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

# DeepSeek

> Use DeepSeek models in your BoostGPT agents

## Overview

DeepSeek offers powerful AI models with specialized reasoning capabilities. DeepSeek R1 is particularly strong at complex reasoning and analytical tasks.

## Available Models

<CardGroup cols={2}>
  <Card title="DeepSeek V3" icon="brain-circuit">
    **1 credit** " General-purpose chat model

    * 64K context window
    * Good reasoning for everyday tasks
    * Speed: Fast " Cost: Low
    * Best for: Conversations, general tasks
  </Card>

  <Card title="DeepSeek R1" icon="brain">
    **2 credits** " Specialized reasoning model

    * 64K context window
    * Excellent logical and analytical capabilities
    * Speed: Medium " Cost: Medium
    * **Reasoning model** for complex problems
  </Card>
</CardGroup>

## Setup

### Using BoostGPT-Hosted API Keys

<Steps>
  <Step title="Select DeepSeek Model">
    In your BoostGPT dashboard, select DeepSeek V3 or R1 when creating or configuring your bot.
  </Step>

  <Step title="Choose Your Model">
    * **DeepSeek V3**: For general chat and conversations
    * **DeepSeek R1**: For complex reasoning and analysis
  </Step>
</Steps>

### Using Your Own DeepSeek API Key

<Tabs>
  <Tab title="Dashboard Setup">
    <Steps>
      <Step title="Navigate to Integrations">
        Go to [app.boostgpt.co](https://app.boostgpt.co/integrations) and select **Integrations**
      </Step>

      <Step title="Select DeepSeek">
        Find and click on the **DeepSeek** provider
      </Step>

      <Step title="Add API Key">
        Enter your DeepSeek API key and select which agents will use this key
      </Step>

      <Step title="Save Configuration">
        Click save to apply your custom API key
      </Step>
    </Steps>
  </Tab>

  <Tab title="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 DeepSeek model
    const botResponse = await client.createBot({
      name: 'My DeepSeek Bot',
      model: 'deepseek-reasoner', // R1 model
      instruction: 'You are a logical and analytical assistant.',
      max_reply_tokens: 1000,
      status: 'active'
    });

    if (botResponse.err) {
      console.error('Error:', botResponse.err);
    } else {
      console.log('Bot created:', botResponse.response);
    }
    ```
  </Tab>

  <Tab title="Router SDK">
    ```javascript router.js theme={null}
    import { Router, TelegramAdapter } from '@boostgpt/router';

    const router = new Router({
      apiKey: process.env.BOOSTGPT_API_KEY,
      projectId: process.env.BOOSTGPT_PROJECT_ID,
      defaultBotId: process.env.BOOSTGPT_BOT_ID, // DeepSeek bot
      adapters: [
        new TelegramAdapter({
          telegramToken: process.env.TELEGRAM_TOKEN
        })
      ]
    });

    // Router handles DeepSeek automatically
    router.onMessage(async (message, context) => {
      // Custom commands only
      if (message.content === '/help') {
        return 'I use DeepSeek for reasoning!';
      }

      return null; // Let DeepSeek handle it
    });

    await router.start();
    ```
  </Tab>
</Tabs>

## Model Selection Guide

<AccordionGroup>
  <Accordion icon="brain-circuit" title="DeepSeek V3 - General Chat">
    **Best for:**

    * Customer support chatbots
    * General conversations
    * Simple queries and responses
    * Cost-effective deployments

    **Cost:** 1 credit per request (very affordable)
  </Accordion>

  <Accordion icon="brain" title="DeepSeek R1 - Reasoning Tasks">
    **Best for:**

    * Mathematical problem solving
    * Code analysis and debugging
    * Logical reasoning tasks
    * Complex analytical work

    **Note:** Reasoning model with min 2000 completion tokens

    **Cost:** 2 credits per request
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Reasoning Models" icon="brain" href="/providers/reasoning-models">
    Deep dive into DeepSeek R1
  </Card>

  <Card title="Model Comparison" icon="scale" href="/providers/model-comparison">
    Compare DeepSeek with others
  </Card>

  <Card title="SDK Reference" icon="code" href="/sdk/core/api-reference">
    Full API documentation
  </Card>

  <Card title="Provider Overview" icon="list" href="/providers/overview">
    See all providers
  </Card>
</CardGroup>