Model
GLM 5.3 High Speed
A high-speed large language model introduced by Zhipu AI, focused on high-throughput inference and supporting rapid token generation.
Timeline (last 90 days)
Oct 13
Zhipu's GLM 5.3 High Speed version has started gray-scale testing, with users measuring nearly 500 tokens per second and a first-token latency of under 5 seconds; it currently uses a random distribution mechanism and is not yet fully open.
Unverified50%