GitHub[150K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  2. MiniMax-M2.5MiniMax
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/10089/10070/10082/1000/10044/100
MiniMax-M2.5100/10056/10067/10046/1000/100No data
Overview
Author
Context length
1M
205K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.43/ 1M
$0.30/ 1M
Output
$0.87/ 1M
$1.20/ 1M
Cached input
$0.003625/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
1.2M
41K
Completed sessions
4,331,019
50,823
Token share
22.4%
0.1%
Tokens
29T+353%
134B-63%
MAY 20JUL 14
MAY 20JUL 14

Related comparisons. Other model pairs to check.