GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 Pro 0813DeepSeek
  2. Kimi K3Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro 0813100/100No data36/10081/1000/100No data
Kimi K3100/100100/10012/10093/10050/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$1.32/ 1M
$3.00/ 1M
Output
$3.96/ 1M
$15/ 1M
Cached input
$0.04/ 1M
$0.30/ 1M
MomentumLast 2 mo
Unique users
No usage
649K
Completed sessions
No usage
811,914
Token share
No usage
0.35%
Tokens
No usage
1.9T+294,792%
No trend data
JUL 17SEP 10
RetentionWeek 1
Returning users
Pending
45.5%85K user-weeks

Related comparisons. Other model pairs to check.