官网GitHub

Zhipu GLM-4.5-Air

To allow every developer and user to easily experience the capabilities of cutting-edge large models,Zhipu is providing the GLM-4.5-Air model free of charge to Cherry Studio users. As an efficient foundational model specifically built for agent applications, GLM-4.5-Air achieves an excellent balance between performance and cost, making it an ideal choice for building intelligent applications.

🚀 What is GLM-4.5-Air?

GLM-4.5-Air is Zhipu's newly launched high-performance language model that adopts advancedMixture-of-Experts (MoE) architecture, significantly reducing computational resource consumption while maintaining outstanding reasoning ability.

  • Total parameters: 106 billion

  • Activated parameters: 12 billion

Through streamlined design, GLM-4.5-Air achieves higher inference efficiency, suitable for deployment in resource-constrained environments while still capable of handling complex tasks.

📚 Unified training process, solidifying the intelligence foundation

GLM-4.5-Air shares a consistent training process with the flagship series, ensuring it has a solid foundation of general capabilities:

  1. Large-scale pretraining: on up to 1.5e14 tokens of general corpora, training was completed to build broad knowledge understanding capabilities;

  2. Specialized domain optimization: reinforced training on key tasks such as code generation, logical reasoning, and agent interaction;

  3. Long-context support: context length extended to 128K tokens, able to handle long documents, complex dialogues, or large codebases;

  4. Reinforcement learning enhancement: using RL to optimize the model's decision-making abilities in inference planning, tool calling, and other areas.

This training system gives GLM-4.5-Air excellent generalization and task adaptability.

⚙️ Core capabilities optimized for agents

GLM-4.5-Air has been deeply adapted for agent application scenarios and has the following practical capabilities:

✅ Tool calling support: can call external tools through standardized interfaces to achieve task automation ✅ Web browsing and information extraction: can work with browser plugins to accomplish dynamic content understanding and interaction ✅ Software engineering assistance: supports requirement analysis, code generation, defect identification and repair ✅ Frontend development support: has good understanding and generation capabilities for frontend technologies such as HTML, CSS, and JavaScript

The model can be flexibly integrated into Claude Code, Roo Code and other code agent frameworks, or used as the core engine of any custom Agent.

💡 Intelligent "thinking modes", flexibly responding to various requests

GLM-4.5-Air supportshybrid reasoning modes, and users can control whether to enable deep thinking via thinking.type parameter:

  • enabled: enable thinking, suitable for complex tasks requiring step-by-step reasoning or planning

  • disabled: disable thinking, used for simple queries or immediate responses

  • The default setting is dynamic thinking mode, where the model automatically determines whether in-depth analysis is needed

Task type
Examples

Simple tasks(thinking recommended to be off)

- Query "Zhipu AI's founding time" - Translate "I love you" into Chinese

Medium tasks(thinking recommended to be on)

- Compare the pros and cons of plane vs high-speed train from Beijing to Shanghai - Explain why Jupiter has more moons

Complex tasks(thinking strongly recommended to be on)

- Explain how experts coordinate in an MoE model - Analyze whether to buy an ETF based on market information

🌟 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:

  • ⚡ Generation speed over 100 tokens/second, responsive and supports low-latency interaction

  • 💰 API cost is extremely low: input only 0.8 CNY/1M tokens, output 2 CNY/1M tokens

  • 🖥️ Fewer activated parameters, low computing requirements, easy to run with high concurrency locally or in the cloud

Truly delivers an AI service experience of "high performance, low barrier to entry."

🧠 Focused on practical capability: intelligent code generation

GLM-4.5-Air performs stably in code generation and supports:

  • Covers mainstream languages such as Python, JavaScript, Java and others

  • Generates according to natural language instructionsCode that isstructurally clear and highly maintainable

  • Reduces templated output, closer to real development scenario needs

Suitable for rapid prototyping, automated completion, bug fixing, and other high-frequency development tasks.

Try it for free now GLM-4.5-Air, start your agent development journey! Whether you want to build an automation assistant, a programming companion, or explore the next generation of AI applications, GLM-4.5-Air will be your efficient and reliable AI engine.

📘 Get connected now and unleash your creativity!

PreviousCherryAI (Free)NextQwen3-8B

Last updated

Was this helpful?