GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 FlashDeepSeek
  2. Hy3 previewTencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash100/10074/10081/10082/1000/100No data
Hy3 preview100/10045/10072/10054/1000/100No data
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.14/ 1M
$0.18/ 1M
Output
$0.28/ 1M
$0.60/ 1M
Cached input
$0.03/ 1M
$0.06/ 1M
MomentumLast 2 mo
Unique users
3.7M
10K
Completed sessions
19,305,035
1,028
Token share
60.4%
0%
Tokens
261T+86%
493M-84%
JUL 4AUG 28
JUL 4AUG 28
RetentionWeek 1
Returning users
68.7%354K user-weeks
Pending

Related comparisons. Other model pairs to check.