Unverified50% confidenceCautionExact time
DeepSeek V4.1 Flash 1017 still consumes about 25 reasoning tokens when reasoning_effort is set to none, so it is not a true non-thinking mode.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4.1 Flash offers two reasoning levels, Hide and Max, with the Max mode's thinking process being excessively lengthy.77% similarUnverifiedDeepSeek V4.1 Flash has a shortcoming in combinatorial mathematical reasoning with strict constraints, struggling to precisely track the number of times each digit is used.77% similarVerifiedDeepSeek V4.1 Flash adopts a Causal Encoder-Decoder asymmetric architecture with a total parameter count of 552B.76% similarUnverifiedUnder the Messages protocol, DeepSeek V4.1 Flash 1017 requests without an effort level set do not return a thinking block, and the effort level must be set explicitly.76% similarUnverifiedDeepSeek V4.1 Flash has 40 layers in total: the first 20 are a causal encoder activating 8 billion parameters for understanding sentence meaning, and the last 20 are a decoder activating 16 billion parameters for predicting the next token.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067158API
curl https://kongchang.com/api/v1/knowledge/claims/1067158MCP
get_claim(id=1067158)