# GLM-4.5V

> GLM-4.5V is a Z.ai vision-language foundation model for multimodal agent applications, with flexible reasoning.

## Key facts

- Model author: Z.ai
- Input: $0.60 per 1M tokens
- Output: $1.80 per 1M tokens
- Cached input: $0.11 per 1M tokens
- Context window: 64,000 tokens
- Maximum output: 16,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, vision
- Released: 2025-08-11
- Knowledge cutoff: 2024-12-31
- Model IDs: `z-ai/glm-4.5v`
- Model page: https://www.realrelay.ai/model/z-ai/glm-4.5v

## Overview

GLM-4.5V is a vision-language foundation model from Z.ai for multimodal agent applications. It is built on a Mixture-of-Experts architecture and understands images and video alongside text. Z.ai describes its reasoning as flexible and offers a thinking mode, so developers can choose between quick answers and deeper analysis.

GLM-4.5V has a 64K-token context window and can generate up to 16K output tokens. It accepts text, image and video input and returns text output. Its knowledge cutoff is December 31, 2024. It was released on August 11, 2025. Its weights are openly available.

## Capabilities

GLM-4.5V supports reasoning and visual understanding. Z.ai highlights video understanding among the strengths of the model.

## Pricing

GLM-4.5V costs $0.60 per 1M input tokens and $1.80 per 1M output tokens. Cache reads cost $0.11 per 1M tokens.

GLM-4.5V is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GLM-4.5V for multimodal agents that look at screenshots, photos or video, reason about what they show and decide which action to take.

It also suits question answering over videos and images, where the thinking mode can be switched on for harder questions about a scene, within a 64K-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-4.5v", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-4.5V?

GLM-4.5V is a Z.ai vision-language foundation model for multimodal agent applications, with flexible reasoning.

### How much does GLM-4.5V cost?

GLM-4.5V costs $0.60 per 1M input tokens and $1.80 per 1M output tokens, with cache reads at $0.11 per 1M tokens.

### What is the context window of GLM-4.5V?

GLM-4.5V has a 64K-token context window and can generate up to 16K output tokens.

### What inputs and outputs does GLM-4.5V support?

GLM-4.5V accepts text, image and video input and returns text output.

### What capabilities does GLM-4.5V support?

GLM-4.5V supports reasoning and visual understanding.

### When was GLM-4.5V released?

GLM-4.5V was released on August 11, 2025.

### How do I call GLM-4.5V via the API?

Send requests to RealRelay's OpenAI-compatible API and use the model ID z-ai/glm-4.5v.