← model directory
deepseek
DeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
↓ runs free on your own hardware⚙ tool calling
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....
specs & pricing
- Type
- text
- Provider
- deepseek
- Model ID
- deepseek/deepseek-v4-flash-0731
- Capabilities
- tools, reasoning
- Context window
- 1.3M tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.15 / 1M tokens
- Output price
- $0.31 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.