GitHub[195K]Try OpenCode

CompareAI models

  1. Kimi K2.7 CodeMoonshot
  2. GPT-5.6 LunaOpenAI
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2.7 Code100/100No data38/10062/10050/100No data
GPT-5.6 Luna37/10081/10066/10098/10050/10069/100
Overview
Author
Context length
262K
1.1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image, Pdf
Output modalities
Text
Text
Providers
Pricing
Input
$0.95/ 1M
$0.20/ 1M
Output
$4.00/ 1M
$1.20/ 1M
Cached input
$0.19/ 1M
$0.02/ 1M
MomentumLast 2 mo
Unique users
290K
512K
Completed sessions
434,416
1,187,708
Token share
0.37%
1.17%
Tokens
2T-15%
6.3T+100%
JUL 17SEP 10
JUL 17SEP 10
RetentionWeek 1
Returning users
61%23K user-weeks
57.1%34K user-weeks

Related comparisons. Other model pairs to check.