wehub-resource-sync
27 lines
641 B
TOML
27 lines
641 B
TOML
# Model-specific reasoning HTTP values (accessed 2026-06-28):
|
|
# reasoning.enabled=false disables reasoning; reasoning_effort accepts low/medium/high/xhigh.
|
|
# Sources:
|
|
# https://docs.deepinfra.com/api-reference/chat-completions/openai-chat-completions
|
|
# https://deepinfra.com/zai-org/GLM-5.2/api
|
|
# https://deepinfra.com/docs/advanced/max_tokens_limit
|
|
base_model = "zhipuai/glm-5.2"
|
|
|
|
[interleaved]
|
|
field = "reasoning_content"
|
|
|
|
[[reasoning_options]]
|
|
type = "toggle"
|
|
|
|
[[reasoning_options]]
|
|
type = "effort"
|
|
values = ["low", "medium", "high", "xhigh"]
|
|
|
|
[cost]
|
|
input = 0.93
|
|
output = 3
|
|
cache_read = 0.18
|
|
|
|
[limit]
|
|
context = 1_048_576
|
|
output = 32_768
|