Alibaba Cloud has made an announcement stating that, in a bid to refine resource allocation and bolster service reliability, the default API call rate limit for the Bailian Multimodal Interaction Development Kit on its large-scale model service platform will be revised to 10 Queries Per Second (QPS) starting from April 28, 2026. This updated limit will enable the creation of 600 new sessions per minute and 36,000 new sessions per hour, adequately catering to the requirements of the majority of development, debugging, and routine business operations. Notably, customers who have previously requested adjustments to their rate limits will remain unaffected by this change.
