deepseek-v4-pro-0813 standard verification model-consistency report
Report ID MZZR202608271038385EE13DGenerated at 2026/08/27 18:38
Matched
deepseek-v4-pro-0813 standard verification result: Matched (94/100). Main deductions: Brand-boundary response was unclear; Verification signals need review.
94Consistency score
主要扣分项：品牌边界表达不清；验真信号待复核。
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Pro
Providersa6api
Samples24 probes
Duration4 min 16 sec
Verification versionV11
Identity verdictVerified
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.
Measured token usage827.2KFrom the response usage fields; this is the report's primary usage measure.Test-suite estimate1.7MPrecisely estimated from this test suite when no official baseline is available.Variance assessment51% belowMeasured token usage is below the estimate, possibly due to tokenizer, compression, or usage-reporting differences.Usage conclusionBelow estimateThis 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 5 times
Observed cache share57.4%
Low cache share
Cached tokens were observed, but the share is low. Review API parameters, context reuse, and billing methodology.
Observed tokens14.1KCached tokens8.1KNon-cached tokens6.0KAverage per run2.8K
Cache share by testRepresents the API-reported cache share, not the final billing discount.
Long-context test
Shows stable responses at different context lengths and the model center reference window.
7 samples
Verified up to 32K
1M 需要关注，原因：上下文保持较弱。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths1M / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
64K 档暂不作为当前线路的稳定上下文参考。
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Matched94/100
主要扣分项：品牌边界表达不清；验真信号待复核。
Callability and model visibility15 / 15
No deductions
Protocol and response structure15 / 15
No deductions
Identity and model match16 / 20
品牌边界表达不清（标准题：品牌边界） -4
能力题表现20 / 20
No deductions
Usage and billing consistency15 / 15
No deductions
稳定性与复测表现13 / 15
存在需复核项 -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
Basic call probe
The basic API call succeeded and returned a recognizable response.
deepseek-v4-pro-0813 standard verification result: Matched (94/100). Main deductions: Brand-boundary response was unclear; Verification signals need review.
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Pro
Providersa6api
Samples24
Duration4 min
Test versionV11
Identity verdictVerified
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.
Measured token usage827.2KFrom the response usage fields; this is the report's primary usage measure.Test-suite estimate1.7MPrecisely estimated from this test suite when no official baseline is available.Variance assessment51% belowMeasured token usage is below the estimate, possibly due to tokenizer, compression, or usage-reporting differences.Usage conclusionBelow estimateThis 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 5 times
Observed cache share57.4%
Low cache share
Cached tokens were observed, but the share is low. Review API parameters, context reuse, and billing methodology.
Observed tokens14.1KCached tokens8.1KNon-cached tokens6.0KAverage per run2.8K
Cache share by testRepresents the API-reported cache share, not the final billing discount.
Long-context test
Shows stable responses at different context lengths and the model center reference window.
7 samples
Verified up to 32K
1M 需要关注，原因：上下文保持较弱。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths1M / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
64K 档暂不作为当前线路的稳定上下文参考。
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Matched94/100
主要扣分项：品牌边界表达不清；验真信号待复核。
Callability and model visibility15 / 15
No deductions
Protocol and response structure15 / 15
No deductions
Identity and model match16 / 20
品牌边界表达不清（标准题：品牌边界） -4
能力题表现20 / 20
No deductions
Usage and billing consistency15 / 15
No deductions
稳定性与复测表现13 / 15
存在需复核项 -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
Basic call probe
The basic API call succeeded and returned a recognizable response.
