

DeepSeek-R1 (Groq)
The deep reasoning DeepSeek-R1 running on Groq
Model Specifications
Default Parameters
Supported Parameters
Temperature
SupportedControls randomness: Lower values make output more deterministic, higher values more creative.
More models from DeepSeek

DeepSeek V3.1 Terminus
A large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. USA hosted, it improves tool use, code generation, and reasoning efficiency.

DeepSeek V3.2 Exp
An experimental model hosted in the US introducing DeepSeek Sparse Attention for training and inference efficiency in long-context scenarios.

DeepSeek V3.1
DeepSeek's updated V3.1 model releasedhosted securely in the USA