GitHub[195K]Try OpenCode

CompareAI models

  1. Qwen3.8 MaxAlibaba
  2. Kimi K2 Thinking TurboMoonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.8 Max100/100No data31/10082/10067/100No data
Kimi K2 Thinking Turbo100/100No data28/10064/1000/100No data
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text, Image, Video, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$1.15/ 1M
Output
$6.00/ 1M
$8.00/ 1M
Cached input
$0.25/ 1M
$0.15/ 1M
MomentumLast 2 mo
Unique users
53K
No usage
Completed sessions
38,204
No usage
Token share
0.04%
No usage
Tokens
109B+100%
No usage
JUN 21AUG 15
No trend data

Related comparisons. Other model pairs to check.