Zhipu Releases GLM-5.1 High-Speed API with Output Speed of 400 Tokens/s

Odaily Planet Daily reports that Zhipu has launched the GLM-5.1 high-speed API for select enterprise clients, achieving a model output speed of 400 tokens/s, setting a new global record for end-to-end speed in official large model interfaces. It is understood that this high-speed version retains the capabilities of the flagship model and is powered by a high-performance inference engine jointly developed by Zhipu and the TileRT team. This engine reconstructs the GPU runtime scheduling mechanism, statically orchestrating the model into a persistent Engine Kernel resident on the GPU to reduce kernel startup and memory read/write latency in traditional inference processes. In multi-card scenarios, TileRT further specializes GPU nodes in the 8-card NVL topology into different functional Workers to enhance attention layer computation and cross-card communication efficiency. Currently, this high-speed version service has been made available to select enterprise clients on Zhipu's MaaS platform. In the future, it will continue to optimize FP8 inference and ultra-long context capabilities, providing support for low-latency scenarios such as AI programming, real-time interaction, and real-time speech.