Alibaba Cloud's large model service platform Bailian announced that starting July 15, 2026, the billing unit price for the Fast mode model of the GLM-5.2 m...
行业动态IT之家(RSS)
Today AI Intelligence Brief
Alibaba Cloud's large model service platform Bailian announced that starting July 15, 2026, the
billing unit price for the Fast mode model of the GLM-5.2 model will be reduced by 20%. This mode is designed for output speed-sensitive scenarios, with TPS increased to 1.5~2 times that of standard APIs, reaching 80~100 TPS, suitable for AI streaming programming assistants, multi-step agent reasoning, real-time conversations, and more. Currently, it is the preview phase, charged by input and output tokens. When exceeding the TPM quota, requests to enter the queue are required. When calling, specify the model parameter as the corresponding model ID to enable it.
The readable text on this page was extracted from the public source and organized with attribution, publication time and the original link. Copyright remains with the original author and publisher.
Alibaba Cloud's large model service platform Bailian announced that starting July 15, 2026, the billing unit price for the Fast mode model of the GLM-5.2 m...
IT之家(RSS)2026-07-14T11:48:08.000Z
Scan to open this article
Aioga aggregates global AI updates and preserves source information for verification and citation.