deepseek-ai/deepseek-r1

A reasoning model trained with reinforcement learning, on par with OpenAI o1

Input
Configure the inputs for the AI model.
0
100

Top-p (nucleus) sampling

Prompt

0
100

The maximum number of tokens the model should generate as output.

0
100

The value used to modulate the next token probabilities.

0
100

Presence penalty

0
100

Frequency penalty

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.