Operating as a TEE-backed AI infrastructure, Phala Confidential AI has processed a combined total of 50.72 billion billed input and output tokens over the course of the previous 24 hours.
When reviewing the most utilized offerings during this period, z-ai/glm-5.3-flash led the group by generating 54.28% of the traffic. The second most popular option was deepseek/deepseek-v4-flash with a 17.77% share, closely followed by z-ai/glm-5.3, which accounted for 7.01% of the total usage.
Feel free to explore the top performing model directly by visiting the following link:
https://phala.com/models/z-ai/glm-5.3-flash
When reviewing the most utilized offerings during this period, z-ai/glm-5.3-flash led the group by generating 54.28% of the traffic. The second most popular option was deepseek/deepseek-v4-flash with a 17.77% share, closely followed by z-ai/glm-5.3, which accounted for 7.01% of the total usage.
Feel free to explore the top performing model directly by visiting the following link:
https://phala.com/models/z-ai/glm-5.3-flash
