# GLM-4.5-X

> GLM-4.5-X is a Z.ai text model for strong reasoning, designed to return responses quickly.

## Key facts

- Model author: Z.ai
- Input: $2.20 per 1M tokens
- Output: $8.90 per 1M tokens
- Cached input: $0.45 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-x`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4.5-x

## Overview

GLM-4.5-X is a text model from Z.ai that the vendor describes as high-performance, with strong reasoning and an ultra-fast response. It is designed for applications where response time matters, such as interactive assistants and agents that call tools many times in a row.

GLM-4.5-X 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-X supports reasoning, structured output and tool calling. Z.ai positions it on three traits: high performance, strong reasoning and a fast response.

## Pricing

GLM-4.5-X costs $2.20 per 1M input tokens and $8.90 per 1M output tokens. Cache reads cost $0.45 per 1M tokens.

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

## Use cases

Use GLM-4.5-X for interactive chat assistants and customer-support bots where users wait on each reply, applying its reasoning to harder questions.

It also suits agent loops that call tools many times in a row, where a shorter response time per step adds up across the whole task, with a 128K-token context window for the 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-x", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-4.5-X?

GLM-4.5-X is a Z.ai text model for strong reasoning, designed to return responses quickly.

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

GLM-4.5-X costs $2.20 per 1M input tokens and $8.90 per 1M output tokens, with cache reads at $0.45 per 1M tokens.

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

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

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

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

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

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

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

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

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

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