claudeopus48thinking · Model identity and integrity report
Last updated：Sep 13, 2026, 5:03 PM · Data window: past 90 days
Measured results (90 days)
159 runs · 37 hosts · 149 anomalies
Family-fingerprint consistency
anthropic 149 ████████████████████████░ 94% (suspicious) unknown 10 ██░░░░░░░░░░░░░░░░░░░░░░░ 6% (suspicious)
Observed V3 sub-model mapping
→ abstain 120 (75%) — low confidence → unknown 14 ( 9%) ⚠ mismatch → anthropic/claude-opus-4.5 13 ( 8%) ⚠ mismatch sim=0.68 → anthropic/claude-opus-4.7 9 ( 6%) ⚠ mismatch sim=0.75 → anthropic/claude-fable-5 1 ( 1%) ⚠ mismatch sim=0.85 → anthropic/claude-sonnet-4.6 1 ( 1%) ⚠ mismatch sim=0.73 → anthropic/claude-opus-4.6 1 ( 1%) ⚠ mismatch sim=0.81
Capability score distribution (auxiliary)
0-49 █████████████████░░░░░░░░ 105 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 4 70-89 ████████░░░░░░░░░░░░░░░░░ 50 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://tabitoken.com/v1 | 36 | 20 | 0% | — |
| https://api.justwoker.icu/v1 | 31 | 18 | 0% | — |
| https://gorouter.app/v1 | 23 | 24 | 0% | anthropic/claude-opus-4.5 (2) |
| https://rsxermu666.cn/v1 | 15 | 59 | 0% | anthropic/claude-opus-4.5 (3) |
| https://kktoken.cc/v1 | 8 | 0 | 0% | — |
| https://true-sota.com/v1 | 3 | 0 | 0% | — |
| https://aitext.likiq.top/v1 | 3 | 80 | 0% | — |
| https://syapi.loark.online/v1 | 3 | 64 | 0% | — |
| https://api.lmuai.com/v1 | 3 | 28 | 0% | anthropic/claude-opus-4.5 (2) |
| https://cc.honoursoft.cn/v1 | 3 | 81 | 0% | — |
| https://tokken.cc/v1 | 2 | 44 | 0% | anthropic/claude-opus-4.7 (2) |
| https://airouter.linkof.link/v1 | 2 | 0 | 0% | anthropic/claude-opus-4.7 (1) |
| https://api.qiuqiutoken.com/v1 | 2 | 0 | 0% | — |
| https://bxcv.store/v1 | 2 | 83 | 0% | anthropic/claude-opus-4.5 (2) |
| https://yt.19851117.xyz/v1 | 1 | 0 | 0% | — |
| https://openox.tech/v1 | 1 | 0 | 0% | — |
| https://9r.bores.my.id/gorouter/v1 | 1 | 0 | 0% | — |
| https://www.dogapi.cc/v1 | 1 | 0 | 0% | — |
| https://lucen.cc/v1 | 1 | 0 | 0% | — |
| https://api.chunxiao.pro/v1 | 1 | 0 | 0% | — |
| https://kiro.pix4k.com/v1 | 1 | 0 | 0% | anthropic/claude-opus-4.7 (1) |
| https://once.novai.su/v1 | 1 | 84 | 0% | anthropic/claude-fable-5 (1) |
| http://38.255.17.214:3000/v1 | 1 | 66 | 0% | anthropic/claude-sonnet-4.6 (1) |
| https://sub.kirotoken.cloud/v1 | 1 | 0 | 0% | — |
| https://paidyun.cc.cd/v1 | 1 | 84 | 0% | — |
Recent anomalies
https://yt.19851117.xyz/v1Sep 8, 2026, 7:04 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Sep 6, 2026, 2:03 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://kktoken.cc/v1Sep 5, 2026, 6:24 PM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Sep 5, 2026, 3:24 PM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Sep 5, 2026, 4:23 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Sep 5, 2026, 3:56 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Sep 5, 2026, 3:14 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://kktoken.cc/v1Sep 5, 2026, 2:32 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://rsxermu666.cn/v1Sep 2, 2026, 4:09 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://rsxermu666.cn/v1Sep 2, 2026, 3:55 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://rsxermu666.cn/v1Sep 2, 2026, 3:41 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://rsxermu666.cn/v1Sep 2, 2026, 3:39 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://kktoken.cc/v1Sep 1, 2026, 3:39 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://kktoken.cc/v1Aug 31, 2026, 11:22 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://true-sota.com/v1Aug 31, 2026, 3:10 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Aug 30, 2026, 11:53 PM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Aug 30, 2026, 11:25 PM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://true-sota.com/v1Aug 30, 2026, 2:58 PM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Aug 30, 2026, 12:35 PM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.justwoker.icu/v1Aug 30, 2026, 3:47 AM
- Self-claimed model
- claude-opus-4-8-thinking
- V2 predicted family
- anthropic
- 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 claudeopus48thinking. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.