wehub-resource-sync
14 lines
489 B
TOML
14 lines
489 B
TOML
base_model = "openai/gpt-5.4-mini"
|
|
# 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 = 0.75
|
|
output = 4.5
|
|
cache_read = 0.075
|
|
|
|
[experimental.modes.fast]
|
|
cost = { input = 1.5, output = 9, cache_read = 0.15 }
|
|
provider = { body = { service_tier = "priority" } }
|