14 lines
307 B
TOML
14 lines
307 B
TOML
base_model = "google/gemini-3.5-flash"
|
|
reasoning_options = [{ type = "effort", values = ["minimal", "low", "medium", "high"] }, { type = "budget_tokens", min = 256, max = 24_000 }]
|
|
|
|
[cost]
|
|
input = 1.5
|
|
output = 9
|
|
cache_read = 0.15
|
|
input_audio = 1.5
|
|
|
|
[limit]
|
|
context = 200_000
|
|
input = 128_000
|
|
output = 64_000
|