> ## 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.

# DeepSeek

> Configure DeepSeek models in EnConvo

## Overview

DeepSeek provides high-quality language models at very competitive prices, including their advanced reasoning model DeepSeek R1.

## Supported Models

| Model                 | Description        | Best For         |
| --------------------- | ------------------ | ---------------- |
| **DeepSeek Chat**     | General chat model | Daily tasks      |
| **DeepSeek Reasoner** | Advanced reasoning | Complex problems |

## Setup

<Steps>
  <Step title="Get API Key">
    1. Go to [DeepSeek Platform](https://platform.deepseek.com)
    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 **DeepSeek**
    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          | DeepSeek Chat |
| **Temperature** | Creativity (0-2)      | 0.6           |

## Validate and Use

<Steps>
  <Step title="Validate credentials">
    Click **Validate** in the DeepSeek credential settings. If validation fails, confirm the API key is active and your DeepSeek account has available balance.
  </Step>

  <Step title="Choose the model type">
    Use **DeepSeek Chat** for general work and **DeepSeek Reasoner** when you need multi-step reasoning, coding analysis, or math.
  </Step>

  <Step title="Test response latency">
    Send a short prompt first. Reasoning requests can take longer than chat requests because the model spends more time thinking.
  </Step>
</Steps>

## Reasoning Effort

For DeepSeek Reasoner model:

| Level      | Description        |
| ---------- | ------------------ |
| **Low**    | Fast, economical   |
| **Medium** | Balanced           |
| **High**   | Thorough reasoning |

## Pricing

DeepSeek offers very competitive pricing:

| Model             | Input       | Output      |
| ----------------- | ----------- | ----------- |
| DeepSeek Chat     | \~\$0.14/1M | \~\$0.28/1M |
| DeepSeek Reasoner | \~\$0.55/1M | \~\$2.19/1M |

<Note>
  DeepSeek is one of the most affordable high-quality providers available.
</Note>

## Best Practices

<AccordionGroup>
  <Accordion title="Model Selection">
    * **DeepSeek Chat**: General conversations, writing
    * **DeepSeek Reasoner**: Math, coding, complex analysis
  </Accordion>

  <Accordion title="Cost Optimization">
    DeepSeek is already very affordable - use Reasoner when you need advanced capabilities
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection issues">
    * Check your network connection
    * Verify API key is correct
  </Accordion>

  <Accordion title="Slow responses">
    * DeepSeek Reasoner takes longer for complex tasks
    * This is normal for reasoning models
  </Accordion>
</AccordionGroup>