← All models
Deepseek · Multimodal
DeepSeek: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Open-weightIn: Text, ImageOut: Text
Input / M
$0.05 / M
Output / M
$0.57 / M
Cache read / M
$0.02 / M
Context
1M
Released
Sep 10, 2026