Unverified50% confidenceBenchmarkExact time
社区测出V4.1 Flash峰值达400 token/秒的速度，即便上下文拉到100万token速度也变化不大
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
Unverified在双Spark系统上，DeepSeek V4 Flash（FP8量化）峰值约每秒53个Token74% similarUnverifiedDeepSeek V4 Flash在OpenModel平台的速率限制为每分钟10次请求（10 RPM）和每分钟100K tokens（100K TPM）74% similarUnverified在Artificial Analysis的成本基准中，DeepSeek V4 Flash位于成本最低区间，速度约110 tokens/s70% similarUnverifiedDeepSeek Flash模型每秒token输出可达100多70% similarUnverified在双Spark系统上，GLM 5.3 Flash峰值约每秒46个Token69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/900398API
curl https://kongchang.com/api/v1/knowledge/claims/900398MCP
get_claim(id=900398)