Deepseek R1 Zero
DeepSeek R 1 Zero is a chat model developed by DeepSeek, exceling at reasoning and chain-of-thought tasks through its unique training via large-scale reinforcement learning without supervised fine-tuning. This approach enables the model to generate long chains of thought and demonstrate self-verification and reflection capabilities.
Input
Output
Context
131K
Max Output
-
Parameters
684.5B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output TokensNot available
Parameters684.5B
Release DateJan 20, 2025
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.