**GLM-5.3-FlashX: Delivering inference speeds of 200 tokens/s** > On this page

**GLM-5.3-FlashX: Delivering inference speeds of 200 tokens/s**

> On this page Model Overview How to Use Model API GLM Coding Plan Capabilities Best Practices Key Advancements Competitive Performance at Flash Cost Architecture for Extreme Efficiency Visual Intelligence in the Coding Loop Beyond Coding — Your Partner at Work Serving at Scale on Chinese AI Chips Conclusion Models GLM-5.3-Flash/FlashX Copy page Copy page Copy page Copy page GLM-5.3-Flash is now fully available on the...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-19 01:04（北京时间）
- **原文**：[打开原文](https://docs.z.ai/guides/vlm/glm-5.3-flash)