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

# Models

You can select which large language model you'd like to power [Chat](/features/chat). At this time there's no option to select the [Autocomplete](/features/autocomplete) model as we've optimized a custom model for low latency specifically for this feature.

<CardGroup cols={2}>
  <Card title="Claude 3.7 Sonnet" icon="head-side-brain">
    Anthropic's newest and most capable LLM, released on Feb 24, 2025 as the third generation of
    Sonnet.
  </Card>

  <Card title="Claude 3.5 Sonnet (2024-10-22)" icon="head-side-brain">
    Anthropic's second iteration of Claude 3 Sonnet, released on Oct 22, 2024.
  </Card>

  <Card title="Claude 3 (Opus)" icon="head-side-brain">
    Anthropic's original Opus model.
  </Card>

  <Card title="DeepSeek R1" icon="head-side-brain">
    DeepSeek's reasoning model.
  </Card>

  <Card title="DeepSeek V3" icon="head-side-brain">
    DeepSeek's latest base model.
  </Card>

  <Card title="OpenAI o1-mini" icon="head-side-brain">
    OpenAI's highest performance model for coding and math tasks. Despite the name, this model is
    both faster and stronger than o1-preview on coding and math tasks!
  </Card>

  <Card title="OpenAI o1-preview" icon="head-side-brain">
    OpenAI's newest reasoning model designed to solve problems across generalist domains.
  </Card>

  <Card title="gpt-4o-2024-09-03" icon="head-side-brain">
    OpenAI's newest GPT-4o checkpoint.
  </Card>

  <Card title="gpt-4o-2024-08-06" icon="head-side-brain">
    OpenAI's 2024-08-06 checkpoint for GPT4o.
  </Card>

  <Card title="gpt-4o-2024-05-13" icon="head-side-brain">
    OpenAI's 2024-05-13 checkpoint for GPT4o.
  </Card>

  <Card title="GPT-4 Turbo" icon="head-side-brain">
    OpenAI's original GPT-4 Turbo.
  </Card>

  <Card title="Llama 3.1 405B" icon="head-side-brain">
    Meta's largest model. Open Source.
  </Card>

  <Card title="Llama 3.1 70B" icon="head-side-brain">
    The successor to Llama 3 70B.
  </Card>

  <Card title="Llama 3.1 8B" icon="head-side-brain">
    A small but fast Llama model.
  </Card>

  <Card title="Mistral Large 2" icon="head-side-brain">
    Mistral's newest and most capable LLM released on 7/24.
  </Card>
</CardGroup>

To see a real time leaderboard of how models rank, we recommend looking the [LMSYS leaderboard](https://chat.lmsys.org/?leaderboard) sorted by category 'coding'. Double will always have the most capable model set as the default when you first install.

### Coming Soon ([Click here to get notified](https://forms.gle/WeYfXdsTyLoxxQ6T9))

<CardGroup cols={2}>
  <Card title="GPT-5" icon="head-side-brain" iconType="solid">
    OpenAI's anticipated successor to GPT-4 and most capable coding LLM, available for early access on Double later this year.
  </Card>
</CardGroup>

### Selecting a Model

To change what model Double uses, go to the VS Code settings (`Cmd + ,` or `Ctrl + ,`), expand the Extensions dropdown on the left side of the screen, and select Double. Here you'll find a dropdown with all of the available models.

<img className="block mx-auto h-48 dark:hidden" src="https://mintcdn.com/double/dKjQdXGaKSgxICRk/images/settings_light.png?fit=max&auto=format&n=dKjQdXGaKSgxICRk&q=85&s=da13c25f5e457b1b5a438e8ce70cc0cf" width="1896" height="862" data-path="images/settings_light.png" />

<img className="hidden mx-auto h-48 dark:block" src="https://mintcdn.com/double/dKjQdXGaKSgxICRk/images/settings_dark.png?fit=max&auto=format&n=dKjQdXGaKSgxICRk&q=85&s=6127532ae516a380848fe2e3a9f06bff" width="1896" height="862" data-path="images/settings_dark.png" />