About 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.
Specifications
- Provider
- DeepSeek
- Context Length
- 1,048,576 tokens
- Input Types
- text
- Output Types
- text
- Category
- deepseek/deepseek-v4-flash-20260731
- Added
- 7/31/2026