Unverified50% confidenceReleaseExact time
DeepSeek introduced a 'controllable reasoning intensity' integer parameter, allowing users to set a value from 1 to 100 in API requests to trade off between reasoning cost and accuracy.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/22/2026
First Seen
Valid until: 12/21/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek Pro's 1.6T total parameters with 49B activated parameters result in inference costs comparable to a roughly 49B dense model, while expanding knowledge capacity by approximately 32 times.73% similarUnverifiedThinking Level in DeepSeek models is a capability that allows callers to control how much reasoning the model performs before generating a response, representing a practical application of Test-Time Compute Scaling.70% similarUnverifiedTopping up 10 Chinese yuan is sufficient to meet daily programming assistance needs using the DeepSeek API.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/941028API
curl https://kongchang.com/api/v1/knowledge/claims/941028MCP
get_claim(id=941028)