GitHub[195K]Try OpenCode

CompareAI models

  1. MiniMax-M2.5MiniMax
  2. Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
MiniMax-M2.5100/10051/10063/10049/1000/100No data
Kimi K2.5100/10020/10043/10064/10050/100No data
Overview
Author
Context length
205K
262K
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.30/ 1M
$0.60/ 1M
Output
$1.20/ 1M
$3.00/ 1M
Cached input
$0.03/ 1M
$0.10/ 1M
MomentumLast 2 mo
Unique users
34K
63K
Completed sessions
1,418
2,500
Token share
0.01%
0.01%
Tokens
33B-99%
46B-87%
JUL 2AUG 26
JUL 2AUG 26
RetentionWeek 1
Returning users
66.8%364 user-weeks
72.9%929 user-weeks

Related comparisons. Other model pairs to check.