Agent Serve currently tracks 14 Z.ai models including GLM 5.3, GLM 5.3 Flash, GLM 5.2, GLM 5.1, GLM 5, GLM 5 Turbo, and more.
GLM 4.6 is the default Z.ai model in Agent Serve.
GLM 4.7 Flashx currently has the lowest listed input price at $0.07/1M tokens.
GLM 5.3 currently has the largest listed context window at 1M tokens.
All Z.ai models in Agent Serve support tool use and function calling, allowing agents to invoke external APIs, query databases, and run custom actions.
