14 lines
333 B
TOML
14 lines
333 B
TOML
base_model = "google/gemini-2.5-pro"
|
|
reasoning_options = [{ type = "effort", values = ["minimal", "low", "medium", "high"] }, { type = "budget_tokens", min = 128, max = 32_768 }]
|
|
|
|
[cost]
|
|
input = 1.25
|
|
output = 10
|
|
cache_read = 0.125
|
|
|
|
[[cost.tiers]]
|
|
tier = { type = "context", size = 200_000 }
|
|
input = 2.5
|
|
output = 15
|
|
cache_read = 0.25
|