GitHub[195K]Try OpenCode

CompareAI models

  1. Kimi K3Moonshot
  2. Sonar Reasoning ProPerplexity
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K3100/100100/10013/10092/10050/100No data
Sonar Reasoning Pro100/100No data29/10019/10033/100No data
Overview
Author
Context length
1M
128K
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$3.00/ 1M
$2.00/ 1M
Output
$15/ 1M
$8.00/ 1M
Cached input
$0.30/ 1M
Unknown
MomentumLast 2 mo
Unique users
350K
No usage
Completed sessions
442,689
No usage
Token share
0.55%
No usage
Tokens
1.2T+100%
No usage
JUN 18AUG 12
No trend data

Related comparisons. Other model pairs to check.