name = "GLM Zero Preview"
description = "Compact GPT model for low-latency assistance and high-volume workloads"
release_date = "2024-12-01"
last_updated = "2024-12-01"
attachment = false
reasoning = false
tool_call = false
structured_output = false
open_weights = false

[cost]
input = 1.802
output = 1.802

[limit]
context = 8_000
input = 8_000
output = 4_096

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