Understand this story
Alibaba Cloud Developer Community AI published a hands-on test article on October 27, 2026, stating that on Alibaba Cloud Bailian 2.5.0, web search can be enabled by declaring web_search through the tools parameter. The article records that for "today's weather in Shanghai," the model changed from refusing to answer in 9.2 seconds to returning the day's actual conditions in 24.5 seconds and writing the date correctly; after adding web_extractor, the model could decide on its own the number of retrieval rounds and the scraping targets, and the counts of two web_search calls and three web_extractor calls in the JSON output matched the item-by-item records. The article also records that web-enabled call latency ranged from 17 to 127 seconds, with 22,789 tokens per single input, and notes that agent and agent_max strategies other than turbo incur an additional charge per call. Currently this hands-on test is a single source, with no subsequent developments yet.
AI-generated from public reports
Developments
1 confirmed developments
The author tested that the Bailian model enables web search via the tools parameter
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 27
Alibaba Cloud Developer Community AI
Hands-on test of Alibaba Cloud Bailian's built-in web search and web scraping: enable with a one-line tools declaration
The author tested on Alibaba Cloud Bailian 2.5.0. After declaring web_search via the tools parameter, the model went from refusing to answer "today's weather in Shanghai" in 9.2 seconds to returning the day's actual conditions in 24.5 seconds with the correct date. Adding web_extractor lets the model decide the number of retrieval rounds and scraping targets on its own; in the JSON output, the counts of two web_search calls and three web_extractor calls match the per-call records. The author also recorded web-enabled call latency ranging from 17 to 127 seconds and 22,789 input tokens in a single call, and notes that the agent and agent_max strategies other than turbo incur an additional charge per call.