The model provider is the Sophnet platform. DeepSeek-R1-Distill-Qwen-7B is a distilled model based on the Qwen architecture, optimized for high reasoning speed and low cost. It achieves approximately 70% of the performance of the original model at the 7B scale, while reducing response latency by 40%, making it suitable for real-time interactive scenarios.
The API call cost is only one-quarter of the original Qwen-7B.
It supports streaming output, making it suitable for applications like chatbots.
It achieves an accuracy of over 65% on the GSM8K math task.
Pricing
- Input Tokens: $0.06 /M tokens
- Output Tokens: $0.12 /M tokens
Input Modalities
Try this model
Python