Zhipu AI launches GLM-5.3-FlashX with 200 tokens/s inference speed

Zhipu AI (智谱) has released GLM-5.3-FlashX, which is now available via its API and experience center. The company claims the model achieves inference speeds of up to 200 tokens/s, supported by 100,000 domestic chips and infrastructure optimizations. The underlying model, GLM-5.3-Flash, was open-sourced on August 26 with 320 billion total parameters and a 1-million-token context window.