anomalyco--models.dev
wehub-resource-sync
24 行
639 B
TOML
24 行
639 B
TOML
# Toggle: $.chat_template_kwargs.enable_thinking = true|false (default true).
|
|
# Effort: $.reasoning_effort or $.chat_template_kwargs.reasoning_effort is
|
|
# "max" (default) or "high"; effort has no effect when thinking is disabled.
|
|
# https://docs.getlilac.com/inference/chat-completions#reasoning (accessed 2026-06-25)
|
|
base_model = "zhipuai/glm-5.2"
|
|
name = "GLM 5.2"
|
|
reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["high", "max"] }]
|
|
|
|
[interleaved]
|
|
field = "reasoning_content"
|
|
|
|
[cost]
|
|
input = 0.9
|
|
output = 3
|
|
cache_read = 0.27
|
|
|
|
[limit]
|
|
context = 524_288
|
|
output = 524_288
|
|
|
|
[modalities]
|
|
input = ["text"]
|
|
output = ["text"]
|