wehub-resource-sync
10 lines
355 B
TOML
10 lines
355 B
TOML
base_model = "openai/gpt-5.4-nano"
|
|
# Chat `reasoning_effort = 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 = ["low", "medium", "high"] }]
|
|
|
|
[cost]
|
|
input = 0.2
|
|
output = 1.25
|
|
cache_read = 0.02
|