deepseek-v4-flash standard verification model-consistency report
Report ID MZZR2026070902571006BAA7Generated at 2026/07/09 10:57
Highly matched
deepseek-v4-flash standard verification result: Highly matched (100/100). All primary checks passed in this run.
100Consistency score
All primary checks passed in this run.
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Flash
ProvidersInfistar
Samples106 probes
Duration1 min 50 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 usage227.5KFrom 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 assessment87% 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.
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.
5 samples
Verified up to 200K
400K 需要关注，原因：接口服务异常。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32K / 64K / 100K / 200K / 400KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
400K 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
Highly matched100/100
All primary checks passed in this run.
Callability and model visibility15 / 15
No deductions
Protocol and response structure15 / 15
No deductions
Identity and model match20 / 20
No deductions
能力题表现20 / 20
No deductions
Usage and billing consistency15 / 15
No deductions
稳定性与复测表现15 / 15
No deductions
Test details
Expand each check to view the redacted evidence notes.
18 checks
Model list visibility
deepseek-v4-flash is visible in the API model list.
Passed
Test evidence
Check: Model list visibility
Status: Passed
Samples: 85
API path: /v1/models
Visible models: 85
Basic call probe
The basic API call succeeded and returned a recognizable response.
deepseek-v4-flash standard verification result: Highly matched (100/100). All primary checks passed in this run.
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Flash
ProvidersInfistar
Samples106
Duration2 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 usage227.5KFrom 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 assessment87% 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.
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.
5 samples
Verified up to 200K
400K 需要关注，原因：接口服务异常。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32K / 64K / 100K / 200K / 400KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
400K 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
Highly matched100/100
All primary checks passed in this run.
Callability and model visibility15 / 15
No deductions
Protocol and response structure15 / 15
No deductions
Identity and model match20 / 20
No deductions
能力题表现20 / 20
No deductions
Usage and billing consistency15 / 15
No deductions
稳定性与复测表现15 / 15
No deductions
Test details
Expand each check to view the redacted evidence notes.
18 checks
Model list visibility
deepseek-v4-flash is visible in the API model list.
Passed
Test evidence
Check: Model list visibility
Status: Passed
Samples: 85
API path: /v1/models
Visible models: 85
Basic call probe
The basic API call succeeded and returned a recognizable response.
