GitHub[195K]Try OpenCode

CompareAI models

  1. Llama 4 Scout 17B InstructMeta
  2. Kimi K2.7 CodeMoonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Llama 4 Scout 17B Instruct0/100No data72/100100/10033/100No data
Kimi K2.7 Code100/100No data37/10064/10050/100No data
Overview
Author
Context length
3.5M
262K
Reasoning
False
True
Input modalities
Text, Image
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.18/ 1M
$0.95/ 1M
Output
$0.59/ 1M
$4.00/ 1M
Cached input
Unknown
$0.19/ 1M
MomentumLast 2 mo
Unique users
No usage
342K
Completed sessions
No usage
555,333
Token share
No usage
0.56%
Tokens
No usage
2.5T+56%
No trend data
JUL 6AUG 30
RetentionWeek 1
Returning users
Pending
61.9%26K user-weeks

Related comparisons. Other model pairs to check.