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

# Mistral AI

> Configure Mistral AI models in EnConvo

## Overview

Mistral AI is a French AI company building high-performance open and commercial language models. Their models are known for strong multilingual capabilities, efficient inference, and competitive pricing.

## Supported Models

| Model             | Description                 | Best For                     |
| ----------------- | --------------------------- | ---------------------------- |
| **Mistral Large** | Most capable flagship model | Complex reasoning, analysis  |
| **Mistral Small** | Fast and cost-efficient     | Daily tasks, chat            |
| **Mistral Nemo**  | Lightweight open model      | Quick responses, low latency |
| **Codestral**     | Code-specialized model      | Programming, code generation |

## Setup

<Steps>
  <Step title="Get API Key">
    1. Go to [Mistral Console](https://console.mistral.ai)
    2. Sign in or create an account
    3. Navigate to **API Keys**
    4. Create a new API key
  </Step>

  <Step title="Configure in EnConvo">
    1. Open **Settings** → **AI Provider**
    2. Select **Mistral AI**
    3. Go to **Credentials** module
    4. Enter your API key
  </Step>

  <Step title="Select Model">
    Choose your preferred model from the dropdown
  </Step>
</Steps>

## Configuration

| Setting         | Description           | Default       |
| --------------- | --------------------- | ------------- |
| **Credentials** | API key configuration | Required      |
| **Model Name**  | Model to use          | Mistral Large |
| **Temperature** | Creativity (0-2)      | Medium (1)    |

## Validate and Use

<Steps>
  <Step title="Validate credentials">
    Click **Validate** in the Mistral credential settings. If validation fails, confirm the API key is active and billing or free-tier quota is available.
  </Step>

  <Step title="Choose for the workload">
    Use Mistral Large for higher-quality analysis, Mistral Small for everyday work, and Codestral for code-heavy tasks.
  </Step>

  <Step title="Test multilingual prompts">
    If you work across languages, send a short bilingual prompt first to confirm the selected model handles your language pair well.
  </Step>
</Steps>

## Pricing

Check [Mistral Pricing](https://mistral.ai/pricing) for current rates.

| Model         | Input     | Output    |
| ------------- | --------- | --------- |
| Mistral Large | \$2/1M    | \$6/1M    |
| Mistral Small | \$0.2/1M  | \$0.6/1M  |
| Mistral Nemo  | \$0.15/1M | \$0.15/1M |
| Codestral     | \$0.3/1M  | \$0.9/1M  |

<Note>
  Mistral offers a free tier with rate limits, making it easy to get started.
</Note>

## Best Practices

<AccordionGroup>
  <Accordion title="Model Selection">
    * **Mistral Large**: Complex analysis, long documents, multilingual tasks
    * **Mistral Small**: Everyday chat, quick translations, summaries
    * **Mistral Nemo**: Low-latency tasks, lightweight workloads
    * **Codestral**: Code completion, debugging, refactoring
  </Accordion>

  <Accordion title="Multilingual Usage">
    Mistral models excel at European languages (French, German, Spanish, Italian) in addition to English. Use them for translation and multilingual content creation.
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Invalid API key">
    * Verify the key is copied correctly from [console.mistral.ai](https://console.mistral.ai)
    * Check if the key has been revoked or expired
    * Ensure billing is configured on your Mistral account
  </Accordion>

  <Accordion title="Rate limits">
    * Free tier has strict rate limits
    * Upgrade to a paid plan for higher throughput
    * Use Mistral Small or Nemo for lower-priority tasks to conserve quota
  </Accordion>

  <Accordion title="Model not responding">
    * Check [Mistral Status](https://status.mistral.ai) for service outages
    * Try a different model temporarily
    * Verify your network connection
  </Accordion>
</AccordionGroup>