TPSTokens Per Second

GLM 5 Turbo

Zhipu AI🇨🇳 China
active

Fast inference variant of GLM 5 optimized for agent-driven environments. Deeply optimized for real-world agent workflows involving long execution chains with improved complex reasoning.

Compare with other models →
Context window203K tokens
Input / 1M tokens$0.96
Output / 1M tokens$3.2

Version History

glm-5-turbo-2026-03-15major

GLM 5 Turbo launches with 203K context and fast inference optimized for agent-driven environments. Improved complex reasoning over base GLM 5 at $0.96/$3.20 per 1M tokens.