5.2 (1) |
| https://api.mouubox.com/v1 | 1 | 0 | 0% | openai/gpt-5.2 (1) |
| https://api.quotaflow.ai/v1 | 1 | 74 | 0% | — |
| https://vip.lcodex.cn/v1 | 1 | 0 | 0% | openai/gpt-5.4 (1) |
| https://www.codexapis.com/v1 | 1 | 79 | 0% | openai/gpt-5.2 (1) |
| https://ccb.180txt.cn/v1 | 1 | 0 | 0% | — |
| https://cf-newapi.thereapi.top/v1 | 1 | 0 | 0% | — |
| https://code.shoestravel.xin/v1 | 1 | 78 | 0% | — |
Recent anomalies
http://43.165.184.73:8080/v1Jul 11, 2026, 6:54 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.DKBY.com/v1Jul 11, 2026, 6:47 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.2 (sim 1.00)
- Verdict
- Full swap
https://aitokenyes.com/v1Jul 11, 2026, 6:39 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 1.00)
- Verdict
- Full swap
https://sarang.id/v1Jul 10, 2026, 10:27 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sarang.id/v1Jul 10, 2026, 10:23 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.67)
- Verdict
- Full swap
https://api.sarang.id/v1Jul 10, 2026, 9:08 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://zhiyuanapis.top/v1Jul 7, 2026, 4:38 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://sub.rkshadow.com/v1Jul 4, 2026, 3:39 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.2 (sim 0.93)
- Verdict
- Full swap
https://api.mouubox.com/v1Jun 30, 2026, 2:22 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.2 (sim 0.86)
- Verdict
- Full swap
https://api.quotaflow.ai/v1Jun 27, 2026, 6:04 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://vip.lcodex.cn/v1Jun 21, 2026, 6:04 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.4 (sim 0.92)
- Verdict
- Full swap
https://sub2.congmingai.com/v1Jun 20, 2026, 2:37 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- anthropic
- V3 best match
- openai/gpt-5.2 (sim 0.73)
- Verdict
- Full swap
https://www.codexapis.com/v1Jun 20, 2026, 2:33 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- openai/gpt-5.2 (sim 0.94)
- Verdict
- Full swap
https://sub2.congmingai.com/v1Jun 20, 2026, 2:29 PM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ccb.180txt.cn/v1Jun 20, 2026, 4:59 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://cf-newapi.thereapi.top/v1Jun 20, 2026, 3:49 AM
- Self-claimed model
- gpt-5.3-codex-spark
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://code.shoestravel.xin/v1Jun 15, 2026, 9:22 AM
- Self-claimed model
- gpt-5.3-codex-spark
- 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 gpt53codexspark. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.