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

# Mistral AI

> Use Mistral models in your BoostGPT AI teammates

## Overview

Mistral AI provides open and efficient generative AI models with strong performance across various tasks. Mistral models offer a good balance of capability and cost-effectiveness.

## Available Models

> [card] Mistral Small
>
> **1 credit** • Efficient model for basic tasks. Good balance of speed and capability.
>
> * 32K context window
> * Good reasoning
> * Speed: Fast • Cost: Low
> * Vision: images supported
> * Model id: `mistral-small-latest`

> [card] Mistral Medium
>
> **6 credits** • Mid-tier model with enhanced capabilities. Suitable for more complex tasks.
>
> * 32K context window
> * Excellent reasoning
> * Speed: Medium • Cost: Medium
> * Model id: `mistral-medium-latest`

> [card] Mistral Large
>
> **2 credits** • Most powerful Mistral model. Excellent for demanding applications and complex reasoning.
>
> * 128K context window
> * Excellent reasoning
> * Speed: Medium • Cost: Medium
> * Model id: `mistral-large-latest`

## Setup

### Using BoostGPT-Hosted API Keys

**1. Select Mistral Model**

In your BoostGPT dashboard, select any Mistral model when creating or configuring your bot.

**2. Choose Your Model**

* **Mistral Large**: For complex, demanding applications
* **Mistral Medium**: For balanced production use
* **Mistral Small**: For cost-effective simple tasks

### Using Your Own Mistral API Key

> [tab] Dashboard Setup
>
> **1. Navigate to Integrations**
>
> Go to [app.boostgpt.co](https://app.boostgpt.co/integrations) and select **Integrations**
>
> **2. Select Mistral**
>
> Find and click on the **Mistral** provider
>
> **3. Add API Key**
>
> Enter your Mistral API key and select which AI teammates will use this key
>
> **4. Save Configuration**
>
> Click save to apply your custom API key

> [tab] Core SDK
>
> ```javascript bot.js theme={null}
> import { BoostGPT } from 'boostgpt';
>
> const client = new BoostGPT({
>   project_id: process.env.BOOSTGPT_PROJECT_ID,
>   key: process.env.BOOSTGPT_API_KEY
> });
>
> // Create bot with Mistral model
> const botResponse = await client.createBot({
>   name: 'My Mistral Bot',
>   model: 'mistral-medium-latest',
>   instruction: 'You are a helpful assistant.',
>   max_reply_tokens: 1000,
>   status: 'active'
> });
>
> if (botResponse.err) {
>   console.error('Error:', botResponse.err);
> } else {
>   console.log('Bot created:', botResponse.response);
> }
> ```

## Next Steps

> [card] [Model Comparison](/docs/providers/model-comparison.md)
>
> Compare Mistral with other providers

> [card] [SDK Reference](/docs/sdk/core/api-reference.md)
>
> Full API documentation

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

> [card] [Bring Your Own Key](/docs/providers/bring-your-own-keys.md)
>
> Use your own Mistral API key


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