GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V3.2DeepSeek
  2. DeepSeek V4 Flash Vision ExpDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V3.2100/100No data75/10019/1000/100No data
DeepSeek V4 Flash Vision Exp100/100No data71/10082/10033/100No data
Overview
Author
Context length
128K
1M
Reasoning
True
True
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.27/ 1M
$0.22/ 1M
Output
$0.40/ 1M
$0.66/ 1M
Cached input
$0.13/ 1M
$0.007/ 1M
MomentumLast 2 mo
Unique users
No usage
105K
Completed sessions
No usage
151,581
Token share
No usage
0.67%
Tokens
No usage
3T+100%
No trend data
JUL 5AUG 29
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.