DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
The figures
- Made by
- DeepSeek
- Model ID
- deepseek/deepseek-v4-flash-0731
- Input
- $0.012 per million tokens
- Output
- $1.28 per million tokens
- Context window
- 1.05M tokens
- Longest answer
- 944K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 31 Jul 2026
Read on 3 Oct 2026.