GitHub[150K]Try OpenCode

CompareAI models

  1. Kimi K2 Thinking TurboMoonshot
  2. Kimi K3Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2 Thinking Turbo100/100No data33/10061/1000/100No data
Kimi K3100/100No data16/10093/10060/100No data
Overview
Author
Context length
262K
1M
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$1.15/ 1M
$3.00/ 1M
Output
$8.00/ 1M
$15/ 1M
Cached input
$0.15/ 1M
$0.30/ 1M
MomentumLast 2 mo
Unique users
No usage
73K
Completed sessions
No usage
106,508
Token share
No usage
0.24%
Tokens
No usage
333B+100%
No trend data
MAY 27JUL 21

Related comparisons. Other model pairs to check.