wehub-resource-sync
16 lines
444 B
TOML
16 lines
444 B
TOML
base_model = "google/gemini-3-pro-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 = 2
|
|
output = 12
|
|
cache_read = 0.2
|
|
|
|
[[cost.tiers]]
|
|
tier = { type = "context", size = 200_000 }
|
|
input = 4
|
|
output = 18
|
|
cache_read = 0.4
|