Zhipu has released the new model GLM-5.3-FlashX today, with an officially stated maximum speed of 200 tokens per second, accelerating the experience for enterprise developers.
This high-speed version is based on the previously released GLM-5.3-Flash under the name "Ox Alpha" — it gained popularity among global developers with its superior intelligence at the same size, and its usage has been increasing rapidly. With demand growing too fast, Zhipu has continued to invest resources in Infra infrastructure and inference optimization on the computing power supported by 100,000 domestically-made chips. As a result, FlashX is not only fast but also holds all three cards — intelligence, price, and speed — at the same time for the first time.
