wehub-resource-sync
11 lines
378 B
TOML
11 lines
378 B
TOML
base_model = "google/gemini-3.1-flash-lite-preview"
|
|
# Chat `reasoning_effort = low|medium|high`; `low` is the default.
|
|
# 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 = 0.25
|
|
output = 1.5
|
|
cache_read = 0.025
|
|
input_audio = 0.5
|