GitHub[208K]Try OpenCode

CompareAI models

  1. Jamba MiniAi21
  2. DeepSeek V4 Flash Vision ExpDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Jamba Mini0/100No data77/10052/1000/100No data
DeepSeek V4 Flash Vision Exp100/100No data72/10081/10033/100No data
Overview
Author
Context length
256K
1M
Reasoning
False
True
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.20/ 1M
$0.15/ 1M
Output
$0.40/ 1M
$0.60/ 1M
Cached input
Unknown
$0.003/ 1M
MomentumLast 2 mo
Unique users
No usage
268K
Completed sessions
No usage
610,789
Token share
No usage
1.01%
Tokens
No usage
6.8T+100%
No trend data
JUL 25SEP 18
RetentionWeek 1
Returning users
Pending
69.6%14K user-weeks

Related comparisons. Other model pairs to check.