19 lines
383 B
TOML
19 lines
383 B
TOML
base_model = "google/gemini-3.1-pro-preview"
|
|
reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }, { type = "budget_tokens", min = 256, max = 32_000 }]
|
|
|
|
[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
|
|
|
|
[limit]
|
|
context = 1_000_000
|
|
input = 936_000
|
|
output = 64_000
|