# GLM-5-Turbo

> A Z.ai model built for fast inference in agent-driven environments, available through RealRelay's OpenAI-compatible endpoint.

## Key facts

- Model author: Z.ai
- Input: $1.20 per 1M tokens
- Output: $4.00 per 1M tokens
- Cached input: $0.24 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: 2026-03-15
- Model IDs: `z-ai/glm-5-turbo`
- Model page: https://www.realrelay.ai/model/z-ai/glm-5-turbo

## Overview

GLM-5-Turbo is a model from Z.ai designed for fast inference in agent-driven environments. It takes text in and returns text.

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

## Capabilities

GLM-5-Turbo 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, so one request can reason over the prompt, invoke tools and return a structured result.

## Pricing

Input is $1.20 per 1M tokens and output is $4.00 per 1M tokens. Cached input reads are $0.24 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

Agent-driven environments where the model calls tools and returns structured output while working inside a 200,000 token context window.

Text generation with responses of up to 128,000 output tokens, using the same OpenAI-compatible endpoint as your other calls.

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

## FAQ

### What is GLM-5-Turbo?

GLM-5-Turbo is a Z.ai model designed for fast inference in agent-driven environments. It accepts text and returns text.

### How is GLM-5-Turbo priced?

Input is $1.20 per 1M tokens and output is $4.00 per 1M tokens. Cached input reads are $0.24 per 1M tokens.

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

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

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

Input and output are both text, so requests and responses are plain text.

### Does GLM-5-Turbo support tool calling?

It supports reasoning, structured output and tool calling, so a request can invoke tools and return results in a defined structure.

### When was GLM-5-Turbo released?

GLM-5-Turbo was released on March 15, 2026.

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

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