Back to Models

DeepSeek: DeepSeek V4.1 Flash

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...

Modalities

Input

textimage

Output

text
Pricing
Cost per 1 million tokens
Input
$0.36
Output
$1.44
Model Specs
Context Window
1,048,576
Max Output
943,718
Release Date
2026-09-10
Knowledge Cutoff
2025-05
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-09-10

Provider: