GitHub[220K]Try OpenCode

Compare AI models: DeepSeek V4.1 Flash vs Hy3 preview

  1. DeepSeek V4.1 FlashDeepSeek
  2. Hy3 previewTencentHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4.1 Flash100/100100/10056/10082/10033/10092/100
Hy3 preview50/100 — Reasoning supported; no comparable benchmark45/10067/10053/1000/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text, Image
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.30/ 1M
$0.18/ 1M
Output
$1.20/ 1M
$0.60/ 1M
Cached input
$0.006/ 1M
$0.06/ 1M
MomentumLast 2 mo
Unique users
3.5M
0
Completed sessions
90,376,864
9,900
Token share
33.6%
0%
Tokens
385T+100%
0-100%
AUG 30OCT 24
No trend data
RetentionWeek 1
Returning users
68.9%318K user-weeks
Pending

Related comparisons. Other model pairs to check.