wehub-resource-sync
10 lines
340 B
TOML
10 lines
340 B
TOML
base_model = "zhipuai/glm-5.2"
|
|
# Chat `reasoning_effort = low|medium|high`; `medium` is the default.
|
|
# https://docs.databricks.com/aws/en/machine-learning/model-serving/query-reason-models (accessed 2026-07-11)
|
|
reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
|
|
|
|
[cost]
|
|
input = 1.4
|
|
output = 4.4
|
|
cache_read = 0.26
|