Deepseek V2
DeepSeek, the creator of the DeepSeek V 2 model, has developed a chat model that excels at text generation, reasoning, and function calling, thanks to its comprehensive pretraining on a diverse 8.1 trillion token corpus and subsequent fine-tuning. Notably, the model features a Mixture-of-Experts architecture and has a context window of 131,072 tokens, allowing for efficient and effective processing of long inputs.
Input
Output
Context
131K
Max Output
-
Parameters
235.7B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek V2
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
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.