DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token). It incorporates large-scale reinforcement learning (RL) to enhance its chain-of-thought and reasoning capabilities, delivering strong performance in math, code, and multi-step reasoning tasks.
发布日期2025年1月20日
参数规模1.8B
上下文长度—
许可证MIT
知识截止—
Benchmarks
评测成绩
Pricing
API 价格对比
暂无 API 价格。