GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  2. Llama 4 Maverick 17B InstructMeta
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/10087/10039/10081/1000/10044/100
Llama 4 Maverick 17B Instruct0/10013/10071/10081/10033/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
False
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$1.74/ 1M
$0.27/ 1M
Output
$3.48/ 1M
$0.85/ 1M
Cached input
$0.14/ 1M
Unknown
MomentumLast 2 mo
Unique users
1.4M
No usage
Completed sessions
4,184,888
No usage
Token share
13.4%
No usage
Tokens
29T+65%
No usage
JUN 18AUG 12
No trend data

Related comparisons. Other model pairs to check.