wehub-resource-sync
36 lines
745 B
TOML
36 lines
745 B
TOML
# Opt in with chat_template_args.enable_thinking=true. Baseten documents no
|
|
# explicit false behavior, effort values, or reasoning-token budget.
|
|
# https://docs.baseten.co/inference/model-apis/reasoning
|
|
|
|
name = "GLM 4.7"
|
|
description = "Flagship GLM model for hybrid reasoning, coding, and agentic engineering"
|
|
family = "glm"
|
|
release_date = "2025-12-22"
|
|
last_updated = "2025-12-22"
|
|
attachment = false
|
|
reasoning = true
|
|
temperature = true
|
|
tool_call = true
|
|
structured_output = true
|
|
knowledge = "2025-04"
|
|
open_weights = true
|
|
|
|
[[reasoning_options]]
|
|
type = "toggle"
|
|
|
|
[interleaved]
|
|
field = "reasoning_content"
|
|
|
|
[cost]
|
|
input = 0.6
|
|
output = 2.2
|
|
cache_read = 0.12
|
|
|
|
[limit]
|
|
context = 200_000
|
|
output = 200_000
|
|
|
|
[modalities]
|
|
input = ["text"]
|
|
output = ["text"]
|