Z.ai: GLM 4.5 Air: AI model
GLM-4.5 Air is the lightweight, cost-efficient variant of the flagship GLM-4.5 family. A Mixture-of-Experts model with a 128K-token context window, tuned for high-volume workloads via Hormouz.
- Context window:
- 131,072 tokens
- Input:
- $0.13/1M tokens
- Output:
- $0.85/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Thinking levels:
GLM-4.5 Air is the lighter member of the GLM-4.5 family. Like the flagship, it uses a Mixture-of-Experts (MoE) architecture, but with a smaller active parameter count. Which makes it faster and cheaper and a good fit for high-volume agentic use.
The model supports a hybrid inference mode: a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time responses. Tool calling and a 128K-token context window are both supported.
Pricing is usage-based: $0.13 per million input tokens and $0.85 per million output tokens. GLM-4.5 Air is served through Hormouz behind an OpenAI-compatible API with stable access from inside Iran.
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...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-4.5-air",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Z.ai |
|---|---|
| Type | Text |
| Context window | 131,072 tokens |
| Pricing | $0.13/M in · $0.85/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-4.5-air",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="z-ai/glm-4.5-air",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "z-ai/glm-4.5-air",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Z.ai: GLM 4.5 Air API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Z.ai: GLM 4.5 Air and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How is GLM-4.5 Air different from GLM-4.5?
- GLM-4.5 Air is the lighter, cheaper variant with fewer active parameters, better suited to high-volume workloads. If you need the highest quality, the standard GLM-4.5 is the better pick.
- How much does GLM-4.5 Air cost?
- Billing is usage-based: $0.13 per million input tokens and $0.85 per million output tokens.
- What context window and capabilities does GLM-4.5 Air have?
- It supports up to 128K tokens of context, tool calling and a hybrid inference mode (thinking / non-thinking).
- How do I access GLM-4.5 Air from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path from inside Iran, with no foreign credit card required.
- Is GLM-4.5 Air compatible with OpenAI code?
- Yes. Just point the base URL at Hormouz and drop in a Hormouz key. Your existing code runs unchanged.
Updated 2026-10-13