Z.ai: GLM 4.5 Air API
The compact variant of Z.ai's flagship model, featuring 106B total parameters (12B active). It unifies reasoning, coding, and agentic capabilities with a "Thinking Mode," offering a high-efficiency alternative to the 355B full model while maintaining SOTA performance in tool-use and coding.
- Context window: 131,072 tokens
- Max output: 98,304 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-07-28
- Knowledge cutoff: 2025-03-31
Frequently Asked Questions
What is the context window of GLM 4.5 Air?
GLM 4.5 Air supports a context window of up to 131,072 tokens.
Does GLM 4.5 Air support function calling?
Yes. GLM 4.5 Air supports tool / function calling.
Does GLM 4.5 Air support reasoning?
Yes. GLM 4.5 Air is a reasoning-capable model.
What is the knowledge cutoff of GLM 4.5 Air?
The knowledge cutoff of GLM 4.5 Air is 2025-03-31.