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

# DeepSeek

> Set up DeepSeek & understand how it's used throughout the app

DeepSeek offers powerful reasoning capabilities at competitive pricing. Their chat model comes with built-in thinking/reasoning mode, making it a solid choice if you want to give your users another strong reasoning option alongside the other providers.

## Get your API key

<Steps>
  <Step title="Create or sign into your DeepSeek account">
    Head to the [DeepSeek Platform](https://platform.deepseek.com/) and sign up or log in.
  </Step>

  <Step title="Create an API key">
    Navigate to the API keys section and create a new key.
  </Step>

  <Step title="Add it to your env">
    Paste the key in your `.env.local` file:

    ```env theme={null}
    DEEPSEEK_API_KEY=your_deepseek_api_key
    ```
  </Step>
</Steps>

<Warning>
  Save your API key somewhere safe right away -- you won't be able to see it again.
</Warning>

## Available models

All models are defined in the unified model registry at `lib/ai/models.ts`.

| Model         | ID              | Features           |
| ------------- | --------------- | ------------------ |
| DeepSeek Chat | `deepseek-chat` | Thinking/Reasoning |

<Tip>
  DeepSeek Chat supports **thinking/reasoning mode** -- the model shows its chain of thought before giving you the final answer. This is particularly useful for complex problem-solving and analysis tasks.
</Tip>

## Apps using DeepSeek

DeepSeek is integrated through Vercel AI SDK 6.0, with provider routing handled by `lib/ai/ai-utils.ts`.

<CardGroup cols={1}>
  <Card title="Chat" icon="comments" href="/apps/chat">
    Multi-provider chat app -- DeepSeek is available as an LLM provider
  </Card>
</CardGroup>

## How it works

The codebase uses Vercel AI SDK 6.0 with a unified model registry -- no direct DeepSeek API calls needed.

Here's the typical flow for an AI request:

1. You select a model from the unified registry
2. The request goes through `getModelInstance()` in `lib/ai/ai-utils.ts`
3. The provider is determined via `getProviderFromModelId()`
4. The model is instantiated with `customModel()`
5. The response is streamed back to you
6. Results are stored in PostgreSQL

<Card title="Structure" icon="folder" href="/setup/structure">
  Understand the full project structure of the codebase.
</Card>