GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 Flash 0731DeepSeek
  2. Hy3Tencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash 07310/100100/10058/10082/1000/100No data
Hy3100/10069/10082/10054/1000/100No data
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.44/ 1M
$0.08/ 1M
Output
$1.32/ 1M
$0.33/ 1M
Cached input
$0.03/ 1M
$0.02/ 1M
MomentumLast 2 mo
Unique users
58K
316K
Completed sessions
745,531
5,495,886
Token share
0.53%
1.47%
Tokens
2.3T+100%
6.5T+100%
JUL 5AUG 29
JUL 5AUG 29
RetentionWeek 1
Returning users
Pending
60.5%839 user-weeks

Related comparisons. Other model pairs to check.