DeepSeek V4 Flash 0731
DeepSeekwww.deepseek.com
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....
long-contextopen-weightslow-cost
- Input price
- $0.04 / 1M tokens
- Output price
- $0.30 / 1M tokens
- Context window
- 1.05M tokens
- Max output
- 944K tokens
- Output speed
- 127 tokens/s
- Time to first token
- 1.66s
- Inputs
- text
- Open weights
- Yes
- OpenRouter id
deepseek/deepseek-v4-flash-0731- Listed
- Jul 31, 2026
Benchmarks
Intelligence Indexn/a
Engineering Indexn/a
Speed and benchmarks for “DeepSeek V4 Flash 0731 (Max)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.