GLM 4.6 Turbo

glmReasoningOpen Weights

Fast variant of GLM 4.6 for general chat, coding, and analysis with improved latency and strong reasoning.

Providers2

ReleasedOct 2, 2025

Input Modalitiestext

Output Modalitiestext

Available Providers (2)

Provider	Model ID	Input Cost	Output Cost	Context	Max Output	Docs
NanoGPT	`z-ai/GLM-4.6-turbo`	$1/MTok	$3/MTok	204.8K	131.1K
NanoGPT	`z-ai/GLM-4.6-turbo:thinking`	$1/MTok	$3/MTok	204.8K	131.1K

Reasoning

Tool Calling

Attachments

Open Weights

Structured Output