# GLM-5.3-FlashX-Legal

> GLM-5.3-FlashX-Legal reads text, images and video and returns text, with reasoning, structured output and tool calling.

## Key facts

- Model author: Z.ai
- Input: $0.37 per 1M tokens
- Output: $1.25 per 1M tokens
- Cached input: $0.075 per 1M tokens
- Context window: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Model IDs: `z-ai/glm-5.3-flashx-legal`
- Model page: https://www.realrelay.ai/model/z-ai/glm-5.3-flashx-legal

## What GLM-5.3-FlashX-Legal is

GLM-5.3-FlashX-Legal is a Z.ai model available through RealRelay's OpenAI-compatible endpoint under the model ID z-ai/glm-5.3-flashx-legal. It accepts text, image and video input and returns text.

The model has a 1M token context window and can return up to 128K tokens of output. Reasoning, structured output and tool calling are part of the model's declared capabilities.

## Capabilities and input types

Requests may carry text, image and video parts, and every response is text. Reasoning, structured output and tool calling are supported, so a request can ask for a defined output format or declare functions for the model to call.

The context window holds 1M tokens, and output can extend to 128K tokens within a single request.

## Pricing per 1M tokens

Input is $0.37 per 1M tokens and output is $1.25 per 1M tokens. Cache reads are $0.075 per 1M tokens.

Requests are billed per token on RealRelay's OpenAI-compatible endpoint, so the price of a call follows the number of input and output tokens it uses.

## Where GLM-5.3-FlashX-Legal fits

Because the input side accepts text, images and video, a single request can pair written instructions with media and receive a text answer.

Structured output helps when a response has to follow a defined format, and tool calling helps when the model should call functions declared in the request.

The 1M token context window suits long inputs, while the 128K token output limit covers lengthy single responses.

## 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-5.3-flashx-legal", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-5.3-FlashX-Legal?

It is a Z.ai model available on RealRelay under the model ID z-ai/glm-5.3-flashx-legal. It accepts text, image and video input and returns text.

### What are the prices for GLM-5.3-FlashX-Legal?

Input is $0.37 per 1M tokens and output is $1.25 per 1M tokens. Cache reads are $0.075 per 1M tokens.

### How large is the context window of GLM-5.3-FlashX-Legal?

The context window is 1M tokens, and the model can return up to 128K tokens of output.

### What inputs and outputs does GLM-5.3-FlashX-Legal support?

The model accepts text, image and video input and produces text output.

### Does GLM-5.3-FlashX-Legal support tool calling?

Yes. Tool calling, reasoning and structured output are supported, so requests can declare functions and ask for a defined output format.

### How do I call GLM-5.3-FlashX-Legal?

Send a request to RealRelay's OpenAI-compatible endpoint with the model ID z-ai/glm-5.3-flashx-legal, using the input modalities you need and reading the text response.