# GLM-5

> An open-source foundation model from Z.ai for complex systems design and long-horizon agent workflows, served through RealRelay's OpenAI-compatible endpoint.

## Key facts

- Model author: Z.ai
- Input: $1.00 per 1M tokens
- Output: $3.20 per 1M tokens
- Cached input: $0.20 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2026-02-12
- Model IDs: `z-ai/glm-5`
- Model page: https://www.realrelay.ai/model/z-ai/glm-5

## Overview

GLM-5 is an open-source foundation model from Z.ai, engineered for complex systems design and long-horizon agent workflows. It takes text in and returns text, and its weights are openly available.

On RealRelay the model is called as z-ai/glm-5 through the OpenAI-compatible endpoint, so it fits into an existing OpenAI client setup.

## Capabilities

GLM-5 accepts text input and returns text output. The context window is 200,000 tokens and the maximum output is 128,000 tokens.

It supports reasoning, structured output and tool calling: a single request can reason over the prompt, invoke tools and return results in a defined structure.

## Pricing

Input is $1.00 per 1M tokens and output is $3.20 per 1M tokens. Cached input reads are $0.20 per 1M tokens.

Pricing is metered per 1M tokens, so the tokens a request sends and receives set the price of that request.

## Use cases

Complex systems design work that needs reasoning across a long input, with a context window of 200,000 tokens.

Long-horizon agent workflows where the model calls tools and returns structured output, with up to 128,000 output tokens per response.

## 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-5", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-5?

GLM-5 is Z.ai's open-source foundation model, engineered for complex systems design and long-horizon agent workflows. It accepts text and returns text.

### How is GLM-5 priced?

Input is $1.00 per 1M tokens and output is $3.20 per 1M tokens. Cached input reads are $0.20 per 1M tokens.

### What is the context window of GLM-5?

The context window is 200,000 tokens and the maximum output is 128,000 tokens.

### What inputs and outputs does GLM-5 support?

Text is the only input modality and text is the output modality. Requests and responses are text.

### Does GLM-5 support tool calling?

It supports reasoning, structured output and tool calling, so a request can produce structured results and invoke tools.

### When was GLM-5 released?

GLM-5 was released on February 12, 2026.

### How do I call GLM-5 through the API?

Use the model ID z-ai/glm-5 on RealRelay's OpenAI-compatible endpoint with your existing OpenAI client code.