GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  2. Hy3Tencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/10087/10038/10082/1000/10044/100
Hy3100/10069/10075/10054/1000/100No data
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$1.60/ 1M
$0.14/ 1M
Output
$3.20/ 1M
$0.58/ 1M
Cached input
$0.14/ 1M
$0.04/ 1M
MomentumLast 2 mo
Unique users
1.6M
288K
Completed sessions
3,270,847
4,498,139
Token share
7.42%
1.28%
Tokens
32T+36%
5.5T+100%
JUL 4AUG 28
JUL 4AUG 28
RetentionWeek 1
Returning users
65.8%140K user-weeks
60.5%839 user-weeks

Related comparisons. Other model pairs to check.