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

# Together AI

> Use Together AI models in your BoostGPT AI teammates

## Overview

Together AI hosts open-weight Qwen models, including a coder variant, on managed infrastructure.

## Available Models

> [card] GLM-5.3
>
> **6 credits** • Zhipu's flagship for complex software engineering and long-horizon agent work, with a 1M context window.
>
> * 1M context window
> * Exceptional reasoning (reasoning model)
> * Speed: Medium • Cost: Low
> * Model id: `zai-org/GLM-5.3`

> [card] GLM-5.2
>
> **6 credits** • Zhipu's previous flagship, with a 1M context window and strong long-horizon performance.
>
> * 1M context window
> * Exceptional reasoning (reasoning model)
> * Speed: Medium • Cost: Low
> * Model id: `zai-org/GLM-5.2`

> [card] Kimi K3
>
> **12 credits** • Moonshot's flagship, with a 1M-token context window.
>
> * 1M context window
> * Exceptional reasoning (reasoning model)
> * Speed: Medium • Cost: Medium
> * Model id: `moonshotai/Kimi-K3`

> [card] MiniMax M3
>
> **2 credits** • MiniMax's flagship, served on TogetherAI with a 512K context window.
>
> * 524K context window
> * Excellent reasoning (reasoning model)
> * Speed: Medium • Cost: Low
> * Model id: `MiniMaxAI/MiniMax-M3`

> [card] GPT-OSS (120B)
>
> **2 credits** • OpenAI's open-weight 120B model, served on TogetherAI.
>
> * 131K context window
> * Excellent reasoning
> * Speed: Fast • Cost: Low
> * Model id: `openai/gpt-oss-120b`

> [card] Qwen 2.5 Coder (32B)
>
> **7 credits** • Specialized coding model. Enhanced capabilities for programming tasks.
>
> * 32K context window
> * Excellent reasoning
> * Speed: Fast • Cost: Low
> * Model id: `Qwen/Qwen2.5-Coder-32B-Instruct`

> [card] Qwen 2.5 Turbo (72B)
>
> **10 credits** • Large, fast Qwen model. Powerful performance with optimized speed.
>
> * 128K context window
> * Excellent reasoning
> * Speed: Fast • Cost: Medium
> * Model id: `Qwen/Qwen2.5-72B-Instruct-Turbo`

## Setup

### Using BoostGPT-Hosted API Keys

**1. Select a model**

In your BoostGPT dashboard, choose any Together AI model when creating or configuring an AI teammate.

**2. Start chatting**

Credits are deducted per step at the rate shown on each model above. Nothing else to configure.

### Using Your Own API Key

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

```javascript theme={null}
await client.chat({
  bot_id: 'bot-id',
  message: 'Hello',
  model: 'zai-org/GLM-5.3',
  provider_key: process.env.TOGETHERAI_API_KEY
});
```

## Next Steps

> [card] [Model Comparison](/docs/providers/model-comparison.md)
>
> Compare every model across all providers

> [card] [Provider Overview](/docs/providers/overview.md)
>
> See all supported providers


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.