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...
The figures
- Made by
- DeepSeek
- Model ID
- deepseek/deepseek-v4.1-flash
- Input
- $0.3 per million tokens
- Output
- $1.2 per million tokens
- Context window
- 1.05M tokens
- Longest answer
- 944K tokens
- Takes in
- text, image
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 10 Sept 2026
Read on 3 Oct 2026.