GitHub[150K]Try OpenCode

CompareAI models

  1. Llama 4 Maverick 17B InstructMeta
  2. Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Llama 4 Maverick 17B Instruct0/10013/10072/10082/10040/100No data
Kimi K2.5100/10020/10060/10061/10040/100No data
Overview
Author
Context length
1M
262K
Reasoning
False
True
Input modalities
Text, Image
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.27/ 1M
$0.30/ 1M
Output
$0.85/ 1M
$1.90/ 1M
Cached input
Unknown
Unknown
MomentumLast 2 mo
Unique users
No usage
59K
Completed sessions
No usage
68,065
Token share
No usage
0.22%
Tokens
No usage
281B-70%
No trend data
MAY 20JUL 14

Related comparisons. Other model pairs to check.