Public model
DeepSeek
DeepSeek V4.1 Flash
The smallest model in DeepSeek's new architecture family, with thinking and non-thinking modes, tool calling and a 1M-token context.
deepseek-v4-1-flashAt a glance
Model details
- Context window
- 1M tokens
- Maximum output
- 128K tokens
- Modalities
- Text
Hosting and data handling
- No data kept by the model host
Saved chats are encrypted on your device. Prompts pass through Kalsenti and the model host to produce a reply.
Suggested starting points
- coding
One key. Every model.
Connect with the API format your code already uses.