Perplexity released a research preview of a model it post-trained from Chinese open-source AI model GLM 5.2 to fit its agent system, delivering performance comparable to Anthropic's Claude Opus 4.8 at about one-third of the cost. On July 9, blockchain outlet Decrypt reported the model coordinates tasks within Perplexity's computer environment and hands them off to Claude Opus 4.8 only when needed. Perplexity explained the cost is about 0.344 times that of Opus while delivering performance close to frontier-level, using a structure that does not use a high-cost model for every request. Perplexity applied an advisor tool to GLM 5.2 to distinguish tasks it can handle from those to pass to a stronger external model; GLM 5.2 handles most tasks, and only some high-difficulty tasks are transferred to Claude Opus 4.8. Based on Perplexity's internal efficiency metrics, the post-trained model with the advisor cost about twice as much to operate as the base GLM 5.2, but compared with processing all tasks with Opus 4.8, the cost was about 600 percent lower. GLM 5.2 has about 744 billion parameters and was released by Z.ai under an MIT license in June. The release is Perplexity's second post-training case involving a Chinese open-source model in the past 18 months. The new model runs on