base_model = "zhipuai/glm-5.2" # Chat `reasoning_effort = low|medium|high`; `medium` is the default. # https://docs.databricks.com/aws/en/machine-learning/model-serving/query-reason-models (accessed 2026-07-11) reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }] [cost] input = 1.4 output = 4.4 cache_read = 0.26