# GLM-5.2-Fast

> GLM-5.2-Fast is Z.ai's high-speed text model, supporting reasoning, structured output and tool calling.

## Key facts

- Model author: Z.ai
- Input: $2.25 per 1M tokens
- Output: $7.88 per 1M tokens
- Cached input: $0.56 per 1M tokens
- Context window: 1,048,576 tokens
- Maximum output: 131,072 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Model IDs: `baidu/glm-5.2-fast`
- Model page: https://www.realrelay.ai/model/z-ai/glm-5.2-fast

## Overview

GLM-5.2-Fast is a text-only model from Z.ai, published as a high-speed variant of the GLM family. It takes text prompts and returns text responses.

Reasoning, structured output and tool calling are supported, and the model works over a 1,048,576-token context window with up to 131,072 tokens of output per response. It is served through RealRelay's OpenAI-compatible endpoint under the model ID baidu/glm-5.2-fast.

## Capabilities

GLM-5.2-Fast accepts text input and returns text output. Reasoning, structured output and tool calling are among its supported capabilities, so applications can request structured results and let the model call tools.

The context window is 1,048,576 tokens and the maximum output is 131,072 tokens per response.

## Pricing

Input is priced at $2.25 per 1M tokens and output at $7.88 per 1M tokens. Reads from the cache are priced at $0.56 per 1M tokens.

All prices are listed per 1M tokens.

## Use cases

With a 1,048,576-token context window, GLM-5.2-Fast fits prompts that carry large amounts of text, and its reasoning, structured output and tool calling support suit applications that need results in a defined shape or need to call tools.

Common uses include long-text analysis, agent workflows that depend on tool calling, and reasoning tasks that return structured results.

## 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": "baidu/glm-5.2-fast", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-5.2-Fast?

GLM-5.2-Fast is Z.ai's high-speed text model. It accepts text input and returns text output, and it supports reasoning, structured output and tool calling.

### How is GLM-5.2-Fast priced?

Input is $2.25 per 1M tokens and output is $7.88 per 1M tokens. Reads from the cache are $0.56 per 1M tokens.

### What is the context window of GLM-5.2-Fast?

GLM-5.2-Fast has a context window of 1,048,576 tokens.

### What is the maximum output of GLM-5.2-Fast?

The maximum output is 131,072 tokens per response.

### What inputs and outputs does GLM-5.2-Fast support?

GLM-5.2-Fast supports text input and text output.

### Does GLM-5.2-Fast support tool calling and structured output?

Yes. Tool calling, structured output and reasoning are among its supported capabilities.

### How do I call GLM-5.2-Fast through the OpenAI-compatible API?

Send a chat completion request to RealRelay's OpenAI-compatible endpoint with the model ID baidu/glm-5.2-fast.