GitHub[195K]Try OpenCode

CompareAI models

  1. Kimi K2.5Moonshot
  2. Kimi K2.6Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2.5100/10020/10043/10063/10050/100No data
Kimi K2.6100/10079/10037/10063/10050/10033/100
Overview
Author
Context length
262K
262K
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.60/ 1M
$0.95/ 1M
Output
$3.00/ 1M
$4.00/ 1M
Cached input
$0.10/ 1M
$0.16/ 1M
MomentumLast 2 mo
Unique users
51K
198K
Completed sessions
8,451
203,032
Token share
0.01%
0.08%
Tokens
32B-83%
483B-76%
JUL 20SEP 13
JUL 20SEP 13
RetentionWeek 1
Returning users
70.7%834 user-weeks
64.8%8.9K user-weeks

Related comparisons. Other model pairs to check.