base_model = "openai/gpt-5"
# Chat `reasoning_effort = minimal|low|medium|high`; Responses uses `reasoning.effort`.
# https://docs.databricks.com/aws/en/machine-learning/model-serving/query-reason-models (accessed 2026-06-25)
reasoning_options = [{ type = "effort", values = ["minimal", "low", "medium", "high"] }]

[cost]
input = 1.25
output = 10
cache_read = 0.125