base_model = "sakana/fugu-ultra"
reasoning_options = [{ type = "effort", values = ["high", "xhigh"] }]

[limit]
output = 1_000_000

[cost]
input = 5
output = 30
cache_read = 0.5

[[cost.tiers]]
tier = { type = "context", size = 272_000 }
input = 10
output = 45
cache_read = 1

[provider]
shape = "responses"