# GLM-4.5

> GLM-4.5 is a Z.ai open-weight foundation model built for agent-based applications, using a Mixture-of-Experts design.

## Key facts

- Model author: Z.ai
- Input: $0.60 per 1M tokens
- Output: $2.20 per 1M tokens
- Cached input: $0.11 per 1M tokens
- Context window: 128,000 tokens
- Maximum output: 96,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2025-07-28
- Knowledge cutoff: 2024-12-31
- Model IDs: `z-ai/glm-4.5`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4.5

## Overview

GLM-4.5 is a foundation language model from Z.ai, purpose-built for agent-based applications. It uses a Mixture-of-Experts architecture and supports a context length of up to 128K tokens. It combines a thinking mode for complex reasoning with a non-thinking mode for quick responses.

GLM-4.5 has a 128K-token context window and can generate up to 96K output tokens. It accepts text input and returns text output. Its knowledge cutoff is December 31, 2024. It was released on July 28, 2025. Its weights are openly available.

## Capabilities

GLM-4.5 supports reasoning, structured output and tool calling. Z.ai also documents streaming output and context caching for the model.

## Pricing

GLM-4.5 costs $0.60 per 1M input tokens and $2.20 per 1M output tokens. Cache reads cost $0.11 per 1M tokens.

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

## Use cases

Use GLM-4.5 to build agents that plan multi-step work, call external tools and return structured results, switching on the thinking mode when a task needs deeper reasoning.

The 128K-token context window also leaves room for long documents and extended conversation history in a single request, and streaming output lets an interface show the reply as it is generated.

## 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", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-4.5?

GLM-4.5 is a Z.ai open-weight foundation model built for agent-based applications, using a Mixture-of-Experts design.

### How much does GLM-4.5 cost?

GLM-4.5 costs $0.60 per 1M input tokens and $2.20 per 1M output tokens, with cache reads at $0.11 per 1M tokens.

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

GLM-4.5 has a 128K-token context window and can generate up to 96K output tokens.

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

GLM-4.5 accepts text input and returns text output.

### Does GLM-4.5 support tool calling?

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

### When was GLM-4.5 released?

GLM-4.5 was released on July 28, 2025.

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

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