The DeepSeek-Chat model is an advanced large language model designed for conversational interactions, boasting 67 billion parameters. It is trained on a vast dataset of 2 trillion tokens in both English and Chinese, enabling it to understand and generate human-like text with high accuracy and context awareness.

This model excels in handling complex conversational scenarios, logical reasoning, and multilingual support, making it ideal for applications such as customer service, interactive storytelling, and personalized recommendations. Supports various quantization methods (4-bit, 8-bit, and none) for efficient deployment on different hardware platforms, including NVIDIA, AMD GPUs, and Huawei Ascend NPUs. The model is available in both base and chat-tuned versions, with the latter optimized for dialogue and interaction.

‍

- The deepseek-chat model has been upgraded to DeepSeek-V3. deepseek-reasoner points to the new model DeepSeek-R1.
Source: https://api-docs.deepseek.com/quick_start/pricing