# GLM-4.6V-FlashX

> GLM-4.6V-FlashX is a lightweight, high-speed and affordable Z.ai vision-language model with native function calling.

## Key facts

- Model author: Z.ai
- Input: $0.04 per 1M tokens
- Output: $0.40 per 1M tokens
- Cached input: $0.004 per 1M tokens
- Context window: 128,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: tools, vision
- Model IDs: `z-ai/glm-4.6v-flashx`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4.6v-flashx

## Overview

GLM-4.6V-FlashX is a lightweight, high-speed and affordable multimodal model from Z.ai. It supports native function calling and offers a thinking mode switch. It is designed for visual tasks that run at volume and need quick answers at a low price.

GLM-4.6V-FlashX has a 128K-token context window. It accepts text, image and video input and returns text output.

## Capabilities

GLM-4.6V-FlashX supports tool calling and visual understanding. Z.ai positions it on three traits: lightweight, high speed and low price.

## Pricing

GLM-4.6V-FlashX costs $0.04 per 1M input tokens and $0.40 per 1M output tokens. Cache reads cost $0.004 per 1M tokens.

GLM-4.6V-FlashX is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GLM-4.6V-FlashX for high-volume image understanding, such as describing pictures, reading screenshots or answering questions about uploaded images, at a low price per request.

Native function calling lets it hand extracted details to other systems, and video input extends the same workflow to moving footage, all with a 128K-token context window.

## 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-4.6v-flashx", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-4.6V-FlashX?

GLM-4.6V-FlashX is a lightweight, high-speed and affordable Z.ai vision-language model with native function calling.

### How much does GLM-4.6V-FlashX cost?

GLM-4.6V-FlashX costs $0.04 per 1M input tokens and $0.40 per 1M output tokens, with cache reads at $0.004 per 1M tokens.

### What is the context window of GLM-4.6V-FlashX?

GLM-4.6V-FlashX has a 128K-token context window.

### What inputs and outputs does GLM-4.6V-FlashX support?

GLM-4.6V-FlashX accepts text, image and video input and returns text output.

### Does GLM-4.6V-FlashX support tool calling?

Yes. GLM-4.6V-FlashX supports tool calling, along with visual understanding.

### How do I call GLM-4.6V-FlashX via the API?

Send requests to RealRelay's OpenAI-compatible API and use the model ID z-ai/glm-4.6v-flashx.