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

# DeepSeek

> Track costs for DeepSeek models

This guide covers how to send DeepSeek usage data to Fenra.

## DeepSeek API

DeepSeek's API follows the OpenAI format:

<CodeGroup>
  ```javascript Node.js theme={null}
  async function chat(messages) {
    const response = await fetch('https://api.deepseek.com/chat/completions', {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'Authorization': `Bearer ${process.env.DEEPSEEK_API_KEY}`
      },
      body: JSON.stringify({
        model: 'deepseek-chat',
        messages
      })
    });

    const result = await response.json();

    // Send to Fenra
    await fetch('https://ingest.fenra.io/usage/transactions', {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'X-Api-Key': process.env.FENRA_API_KEY
      },
      body: JSON.stringify({
        provider: 'deepseek',
        model: result.model,
        usage: [{
          type: 'tokens',
          metrics: {
            input_tokens: result.usage.prompt_tokens,
            output_tokens: result.usage.completion_tokens,
            total_tokens: result.usage.total_tokens
          }
        }],
        context: {
          billable_customer_id: process.env.BILLABLE_CUSTOMER_ID
        }
      })
    });

    return result;
  }
  ```

  ```python Python theme={null}
  import requests
  import os

  def chat(messages):
      response = requests.post(
          'https://api.deepseek.com/chat/completions',
          headers={
              'Content-Type': 'application/json',
              'Authorization': f'Bearer {os.getenv("DEEPSEEK_API_KEY")}'
          },
          json={
              'model': 'deepseek-chat',
              'messages': messages
          }
      )

      result = response.json()

      # Send to Fenra
      requests.post(
          'https://ingest.fenra.io/usage/transactions',
          headers={
              'Content-Type': 'application/json',
              'X-Api-Key': os.getenv('FENRA_API_KEY')
          },
          json={
              'provider': 'deepseek',
              'model': result['model'],
              'usage': [{
                  'type': 'tokens',
                  'metrics': {
                      'input_tokens': result['usage']['prompt_tokens'],
                      'output_tokens': result['usage']['completion_tokens'],
                      'total_tokens': result['usage']['total_tokens']
                  }
              }],
              'context': {
                  'billable_customer_id': os.getenv('BILLABLE_CUSTOMER_ID')
              }
          }
      )

      return result
  ```
</CodeGroup>

## DeepSeek Reasoner

For reasoning models, include reasoning tokens:

```javascript theme={null}
usage: [{
  type: 'tokens',
  metrics: {
    input_tokens: result.usage.prompt_tokens,
    output_tokens: result.usage.completion_tokens,
    total_tokens: result.usage.total_tokens,
    reasoning_tokens: result.usage.completion_tokens_details?.reasoning_tokens || 0
  }
}]
```

## Supported Models

Fenra supports all DeepSeek models. Common models include:

| Model               | Description                     |
| ------------------- | ------------------------------- |
| `deepseek-chat`     | General chat                    |
| `deepseek-coder`    | Code-optimized                  |
| `deepseek-reasoner` | Reasoning with chain-of-thought |

## Next Steps

* [Compare DeepSeek costs](/product-overview/cost-explorer/breakdown) with other providers