GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  2. Mistral Small 4Mistral
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/10087/10038/10082/1000/10044/100
Mistral Small 4100/10065/10074/10054/10033/10052/100
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$1.60/ 1M
$0.15/ 1M
Output
$3.20/ 1M
$0.60/ 1M
Cached input
$0.14/ 1M
$0.01/ 1M
MomentumLast 2 mo
Unique users
1.6M
No usage
Completed sessions
3,273,466
No usage
Token share
7.4%
No usage
Tokens
32T+36%
No usage
JUL 4AUG 28
No trend data
RetentionWeek 1
Returning users
65.8%140K user-weeks
Pending

Related comparisons. Other model pairs to check.