claudeopus45 · Model identity and integrity report
Last updated：Sep 13, 2026, 6:49 PM · Data window: past 90 days
Verification capability — fingerprint reference available
- Family
- anthropic
- 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
- 60 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)
50 runs · 29 hosts · 31 anomalies
Family-fingerprint consistency
anthropic 47 ████████████████████████░ 94% (expected) unknown 2 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious) deepseek 1 █░░░░░░░░░░░░░░░░░░░░░░░░ 2% (suspicious)
Observed V3 sub-model mapping
→ abstain 23 (46%) — low confidence → anthropic/claude-opus-4.5 16 (32%) ⚠ mismatch sim=0.86 → anthropic/claude-opus-4.6 4 ( 8%) ⚠ mismatch sim=0.81 → unknown 3 ( 6%) ⚠ mismatch → anthropic/claude-sonnet-4.5 2 ( 4%) ⚠ mismatch sim=0.91 → anthropic/claude-sonnet-4.6 1 ( 2%) ⚠ mismatch sim=0.69 → anthropic/claude-sonnet-5 1 ( 2%) ⚠ mismatch sim=0.76
Capability score distribution (auxiliary)
0-49 ███████████████░░░░░░░░░░ 30 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 2 70-89 █████████░░░░░░░░░░░░░░░░ 18 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://speed.toter.me/v1 | 7 | 10 | 100% | anthropic/claude-opus-4.6 (2) |
| https://ai.furry.vg/v1 | 6 | 43 | 100% | anthropic/claude-opus-4.5 (4) |
| https://turbo-api.com/v1 | 5 | 86 | 100% | anthropic/claude-opus-4.5 (5) |
| https://api.gpt2share.com/v1 | 3 | 86 | 100% | anthropic/claude-opus-4.5 (3) |
| https://sarang.id/v1 | 3 | 45 | 67% | anthropic/claude-sonnet-5 (1) |
| https://ruoli.dev/v1 | 2 | 0 | 100% | — |
| https://api.qiyiguoai.com/v1 | 2 | 87 | 100% | anthropic/claude-opus-4.6 (2) |
| https://api.unreallou.com/v1 | 1 | 0 | 100% | — |
| https://speed32.toter.me/v1 | 1 | 0 | 100% | — |
| https://api.opusmax.pro/v1 | 1 | 0 | 100% | — |
| https://tdyun.ai/v1 | 1 | 0 | 100% | — |
| https://speed18.toter.me/v1 | 1 | 0 | 100% | — |
| https://speed11.toter.me/v1 | 1 | 0 | 100% | anthropic/claude-opus-4.5 (1) |
| https://uuapi.io/v1 | 1 | 0 | 100% | — |
| https://llm.twinight.co/v1 | 1 | 0 | 0% | — |
| https://speed48.toter.me/v1 | 1 | 0 | 100% | — |
| https://ccapi.ztxfkw.top/v1 | 1 | 76 | 100% | — |
| https://cc.cervus.top/v1 | 1 | 67 | 100% | anthropic/claude-opus-4.5 (1) |
| https://www.daseinai.xyz/v1 | 1 | 0 | 100% | — |
| https://kirohc.wisdomhermes.com/v1 | 1 | 0 | 0% | — |
| https://pool.chaozhiyuanai.com/v1 | 1 | 0 | 100% | — |
| https://api456.me/v1 | 1 | 0 | 100% | — |
| https://www.bb-api.com/v1 | 1 | 81 | 100% | — |
| https://a2neai.com/v1 | 1 | 0 | 100% | — |
| https://api.gemai.cc/v1 | 1 | 0 | 100% | anthropic/claude-sonnet-4.5 (1) |
Recent anomalies
https://api.unreallou.com/v1Sep 12, 2026, 3:58 AM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api.opusmax.pro/v1Sep 11, 2026, 7:32 AM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://tdyun.ai/v1Sep 9, 2026, 5:17 PM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed18.toter.me/v1Sep 9, 2026, 9:18 AM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ruoli.dev/v1Sep 8, 2026, 3:42 PM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://uuapi.io/v1Sep 8, 2026, 5:28 AM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed48.toter.me/v1Sep 5, 2026, 8:46 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ccapi.ztxfkw.top/v1Sep 5, 2026, 5:27 PM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed.toter.me/v1Sep 5, 2026, 3:57 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed.toter.me/v1Sep 5, 2026, 3:50 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed.toter.me/v1Sep 5, 2026, 3:40 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.6 (sim 0.88)
- Verdict
- Sub-model downgrade
https://speed.toter.me/v1Sep 5, 2026, 3:29 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.6 (sim 0.80)
- Verdict
- Full swap
https://speed.toter.me/v1Sep 5, 2026, 3:15 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://speed.toter.me/v1Sep 5, 2026, 2:40 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-4.5 (sim 0.82)
- Verdict
- Sub-model downgrade
https://www.daseinai.xyz/v1Aug 28, 2026, 1:59 PM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://pool.chaozhiyuanai.com/v1Aug 24, 2026, 6:32 PM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://api456.me/v1Aug 24, 2026, 9:55 AM
- Self-claimed model
- claude-opus-4-5
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.bb-api.com/v1Aug 23, 2026, 3:38 PM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://ruoli.dev/v1Aug 23, 2026, 7:12 AM
- Self-claimed model
- claude-opus-4-5-20251101
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://a2neai.com/v1Aug 14, 2026, 9:16 PM
- Self-claimed model
- claude-opus-4-5-20251101
- 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 claudeopus45. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.