GitHub[150K]Try OpenCode

CompareAI models

  1. Kimi K2.5Moonshot
  2. Sonar Reasoning ProPerplexity
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2.5100/10020/10060/10061/10040/100No data
Sonar Reasoning Pro100/100No data30/10015/10040/100No data
Overview
Author
Context length
262K
128K
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.30/ 1M
$2.00/ 1M
Output
$1.90/ 1M
$8.00/ 1M
Cached input
Unknown
Unknown
MomentumLast 2 mo
Unique users
59K
No usage
Completed sessions
68,065
No usage
Token share
0.22%
No usage
Tokens
281B-70%
No usage
MAY 20JUL 14
No trend data

Related comparisons. Other model pairs to check.