Compare AI models: DeepSeek V4.1 Flash vs Hy3 preview
- DeepSeek V4.1 FlashDeepSeek
- Hy3 previewTencentHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
| Model | Reasoning | Coding | Cost efficiency | Context window | Multimodal | Tool use |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 100/100 | 100/100 | 72/100 | 81/100 | 33/100 | 92/100 |
| Hy3 preview | 50/100 — Reasoning supported; no comparable benchmark | 45/100 | 67/100 | 53/100 | 0/100 | 50/100 — 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
$0.14/ 1M
$0.18/ 1M
Output
$0.42/ 1M
$0.60/ 1M
Cached input
$0.0042/ 1M
$0.06/ 1M
MomentumLast 2 mo
Unique users
2.7M
0
Completed sessions
58,954,451
10,059
Token share
27.2%
0%
Tokens
281T+100%
0-100%
AUG 25OCT 19
No trend data
RetentionWeek 1
Returning users
68.5%317K user-weeks
Pending