anthropic/claude-opus-4.8 · Model identity and integrity report
Last updated:Jul 30, 2026, 1:17 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)
3041 runs · 941 hosts · 2592 anomalies
Family-fingerprint consistency
anthropic 2644 ██████████████████████░░░ 87% (expected) unknown 179 ██░░░░░░░░░░░░░░░░░░░░░░░ 6% (suspicious) deepseek 107 █░░░░░░░░░░░░░░░░░░░░░░░░ 4% (suspicious) openai 69 █░░░░░░░░░░░░░░░░░░░░░░░░ 2% (suspicious) qwen 32 ░░░░░░░░░░░░░░░░░░░░░░░░░ 1% (suspicious) google 7 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious) zhipu 3 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0% (suspicious)
Observed V3 sub-model mapping
→ abstain 1320 (43%) — low confidence → anthropic/claude-opus-4.5 582 (19%) ⚠ mismatch sim=0.68 → anthropic/claude-opus-4.7 500 (16%) ⚠ mismatch sim=0.83 → unknown 268 ( 9%) ⚠ mismatch → anthropic/claude-fable-5 94 ( 3%) ⚠ mismatch sim=0.91 → anthropic/claude-sonnet-4.6 79 ( 3%) ⚠ mismatch sim=0.75 → anthropic/claude-opus-4.8 76 ( 2%) ✓ correct sim=0.85 → anthropic/claude-sonnet-5 54 ( 2%) ⚠ mismatch sim=0.71 → anthropic/claude-sonnet-4.5 37 ( 1%) ⚠ mismatch sim=0.61 → anthropic/claude-opus-4.6 14 ( 0%) ⚠ mismatch sim=0.78 → openai/gpt-5.4 5 ( 0%) ⚠ mismatch sim=0.95 → openai/gpt-5.5 5 ( 0%) ⚠ mismatch sim=0.95 → anthropic/claude-haiku-4.5 4 ( 0%) ⚠ mismatch sim=0.72 → openai/gpt-5.2 2 ( 0%) ⚠ mismatch sim=0.74 → deepseek/deepseek-v4-pro 1 ( 0%) ⚠ mismatch sim=0.73
Capability score distribution (auxiliary)
0-49 ██████████░░░░░░░░░░░░░░░ 1222 50-69 █░░░░░░░░░░░░░░░░░░░░░░░░ 55 70-89 ███████░░░░░░░░░░░░░░░░░░ 836 90-100 ████████░░░░░░░░░░░░░░░░░ 928
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://cc-vibe.com/v1 | 72 | 40 | 93% | anthropic/claude-opus-4.5 (12) |
| https://api.aisz.mom/v1 | 61 | 75 | 98% | anthropic/claude-opus-4.7 (13) |
| https://api.ethancode.xyz/v1 | 48 | 76 | 98% | anthropic/claude-opus-4.5 (11) |
| https://www.yiyuantoken.com/v1 | 44 | 66 | 95% | anthropic/claude-opus-4.5 (25) |
| https://deepkey.top/v1 | 44 | 69 | 95% | anthropic/claude-opus-4.5 (13) |
| https://a6api.com/v1 | 39 | 35 | 90% | anthropic/claude-opus-4.5 (13) |
| https://rsxermu666.cn/v1 | 30 | 59 | 100% | anthropic/claude-opus-4.5 (7) |
| https://apiclaude.cc/v1 | 30 | 33 | 90% | anthropic/claude-opus-4.5 (3) |
| https://mikucode.xyz/v1 | 25 | 68 | 72% | anthropic/claude-opus-4.7 (4) |
| https://api.a6api.com/v1 | 24 | 34 | 100% | anthropic/claude-opus-4.5 (16) |
| https://yunwu.ai/v1 | 22 | 51 | 95% | anthropic/claude-opus-4.5 (8) |
| https://chegnzi.top/v1 | 21 | 71 | 90% | anthropic/claude-fable-5 (6) |
| https://muyuan.do/v1 | 21 | 47 | 100% | anthropic/claude-sonnet-4.5 (3) |
| https://api.passionapi.com/v1 | 20 | 0 | 100% | anthropic/claude-opus-4.5 (10) |
| https://opusrelay.com/v1 | 19 | 52 | 21% | deepseek/deepseek-v4-pro (1) |
| https://cc.freemodel.dev/v1 | 19 | 11 | 100% | — |
| https://api.shuaiapi.com/v1 | 18 | 49 | 89% | anthropic/claude-opus-4.7 (4) |
| https://sub.100xlabs.space/v1 | 18 | 49 | 83% | anthropic/claude-opus-4.5 (3) |
| https://turbo-api.com/v1 | 18 | 90 | 39% | anthropic/claude-sonnet-5 (4) |
| https://codexauv.com/v1 | 18 | 84 | 100% | anthropic/claude-sonnet-4.6 (6) |
| https://maxapi.hanyue.xyz/v1 | 17 | 32 | 100% | anthropic/claude-opus-4.5 (8) |
| https://api.llmapi.pro:99/v1 | 17 | 46 | 88% | anthropic/claude-opus-4.7 (2) |
| https://ai98pro.xyz/v1 | 17 | 91 | 100% | anthropic/claude-opus-4.7 (6) |
| https://api.lmuai.com/v1 | 16 | 24 | 69% | anthropic/claude-opus-4.5 (6) |
| https://api.vibelearning.top/v1 | 16 | 73 | 94% | anthropic/claude-opus-4.7 (5) |
Recent anomalies
https://sub.aspirinz.cc/v1Jul 30, 2026, 1:15 PM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-fable-5 (sim 1.00)
- Verdict
- Sub-model downgrade
http://208.87.240.193:7777/v1Jul 30, 2026, 1:09 PM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-5 (sim 0.72)
- Verdict
- Sub-model downgrade
https://www.cc-vibe.com/v1Jul 30, 2026, 12:07 PM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.packyapi.com/v1Jul 30, 2026, 12:03 PM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.65)
- Verdict
- Sub-model downgrade
https://downstream.jbbtoken.cn/v1Jul 30, 2026, 10:45 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-4.5 (sim 0.60)
- Verdict
- Sub-model downgrade
https://api.kunkunout.com/v1Jul 30, 2026, 10:28 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://aiapi.market/v1Jul 30, 2026, 10:28 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.64)
- Verdict
- Sub-model downgrade
https://api123.top/v1Jul 30, 2026, 9:12 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.70)
- Verdict
- Sub-model downgrade
https://osss.ai/v1Jul 30, 2026, 9:07 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://www.yiyuantoken.com/v1Jul 30, 2026, 8:28 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.67)
- Verdict
- Sub-model downgrade
https://tokken.cc/v1Jul 30, 2026, 8:12 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.70)
- Verdict
- Sub-model downgrade
https://ai.luminai.cc/v1Jul 30, 2026, 6:42 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.68)
- Verdict
- Sub-model downgrade
https://hk-user.twskyhope.top/v1Jul 30, 2026, 6:36 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.70)
- Verdict
- Sub-model downgrade
https://ai.furry.vg/v1Jul 30, 2026, 6:08 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.92)
- Verdict
- Sub-model downgrade
https://ai.furry.vg/v1Jul 30, 2026, 5:52 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.65)
- Verdict
- Sub-model downgrade
https://hk-user.twskyhope.top/v1Jul 30, 2026, 5:46 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-opus-4.5 (sim 0.67)
- Verdict
- Sub-model downgrade
https://hanhaoshuai.dpdns.org/v1Jul 30, 2026, 3:37 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-4.5 (sim 0.61)
- Verdict
- Sub-model downgrade
https://tokken.cc/v1Jul 30, 2026, 2:35 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://zivv.pro/v1Jul 30, 2026, 2:34 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-fable-5 (sim 1.00)
- Verdict
- Sub-model downgrade
https://cc-vibe.com/v1Jul 30, 2026, 1:41 AM
- Self-claimed model
- claude-opus-4-8
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-sonnet-4.5 (sim 0.61)
- Verdict
- Sub-model downgrade
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming anthropic/claude-opus-4.8. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.