GitHub[220K]Try OpenCode

Compare AI models: DeepSeek V4 Flash vs Hy4

  1. DeepSeek V4 FlashDeepSeek
  2. Hy4TencentHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash26/10073/10076/10081/1000/1000/100
Hy450/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder52/10092/10033/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.14/ 1M
$0.46/ 1M
Output
$0.28/ 1M
$1.39/ 1M
Cached input
$0.0028/ 1M
$0.02/ 1M
MomentumLast 2 mo
Unique users
1.2M
1.7K
Completed sessions
17,999,818
6,240
Token share
4.15%
0%
Tokens
55T-81%
11B+100%
SEP 11NOV 5
SEP 11NOV 5
RetentionWeek 1
Returning users
60.3%88K user-weeks
Pending

Related comparisons. Other model pairs to check.