wehub-resource-sync
20 lines
580 B
TOML
20 lines
580 B
TOML
base_model = "openai/gpt-5.4"
|
|
# Chat `reasoning_effort = low|medium|high`; Responses uses `reasoning.effort`.
|
|
# 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 = 2.5
|
|
output = 15
|
|
cache_read = 0.25
|
|
|
|
[[cost.tiers]]
|
|
tier = { type = "context", size = 272_000 }
|
|
input = 5
|
|
output = 22.5
|
|
cache_read = 0.5
|
|
|
|
[experimental.modes.fast]
|
|
cost = { input = 5, output = 30, cache_read = 0.5 }
|
|
provider = { body = { service_tier = "priority" } }
|