All Models
GLM-4.5-Air
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 `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
Available Providers (14)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Zhipu AI Coding Plan | glm-4.5-air | $0.00/MTok | $0.00/MTok | 131.1K | 98.3K | |
 Z.AI Coding Plan | glm-4.5-air | $0.00/MTok | $0.00/MTok | 131.1K | 98.3K | |
 Chutes | zai-org/GLM-4.5-Air | $0.05/MTok | $0.22/MTok | 131.1K | 131.1K | |
 submodel | zai-org/GLM-4.5-Air | $0.10/MTok | $0.50/MTok | 131.1K | 131.1K | |
 ZenMux | z-ai/glm-4.5-air | $0.11/MTok | $0.56/MTok | 128K | 64K | |
 NovitaAI | zai-org/glm-4.5-air | $0.13/MTok | $0.85/MTok | 131.1K | 98.3K | |
 Z.AI | glm-4.5-air | $0.20/MTok | $1.10/MTok | 131.1K | 98.3K | |
 Nebius Token Factory | zai-org/GLM-4.5-Air | $0.20/MTok | $1.20/MTok | 128K | 4.1K | |
 OpenRouter | z-ai/glm-4.5-air | $0.20/MTok | $1.10/MTok | 128K | 96K | |
 Zhipu AI | glm-4.5-air | $0.20/MTok | $1.10/MTok | 131.1K | 98.3K | |
 Vercel AI Gateway | zai/glm-4.5-air | $0.20/MTok | $1.10/MTok | 128K | 96K | |
 Fireworks AI | accounts/fireworks/models/glm-4p5-air | $0.22/MTok | $0.88/MTok | 131.1K | 131.1K | |
 Cortecs | glm-4.5-air | $0.22/MTok | $1.34/MTok | 131.1K | 131.1K | |
 Qiniu | glm-4.5-air | —/MTok | —/MTok | 131K | 4.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output