name = "GLM-4.7-FlashX"
description = "Efficient GLM model for fast reasoning, coding, and agent workflows"
family = "glm-flash"
release_date = "2026-01-19"
last_updated = "2026-01-19"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true

[[reasoning_options]]
type = "toggle"

[cost]
input = 0.07
output = 0.40
cache_read = 0.01
cache_write = 0

[limit]
context = 200_000
output = 131_072

[modalities]
input = ["text"]
output = ["text"]