Z.ai: GLM 4.5 Air (free)
FreeZ AiID: z-ai/glm-4.5-air:free
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)
Pricing per 1M Tokens
| Input (Prompt) | Free |
| Output (Completion) | Free |
| Cache Read | Free |
| Cache Write | Free |
| Image | N/A |
Specifications
| Context Length | 131K |
| Max Output Tokens | 96K |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | Other |
| Instruct Type | N/A |
| Top Provider Context | 131K |
| Top Provider Max Output | 96K |
| Moderated | No |
Compare this model
See how Z.ai: GLM 4.5 Air (free) stacks up against other models.
More from Z Ai
Last updated: March 23, 2026
First tracked: March 23, 2026