GitHub[220K]Try OpenCode

Compare AI models: DeepSeek V4 Flash vs Hy4 preview

  1. DeepSeek V4 FlashDeepSeek
  2. Hy4 previewTencentHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash26/10073/10077/10081/1000/1000/100
Hy4 preview50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder39/10087/1000/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.13/ 1M
$0.83/ 1M
Output
$0.26/ 1M
$2.50/ 1M
Cached input
$0.03/ 1M
$0.04/ 1M
MomentumLast 2 mo
Unique users
1.1M
46K
Completed sessions
17,144,953
115,232
Token share
3.92%
0.01%
Tokens
52T-82%
165B-26%
SEP 12NOV 6
SEP 12NOV 6
RetentionWeek 1
Returning users
60.3%88K user-weeks
48.5%1.1K user-weeks

Related comparisons. Other model pairs to check.