# GLM-4-32B-0414-128K

> GLM-4-32B-0414-128K is a cost-effective Z.ai foundation language model with a 128K-token context window.

## Key facts

- Model author: Z.ai
- Input: $0.10 per 1M tokens
- Output: $0.10 per 1M tokens
- Context window: 128,000 tokens
- Maximum output: 16,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: search, structured_output, tools
- Model IDs: `z-ai/glm-4-32b-0414-128k`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4-32b-0414-128k

## Overview

GLM-4-32B-0414-128K is a foundation language model from Z.ai that the vendor describes as highly cost-effective. It is a text-only model aimed at high-intelligence language work at a low price, with the same price for input and output tokens. It supports web search, structured output and tool calling.

GLM-4-32B-0414-128K has a 128K-token context window and can generate up to 16K output tokens. It accepts text input and returns text output.

## Capabilities

GLM-4-32B-0414-128K supports structured output, tool calling and web search. Z.ai summarizes its strength as high intelligence at a very low price.

## Pricing

GLM-4-32B-0414-128K costs $0.10 per 1M input tokens and $0.10 per 1M output tokens.

GLM-4-32B-0414-128K is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GLM-4-32B-0414-128K for high-volume text work where price matters, such as summarizing long documents, answering questions over retrieved passages and drafting replies.

Web search and tool calling let it fetch information or trigger actions, and structured output keeps results in a format that other systems can parse. The 128K-token window also holds long source texts.

## 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-4-32b-0414-128k", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-4-32B-0414-128K?

GLM-4-32B-0414-128K is a cost-effective Z.ai foundation language model with a 128K-token context window.

### How much does GLM-4-32B-0414-128K cost?

GLM-4-32B-0414-128K costs $0.10 per 1M input tokens and $0.10 per 1M output tokens.

### What is the context window of GLM-4-32B-0414-128K?

GLM-4-32B-0414-128K has a 128K-token context window and can generate up to 16K output tokens.

### What inputs and outputs does GLM-4-32B-0414-128K support?

GLM-4-32B-0414-128K accepts text input and returns text output.

### Does GLM-4-32B-0414-128K support tool calling?

Yes. GLM-4-32B-0414-128K supports tool calling, along with structured output and web search.

### How do I call GLM-4-32B-0414-128K via the API?

Send requests to RealRelay's OpenAI-compatible API and use the model ID z-ai/glm-4-32b-0414-128k.