GitHub[150K]Try OpenCode

CompareAI models

  1. DeepSeek V4 Flash 0731DeepSeek
  2. Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash 0731100/100No data87/10080/1000/100No data
Kimi K2.5100/10020/10047/10061/10050/100No data
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.09/ 1M
$0.60/ 1M
Output
$0.18/ 1M
$3.00/ 1M
Cached input
$0.02/ 1M
$0.10/ 1M
MomentumLast 2 mo
Unique users
No usage
59K
Completed sessions
No usage
16,945
Token share
No usage
0.08%
Tokens
No usage
120B-85%
No trend data
JUN 8AUG 2

Related comparisons. Other model pairs to check.