# GLM-4.5-AirX

> GLM-4.5-AirX is a lightweight Z.ai text model designed for fast responses while keeping high performance.

## Key facts

- Model author: Z.ai
- Input: $1.10 per 1M tokens
- Output: $4.50 per 1M tokens
- Cached input: $0.22 per 1M tokens
- Context window: 128,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2025-07-28
- Model IDs: `z-ai/glm-4.5-airx`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4.5-airx

## Overview

GLM-4.5-AirX is a lightweight text model from Z.ai that pairs high performance with an ultra-fast response. It is designed for applications where latency matters, such as live assistants and agents that chain many tool calls. It supports reasoning, structured output and tool calling.

GLM-4.5-AirX has a 128K-token context window. It accepts text input and returns text output. It was released on July 28, 2025.

## Capabilities

GLM-4.5-AirX supports reasoning, structured output and tool calling. Z.ai lists three traits for it: lightweight, high performance and an ultra-fast response.

## Pricing

GLM-4.5-AirX costs $1.10 per 1M input tokens and $4.50 per 1M output tokens. Cache reads cost $0.22 per 1M tokens.

GLM-4.5-AirX is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GLM-4.5-AirX for latency-sensitive assistants, such as live chat and in-product helpers, where a short response time matters more than the size of the model.

It is also suited to agent steps that call tools repeatedly and return structured output, since each step finishes quickly and the 128K-token context window carries the task history.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "z-ai/glm-4.5-airx", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-4.5-AirX?

GLM-4.5-AirX is a lightweight Z.ai text model designed for fast responses while keeping high performance.

### How much does GLM-4.5-AirX cost?

GLM-4.5-AirX costs $1.10 per 1M input tokens and $4.50 per 1M output tokens, with cache reads at $0.22 per 1M tokens.

### What is the context window of GLM-4.5-AirX?

GLM-4.5-AirX has a 128K-token context window.

### What inputs and outputs does GLM-4.5-AirX support?

GLM-4.5-AirX accepts text input and returns text output.

### Does GLM-4.5-AirX support tool calling?

Yes. GLM-4.5-AirX supports tool calling, along with reasoning and structured output.

### When was GLM-4.5-AirX released?

GLM-4.5-AirX was released on July 28, 2025.

### How do I call GLM-4.5-AirX via the API?

Send requests to RealRelay's OpenAI-compatible API and use the model ID z-ai/glm-4.5-airx.