GLM 4.5 Air

About 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)

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Zhipu Ai Model Lineup

Compare all models from Zhipu Ai to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Devstral 2 2512

Mistral

Input: $0.05

Output: $0.22

Context: 262k

Qwen2.5 VL 32B Instruct

Alibaba Qwen

Input: $0.05

Output: $0.22

Context: 128k

Qwen3 14B

Alibaba Qwen

Input: $0.05

Output: $0.22

Context: 131k

DeepSeek V4 Flash Latest

DeepSeek

Input: $0.09

Output: $0.18

Context: 1.0M

💡 Cheaper Alternatives

Same Brand (Zhipu Ai)

Cross Brand

🚀 Quick Start

Get started with GLM 4.5 Air API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="z-ai/glm-4.5-air",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision