> ## Documentation Index
> Fetch the complete documentation index at: https://docs.boostgpt.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Zhipu AI

> Use Zhipu AI models in your BoostGPT agents

## Overview

Zhipu's GLM models are strong multilingual generalists with a 200K context window, well suited to long documents and agentic tool use.

## Available Models

<CardGroup cols={2}>
  <Card title="GLM-4.6" icon="bolt">
    **1 credit** • Zhipu's capable general-purpose GLM model with a 200K context window and strong agentic performance.

    * 200K context window
    * Excellent reasoning
    * Speed: Medium • Cost: Low
    * Model id: `glm-4.6`
  </Card>

  <Card title="GLM-4.7" icon="sparkles">
    **1 credit** • Newer GLM-4 generation model with adaptive reasoning for complex agentic and coding tasks.

    * 200K context window
    * Excellent reasoning (reasoning model)
    * Speed: Medium • Cost: Low
    * Model id: `glm-4.7`
  </Card>

  <Card title="GLM-4.7 Flash" icon="zap">
    **1 credit** • The fast, free GLM-4.7 tier, optimized for low latency and high-volume tasks.

    * 200K context window
    * Good reasoning
    * Speed: Very\_fast • Cost: Very\_low
    * Model id: `glm-4.7-flash`
  </Card>

  <Card title="GLM-5.1" icon="circle">
    **1 credit** • Zhipu's frontier GLM-5 model, a large MoE for the most demanding reasoning and agentic work.

    * 200K context window
    * Exceptional reasoning (reasoning model)
    * Speed: Medium • Cost: Low
    * Model id: `glm-5.1`
  </Card>

  <Card title="GLM-4.6V" icon="gauge">
    **1 credit** • Multimodal GLM model that reasons over both images and text.

    * 128K context window
    * Excellent reasoning
    * Speed: Medium • Cost: Low
    * Vision: images supported
    * Model id: `glm-4.6v`
  </Card>
</CardGroup>

## Setup

### Using BoostGPT-Hosted API Keys

<Steps>
  <Step title="Select a model">
    In your BoostGPT dashboard, choose any Zhipu AI model when creating or configuring an agent.
  </Step>

  <Step title="Start chatting">
    Credits are deducted per step at the rate shown on each model above. Nothing else to configure.
  </Step>
</Steps>

### Using Your Own API Key

Bring your own key to bill Zhipu AI directly instead of spending BoostGPT credits. See
[Bring Your Own Keys](/providers/bring-your-own-keys).

```javascript theme={null}
await client.chat({
  bot_id: 'bot-id',
  message: 'Hello',
  model: 'glm-4.6',
  provider_key: process.env.ZHIPU_API_KEY
});
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Model Comparison" icon="chart-bar" href="/providers/model-comparison">
    Compare every model across all providers
  </Card>

  <Card title="Provider Overview" icon="layer-group" href="/providers/overview">
    See all supported providers
  </Card>
</CardGroup>