GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction. Users can control the reasoning behaviour with the reasoningenabled boolean. Learn more in our docs
Z.AI: GLM 4.5 Air (free) – Recent Activity and Usage Stats | OpenRouter
Recent activity on GLM 4.5 Air (free)
Total usage per day on OpenRouter
Prompt
1.96B
Reasoning
48.3M
Completion
32.5M
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.