deepseek-v4-pro-0813 standard verification model-consistency report
Report ID MZZR2026082710292250AD8BGenerated at 2026/08/27 18:29
Suspected impersonation / unavailable
deepseek-v4-pro-0813 standard verification result: Suspected impersonation / unavailable (33/100). Main deductions: Basic API call unavailable; Failed evidence items were found.
33Consistency score
主要扣分项：基础调用不可用；存在Failed证据项。
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Pro
Providersa6api
Samples2 probes
Duration12 sec
Verification versionV11
Identity verdictNot verified
Verification basisMozhenzhen versioned baseline
Token usage
Measured API usage is shown first; official baselines or test estimates are used only when measured values are unavailable.
Estimated token usage1.7MUses the test-suite estimate when measured usage is unavailable.Variance assessmentNone本报告有题包预计 Token，但当前接口没有返回实际用量。Usage conclusion只看到预计This reflects usage observability, not the final billed amount.
Token cache usage test
Observes token usage, cache fields, and reuse across rounds; 0% means no cached-token field was observed.
Tested 0 times
Observed cache share--
暂未观测到用量记录
当前接口没有稳定返回 Token 用量记录，建议结合账单明细或接口日志复核。
Observed tokens0Cached tokens0Non-cached tokens0Average per run--
Cache share by testRepresents the API-reported cache share, not the final billing discount.
No per-test records are available; only the aggregate result is shown.
Long-context test
Shows stable responses at different context lengths and the model center reference window.
7 samples
未形成稳定样本
基础调用未成功（基础调用不可用），长上下文专项已跳过。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths990K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
基础调用未成功（基础调用不可用），长上下文专项已跳过。
A newer report is availableThis report has been superseded by a later retest. View the latest report。
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Suspected impersonation / unavailable33/100
主要扣分项：基础调用不可用；存在Failed证据项。
Callability and model visibility0 / 15
基础调用不可用（基础调用探针） -15
Protocol and response structure0 / 15
基础调用不可用（基础调用探针） -15
Identity and model match12 / 20
基础调用不可用（基础调用探针） -8
能力题表现8 / 20
基础调用不可用（基础调用探针） -12
Usage and billing consistency10 / 15
基础调用不可用（基础调用探针） -5
稳定性与复测表现3 / 15
基础调用不可用（基础调用探针） -10存在Failed证据项 -2
Test details
Expand each check to view the redacted evidence notes.
20 checks
Model list visibility
deepseek-v4-pro-0813 is visible in the API model list.
Passed
Test evidence
Check: Model list visibility
Status: Passed
Samples: 1
API path: /models
Visible models: 1
Check: Specialty test: token cache usage over 5 rounds
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Token cache usage test (may affect real billing)
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
Check: Specialty test: 32K context capability
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
deepseek-v4-pro-0813 standard verification result: Suspected impersonation / unavailable (33/100). Main deductions: Basic API call unavailable; Failed evidence items were found.
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Pro
Providersa6api
Samples2
Duration12 sec
Test versionV11
Identity verdictNot verified
Verification basisMozhenzhen versioned baseline
Token usage
Measured API usage is shown first; official baselines or test estimates are used only when measured values are unavailable.
Estimated token usage1.7MUses the test-suite estimate when measured usage is unavailable.Variance assessmentNone本报告有题包预计 Token，但当前接口没有返回实际用量。Usage conclusion只看到预计This reflects usage observability, not the final billed amount.
Token cache usage test
Observes token usage, cache fields, and reuse across rounds; 0% means no cached-token field was observed.
Tested 0 times
Observed cache share--
暂未观测到用量记录
当前接口没有稳定返回 Token 用量记录，建议结合账单明细或接口日志复核。
Observed tokens0Cached tokens0Non-cached tokens0Average per run--
Cache share by testRepresents the API-reported cache share, not the final billing discount.
No per-test records are available; only the aggregate result is shown.
Long-context test
Shows stable responses at different context lengths and the model center reference window.
7 samples
未形成稳定样本
基础调用未成功（基础调用不可用），长上下文专项已跳过。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths990K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
基础调用未成功（基础调用不可用），长上下文专项已跳过。
A newer report is availableThis report has been superseded by a later retest. View the latest report。
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Suspected impersonation / unavailable33/100
主要扣分项：基础调用不可用；存在Failed证据项。
Callability and model visibility0 / 15
基础调用不可用（基础调用探针） -15
Protocol and response structure0 / 15
基础调用不可用（基础调用探针） -15
Identity and model match12 / 20
基础调用不可用（基础调用探针） -8
能力题表现8 / 20
基础调用不可用（基础调用探针） -12
Usage and billing consistency10 / 15
基础调用不可用（基础调用探针） -5
稳定性与复测表现3 / 15
基础调用不可用（基础调用探针） -10存在Failed证据项 -2
Test details
Expand each check to view the redacted evidence notes.
20 checks
Model list visibility
deepseek-v4-pro-0813 is visible in the API model list.
Passed
Test evidence
Check: Model list visibility
Status: Passed
Samples: 1
API path: /models
Visible models: 1
Check: Specialty test: token cache usage over 5 rounds
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Token cache usage test (may affect real billing)
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
Check: Specialty test: 32K context capability
Status: Skipped
Samples: 0
Test type: Text test
Specialty: Context test
跳过原因：基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
