GLM 4.5 Air

GLM 4.5 Air is a Z.ai model available in Agent Serve. GLM 4.5 Air is a Z.ai model tracked in Agent Serve. It supports a 128k token context window. Pricing starts at $0.2/1M input tokens and $1.1/1M output tokens. Key capabilities include Temperature 0-1, Tool choice, Structured outputs.

GLM 4.5 Air starts at $0.2/1M input tokens, and $1.1/1M output tokens.

GLM 4.5 Air supports a context window of 128k tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

GLM 4.5 Air supports the following capabilities in Agent Serve: Temperature 0-1, Tool choice, Structured outputs, Thinking disabled, enabled, Max output 98k.

Best for reasoning-heavy tasks that need more deliberate model control. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.