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

# Groq

> Route Groq model calls through Keywords AI Gateway using your own Groq credits.

<Note> This section is for **Keywords AI LLM gateway** users.</Note>

Use Keywords AI Gateway to call **Groq** models while keeping unified observability (logs, cost, latency, and reliability metrics) in Keywords AI — and optionally charge usage to **your own Groq credits**.

## Prerequisites

* A **Keywords AI API key**
* A **Groq API key** (BYOK credits)

<CardGroup cols={1}>
  <Card title="Get Groq API key" icon="key" href="https://console.groq.com/keys">
    Retrieve your API key from the Groq Console to begin integration.
  </Card>
</CardGroup>

## Supported SDKs / integrations

<AccordionGroup>
  <Accordion title="✅ Supported Frameworks">
    * [OpenAI SDK](/integration/development-frameworks/llm_framework/openai/openai-sdk)
    * [LangChain SDK](/integration/development-frameworks/llm_framework/langchain)
    * [Vercel/OpenAI](/integration/development-frameworks/llm_framework/vercel#openai)
    * [Vercel/Google](/integration/development-frameworks/llm_framework/vercel#google)
    * [LlamaIndex SDK](/integration/development-frameworks/llm_framework/llama-index)
    * [Google GenAI](/integration/development-frameworks/llm_framework/google_genai)
    * [Keywords native (Otel)](/get-started/quickstart/gateway)
  </Accordion>

  <Accordion title="❌ Unsupported Frameworks">
    * [Anthropic SDK](/integration/development-frameworks/llm_framework/anthropic)
    * [Vercel/Anthropic](/integration/development-frameworks/llm_framework/vercel#anthropic)
  </Accordion>
</AccordionGroup>

## Configuration

There are 2 ways to add your Groq credentials to your requests:

### Via UI (Global)

<Steps>
  <Step title="Navigate to Providers">
    Go to the [Providers page](https://platform.keywordsai.co/platform/api/providers). This page allows you to manage credentials for over 20+ supported providers.

    <Frame>
      <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/settings/providers.jpg" alt="Keywords AI Providers Page" />
    </Frame>
  </Step>

  <Step title="Add your Groq API Key">
    Select Groq and paste your API key.

    <Frame>
      <img src="https://mintcdn.com/keywordsai/-egFtHX1IBbYpy-e/images/providers/groq.png?fit=max&auto=format&n=-egFtHX1IBbYpy-e&q=85&s=41a7f14cad3271d62a39c89e0ed6457b" alt="Add Groq Credentials" width="1126" height="900" data-path="images/providers/groq.png" />
    </Frame>
  </Step>

  <Step title="Configure Load Balancing (Optional)">
    You can add multiple Groq API keys for redundancy. Use the `Load balancing weight` field to determine how traffic is distributed between keys.
  </Step>
</Steps>

### Via code (Per-Request)

You can pass credentials dynamically in the request body. This is useful if you need to use your users' own API keys (BYOK credits).

Add the `customer_credentials` parameter to your [Gateway request](/api-endpoints/develop/gateway/chat-completions):

```json theme={"system"}
{
  // Rest of the request body
  "customer_credentials": {
    "groq": {
      "api_key": "YOUR_GROQ_API_KEY"
    }
  }
}
```

## Override credentials for a particular model (Optional)

If you uploaded provider credentials in the UI, you can still override credentials for specific models on a per-request basis.

```json theme={"system"}
{
  // Rest of the request body
  "customer_credentials": {
    "groq": {
      "api_key": "YOUR_GROQ_API_KEY"
    }
  },
  "credential_override": {
    "groq/llama-3.1-8b-versatile": {
      "api_key": "ANOTHER_GROQ_API_KEY"
    }
  }
}
```

## Log Groq requests

If you are not using the Gateway to proxy requests, you can still log your Groq requests to Keywords AI asynchronously. This allows you to track cost, latency, and performance metrics for external calls.

```python Groq Python SDK theme={"system"}
import requests

url = "https://api.keywordsai.co/api/request-logs/create/"
payload = {
    "model": "llama3-8b-8192",
    "prompt_messages": [
        {
            "role": "user",
            "content": "Write a short poem about AI"
        }
    ],
    "completion_message": {
        "role": "assistant",
        "content": "In circuits bright and data streams, AI awakens from digital dreams..."
    },
    "cost": 0.0001,
    "generation_time": 0.8,
    "customer_params": {
        "customer_identifier": "user_101"
    }
}
headers = {
    "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, headers=headers, json=payload)
```

<Card title="Get Started with Logging" icon="rocket" href="/documentation/products/logs/quickstart"> Learn how to set up comprehensive logging for all your LLM requests </Card>