# GLM-5V-Turbo

> A native multimodal agent foundation model from Z.ai for vision-based coding and agent-driven tasks, served through RealRelay's OpenAI-compatible endpoint.

## Key facts

- Model author: Z.ai
- Input: $1.20 per 1M tokens
- Output: $4.00 per 1M tokens
- Cached input: $0.24 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: file, image, text, video
- Output modalities: text
- Capabilities: reasoning, tools, vision
- Released: 2026-04-01
- Model IDs: `z-ai/glm-5v-turbo`
- Model page: https://www.realrelay.ai/model/z-ai/glm-5v-turbo

## Overview

GLM-5V-Turbo is Z.ai's native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It accepts text, images, video and files as input and returns text.

On RealRelay the model is called as z-ai/glm-5v-turbo through the OpenAI-compatible endpoint, so multimodal requests use the same client setup as your text calls.

## Capabilities

Input modalities are text, image, video and file; the output modality is text. The context window is 200,000 tokens and the maximum output is 128,000 tokens.

It supports reasoning, vision and tool calling, so one request can work with visual input, invoke tools and return a text answer.

## Pricing

Input is $1.20 per 1M tokens and output is $4.00 per 1M tokens. Cached input reads are $0.24 per 1M tokens.

Pricing is metered per 1M tokens, so the tokens a request sends and receives set the price of that request.

## Use cases

Vision-based coding work where images or video are part of the request alongside text, across a 200,000 token context window.

Agent-driven tasks that combine visual input, tool calling and text output of up to 128,000 tokens per response.

## 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-5v-turbo", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-5V-Turbo?

GLM-5V-Turbo is Z.ai's native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It accepts text, image, video and file input and returns text.

### How is GLM-5V-Turbo priced?

Input is $1.20 per 1M tokens and output is $4.00 per 1M tokens. Cached input reads are $0.24 per 1M tokens.

### What is the context window of GLM-5V-Turbo?

The context window is 200,000 tokens and the maximum output is 128,000 tokens.

### What inputs and outputs does GLM-5V-Turbo support?

Input modalities are text, image, video and file, and the output modality is text.

### Does GLM-5V-Turbo support vision and tool calling?

It supports reasoning, vision and tool calling, so a request can reason about visual input, invoke tools and return text.

### When was GLM-5V-Turbo released?

GLM-5V-Turbo was released on April 1, 2026.

### How do I call GLM-5V-Turbo through the API?

Use the model ID z-ai/glm-5v-turbo on RealRelay's OpenAI-compatible endpoint with your existing OpenAI client code.