Unverified50% confidenceFactExact time
Kimi K3's Extra High and Max reasoning levels now use the max parameter, and the previously sent xhigh setting will be rejected by this model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/26/2026
First Seen
Valid until: 1/24/2027
Sources
Related Entities
Related Claims
UnverifiedCline CLI v3.0.74 changes Kimi K3's Extra High and Max tiers to use max reasoning effort instead of sending xhigh.78% similarUnverifiedKimi K3.1 Pro supports three reasoning effort levels: low, medium, and max.74% similarUnverifiedKimi's parameter count grew from 1T in K2 to 2.8T in K3.68% similarUnverifiedIn v4.1.23, for models such as Kimi K3 that only accept specific reasoning levels, Cline automatically selects the closest level supported by that model.66% similarPartially VerifiedBoth Qwen 3 Max and DeepSeek-V3 adopt the MoE architecture with total parameter counts reaching hundreds of billions, but the parameters actually activated during inference are only a small fraction of the total.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098916API
curl https://kongchang.com/api/v1/knowledge/claims/1098916MCP
get_claim(id=1098916)