GLM-4.5-Air

GLM-4.5-Air is a lighter variant of GLM-4.5 from Z.ai (Zhipu, GLM). It is designed for fast coding assistance and cheaper agents. It is the first version of the glm-air line. It has a context window of 131072 tokens and a maximum output of 98304 tokens. Weights are open. It supports reasoning mode and tool calling. It accepts text and returns text. Knowledge cutoff is April 2025. It is served by 19 hosts. Pricing starts at $0.10 per million input tokens and $0.2911 per million output tokens. Cached input is $0.0233 per million tokens.

First version of its line in the registry.

Range across the hosts that serve it: up to $0.20 per 1M input tokens.

• ·131072 token context window
• ·98304 token max output
• ·Open weights
• ·Reasoning mode and tool calling
• ·Priced from $0.10 per million input

• Reach for it for fast coding assistance
• Reach for it for cheaper agent workflows
• Reach for it for text generation with tool calling
• Reach for it for reasoning tasks

19 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 131072 tokens, and the maximum output is 98304 tokens.

Are the weights open?

Yes, the weights are open. The model also supports reasoning mode and tool calling.

What is the price?

Input starts at $0.10 per million tokens, output at $0.2911 per million, and cached input at $0.0233 per million.