> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/pre-basic/providers/cherryai/free-glm45air.md).
# Zhipu GLM-4.5-Air
To make it easy for every developer and user to experience the capabilities of cutting-edge large models,**Zhipu has made the GLM-4.5-Air model available for free to Cherry Studio users**. As an efficient foundation model built specifically for agent applications, GLM-4.5-Air achieves an excellent balance between performance and cost, making it an ideal choice for building intelligent applications.
***
**π What is GLM-4.5-Air?**
GLM-4.5-Air is Zhipuβs latest high-performance language model, using the advanced**Mixture-of-Experts (MoE) architecture**, significantly reducing computational resource consumption while maintaining outstanding reasoning ability.
* **Total parameters: 106 billion**
* **Activated parameters: 12 billion**
Through a streamlined design, GLM-4.5-Air achieves higher inference efficiency, making it suitable for deployment in resource-constrained environments while still handling complex tasks.
***
**π Unified training pipeline, laying a solid intelligent foundation**
GLM-4.5-Air shares the same training pipeline as the flagship series, ensuring a strong foundation of general capabilities:
1. **Large-scale pretraining**: on up to **150 trillion tokens of general-purpose corpora**for training, building broad knowledge understanding capabilities;
2. **Domain-specific optimization**: strengthened training on key tasks such as code generation, logical reasoning, and agent interaction;
3. **Long-context support**: context length extended to **128K tokens**, capable of handling long documents, complex conversations, or large code projects;
4. **Reinforcement learning enhancement**: optimizing the modelβs decision-making abilities in reasoning, planning, tool use, and more through RL.
This training system gives GLM-4.5-Air excellent generalization ability and task adaptability.
***
**βοΈ Core capabilities optimized for agents**
GLM-4.5-Air has been deeply adapted for agent application scenarios and offers the following practical capabilities:
β **Tool-calling support**: can call external tools through standardized interfaces to automate tasks\
β **Web browsing and information extraction**: can work with browser plugins to understand and interact with dynamic content\
β **Software engineering assistance**: supports requirement analysis, code generation, defect identification, and fixing\
β **Front-end development support**: has a good understanding of and generation capability for front-end technologies such as HTML, CSS, and JavaScript
This model can be flexibly integrated into **Claude Code, Roo Code** and other code agent frameworks, and can also be used as the core engine of any custom Agent.
***
**π‘ Intelligent "thinking mode" for flexible responses to various requests**
GLM-4.5-Air supports**hybrid reasoning mode**, and users can use `thinking.type` parameter to control whether deep thinking is enabled:
* `enabled`: enable thinking, suitable for complex tasks that require step-by-step reasoning or planning
* `disabled`: disable thinking, for simple queries or immediate responses
* The default is **dynamic thinking mode**, where the model automatically decides whether deep analysis is needed
| Task type | Example |
| ---------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Simple tasks**(thinking recommended off) |
- Query: "When was Zhipu AI founded?" - Translate "I love you" into Chinese
|
| **Medium tasks**(thinking recommended on) |
- Compare the pros and cons of taking a plane versus a high-speed train from Beijing to Shanghai - Explain why Jupiter has so many moons
|
| **Complex tasks**(strongly recommended to enable thinking) |
- Explain how experts cooperate in an MoE model - Analyze whether to buy ETFs based on market information
|
***
**π Efficient and low-cost, easier deployment**
GLM-4.5-Air achieves an excellent balance between performance and cost, making it especially suitable for real-world business deployment:
* β‘ **Generation speed exceeds 100 tokens/second**, with fast responses and low-latency interaction support
* π° **Extremely low API cost**: input only **RMB 0.8/million tokens**, output **RMB 2/million tokens**
* π₯οΈ Fewer activated parameters, lower compute requirements, easy to run locally or in the cloud with high concurrency
Truly delivers an AI service experience that is "high-performance and low-barrier."
***
**π§ Focus on practical capabilities: intelligent code generation**
GLM-4.5-Air performs steadily in code generation and supports:
* covers **Python, JavaScript, Java** and other mainstream languages
* generating code according to natural language instructions**that is well-structured and highly maintainable**code
* reducing template-like output and better matching the needs of real development scenarios
Suitable for frequent development tasks such as rapid prototyping, automatic completion, and bug fixing.
***
Try GLM-4.5-Air for free now **GLM-4.5-Air**, and start your journey into agent development!\
Whether you want to build an automated assistant, a coding companion, or explore next-generation AI applications, GLM-4.5-Air will be your efficient and reliable AI engine.
π Connect now and unleash your creativity!
***
### π‘ Get help and submit feedback
If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) the official channels provided there.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.cherryai.com.cn/docs/en-us/pre-basic/providers/cherryai/free-glm45air.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.