Yi-Lightning
零一万物 released the 文本 model · Launched on 2024-10
Commercial Closed-source
文本
闭源
API 可用
模型简介
Yi-Lightning is a high-speed large model launched by 01.AI, adopting a MoE architecture, achieving extremely low inference latency while maintaining high-quality output. It is known for fast response on the LMArena leaderboard and performs particularly well in Chinese scenarios. Yi-Lightning is positioned as cost-effective, suitable for real-time dialogue and customer service scenarios requiring quick responses.
核心特性
- 极低延迟
- MoE 高效架构
- 128K 上下文
- 中文优化
核心优势
- 响应速度极快
- 中文能力强
- 性价比高
技术规格
参数量
未公开（MoE）
上下文窗口
128K tokens
API 支持
Yes
开源状态
Closed Source
发布日期
2024-10
提供商
零一万物
价格信息
输入 ¥0.99/1M tokens，输出 ¥0.99/1M tokens
基准测试
LMArena 速度排名前列，在中文快速响应场景中表现优异