deepseek-v4-flash deep verification model-consistency report
Report ID MZZR20260805074122C0ED98Generated at 2026/08/05 15:41
Suspected impersonation / unavailable
deepseek-v4-flash deep verification result: Suspected impersonation / unavailable (4/100). Main deductions: Basic API call unavailable; Model not visible in the model list; Failed evidence items were found.
4Consistency score
主要扣分项：基础调用不可用；模型列表不可见；存在Failed证据项。
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Flash
Providers聚光AI
SamplesPending review
Duration11 sec
Verification versionV11
Identity verdictNot verified
Verification basisOken
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.
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
模型列表没有看到该模型，长上下文专项无法继续验证。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths950K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
模型列表没有看到该模型，长上下文专项无法继续验证。
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Suspected impersonation / unavailable4/100
主要扣分项：基础调用不可用；模型列表不可见；存在Failed证据项。
Callability and model visibility0 / 10
基础调用不可用 -10
Protocol and response structure0 / 12
基础调用不可用 -12
Identity and model match0 / 18
基础调用不可用 -8模型列表不可见（模型列表可见性） -10
Core capabilities and model-specific tests1 / 25
基础调用不可用 -12模型列表不可见（模型列表可见性） -12
Usage and billing consistency0 / 10
基础调用不可用 -5模型列表不可见（模型列表可见性） -5
Reliability and availability3 / 25
基础调用不可用 -10模型列表不可见（模型列表可见性） -10存在Failed证据项 -2
Test details
Expand each check to view the redacted evidence notes.
27 checks
Model list visibility
接口模型列表中暂未看到 deepseek-v4-flash。
Failed
Test evidence
Check: Model list visibility
Status: Failed
Samples: 0
Needs review原因：模型列表不可见
deepseek-v4-flash deep verification result: Suspected impersonation / unavailable (4/100). Main deductions: Basic API call unavailable; Model not visible in the model list; Failed evidence items were found.
EvaluatorMozhenzhen
Tested modelDeepSeek V4 Flash
Providers聚光AI
Samples0
Duration11 sec
Test versionV11
Identity verdictNot verified
Verification basisOken
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.
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
模型列表没有看到该模型，长上下文专项无法继续验证。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths950K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance
模型列表没有看到该模型，长上下文专项无法继续验证。
Model authenticity score
Review API availability, model identity, response completeness, and other checks separately.
Scoring breakdown
Suspected impersonation / unavailable4/100
主要扣分项：基础调用不可用；模型列表不可见；存在Failed证据项。
Callability and model visibility0 / 10
基础调用不可用 -10
Protocol and response structure0 / 12
基础调用不可用 -12
Identity and model match0 / 18
基础调用不可用 -8模型列表不可见（模型列表可见性） -10
Core capabilities and model-specific tests1 / 25
基础调用不可用 -12模型列表不可见（模型列表可见性） -12
Usage and billing consistency0 / 10
基础调用不可用 -5模型列表不可见（模型列表可见性） -5
Reliability and availability3 / 25
基础调用不可用 -10模型列表不可见（模型列表可见性） -10存在Failed证据项 -2
Test details
Expand each check to view the redacted evidence notes.
27 checks
Model list visibility
接口模型列表中暂未看到 deepseek-v4-flash。
Failed
Test evidence
Check: Model list visibility
Status: Failed
Samples: 0
Needs review原因：模型列表不可见
