Unverified50% confidenceFactExact time
WorldofAI measured V4.1 Flash 1017's generation speed at about 244 tokens per second, with early tests approaching 300 tokens per second.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/20/2026
First Seen
Valid until: 11/3/2026
Sources
DeepSeek V4.1 Flash Hands-On: Open-Source Model Nears Closed-Source Flagships
bilibiliubilier10/20/2026
Related Entities
Related Claims
UnverifiedThe community measured V4.1 Flash reaching a peak speed of 400 tokens/second, with little change in speed even when the context is extended to 1 million tokens.79% similarUnverifiedIn a 3D city generator test, V4.1 Flash achieved an output speed of 287 tokens per second, with a total completion time of 83 minutes.78% similarUnverifiedIn an online Excel application test, V4.1 Flash generated 386 tokens per second with a cache hit rate as high as 99%.75% similarVerifiedV4.1 Flash activates only 8 billion parameters during the input stage and 16 billion parameters during the output stage.72% similarUnverifiedThe DeepSeek Flash model can output more than 100 tokens per second.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1077067API
curl https://kongchang.com/api/v1/knowledge/claims/1077067MCP
get_claim(id=1077067)