# GLM-4.6V

> GLM-4.6V is a Z.ai multimodal model for visual understanding and long-context reasoning across images, documents and video.

## Key facts

- Model author: Z.ai
- Input: $0.30 per 1M tokens
- Output: $0.90 per 1M tokens
- Cached input: $0.05 per 1M tokens
- Context window: 128,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: tools, vision
- Released: 2025-12-08
- Model IDs: `z-ai/glm-4.6v`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4.6v

## Overview

GLM-4.6V is a large multimodal model from Z.ai, designed for high-fidelity visual understanding and long-context reasoning across images, documents and mixed media. It processes complex page layouts, supports native function calling, and offers a switch that turns thinking mode on or off.

GLM-4.6V has a 128K-token context window. It accepts text, image and video input and returns text output. It was released on December 8, 2025. Its weights are openly available.

## Capabilities

GLM-4.6V supports tool calling and visual understanding. Z.ai documents native function calling and a thinking mode switch for the model.

## Pricing

GLM-4.6V costs $0.30 per 1M input tokens and $0.90 per 1M output tokens. Cache reads cost $0.05 per 1M tokens.

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

## Use cases

Use GLM-4.6V for document understanding: reading scanned pages, reports and slides with complex layouts together with the question you want answered, then returning the answer as text.

It also suits visual agents that look at screenshots, images or video and call tools through native function calling, using the 128K-token context window to keep long mixed-media inputs in one request.

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

## FAQ

### What is GLM-4.6V?

GLM-4.6V is a Z.ai multimodal model for visual understanding and long-context reasoning across images, documents and video.

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

GLM-4.6V costs $0.30 per 1M input tokens and $0.90 per 1M output tokens, with cache reads at $0.05 per 1M tokens.

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

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

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

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

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

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

### When was GLM-4.6V released?

GLM-4.6V was released on December 8, 2025.

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

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