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

# Chat completion using Groq Endpoint

> Sends a request for chat completions. For more details on parameters, visit [Groq Cloud](https://console.groq.com/docs/api-reference#chat-create).

### Request Body

<ParamField body="messages" type="array" required>
  Array of messages to send to the chat model.

  <Expandable title="properties" type="object">
    <ParamField body="role" type="string" required>
      The role of the message sender (e.g., 'user' or 'assistant' or 'system').
    </ParamField>

    <ParamField body="content" type="string" required>
      The content of the message.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="model" type="string" required>
  The [model](https://console.groq.com/docs/api-reference#models-list) to use for chat completion.
</ParamField>

<ParamField body="stream" type="boolean">
  Whether to stream the response or not.
</ParamField>

### 200 - Successful chat completion response

<ResponseField name="id" type="string">
  The unique identifier for the chat completion request.
</ResponseField>

<ResponseField name="object" type="string">
  The type of the object returned, typically 'chat.completion'.
</ResponseField>

<ResponseField name="created" type="integer">
  The timestamp of when the chat completion was created.
</ResponseField>

<ResponseField name="model" type="string">
  The model used for generating the chat completion.
</ResponseField>

<ResponseField name="system_fingerprint" type="string">
  Fingerprint of the system, if available.
</ResponseField>

<ResponseField name="choices" type="array">
  The array of completion choices.

  <Expandable title="properties" type="object">
    <ResponseField name="index" type="integer">
      The index of the choice.
    </ResponseField>

    <ResponseField name="message" type="object">
      The message returned by the model.

      <Expandable title="properties" type="object">
        <ResponseField name="role" type="string">
          The role of the message sender (e.g., 'assistant').
        </ResponseField>

        <ResponseField name="content" type="string">
          The content of the message.
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="finish_reason" type="string">
      The reason the completion ended (e.g., 'stop').
    </ResponseField>

    <ResponseField name="logprobs" type="object">
      Log probabilities of the tokens, if available.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  Usage statistics for the request.

  <Expandable title="properties" type="object">
    <ResponseField name="prompt_tokens" type="integer">
      The number of tokens in the prompt.
    </ResponseField>

    <ResponseField name="completion_tokens" type="integer">
      The number of tokens in the completion.
    </ResponseField>

    <ResponseField name="total_tokens" type="integer">
      The total number of tokens used in the request.
    </ResponseField>

    <ResponseField name="prompt_time" type="float">
      The time taken for the prompt processing.
    </ResponseField>

    <ResponseField name="completion_time" type="float">
      The time taken for the completion processing.
    </ResponseField>

    <ResponseField name="total_time" type="float">
      The total time taken for the request.
    </ResponseField>
  </Expandable>
</ResponseField>

### 400 - Error response

<ResponseField name="error" type="string">
  The error message explaining what went wrong.
</ResponseField>

<ResponseExample>
  ```json 200 theme={null}
  {
    "id": "34a9110d-c39d-423b-9ab9-9c748747b204",
    "object": "chat.completion",
    "created": 1708045122,
    "model": "mixtral-8x7b-32768",
    "system_fingerprint": null,
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "Low latency Large Language Models (LLMs) are important in the field of artificial intelligence and natural language processing (NLP) for several reasons:\n\n1. Real-time applications: Low latency LLMs are essential for real-time applications such as chatbots, voice assistants, and real-time translation services. These applications require immediate responses, and high latency can lead to a poor user experience.\n\n2. Improved user experience: Low latency LLMs provide a more seamless and responsive user experience. Users are more likely to continue using a service that provides quick and accurate responses, leading to higher user engagement and satisfaction.\n\n3. Competitive advantage: In today's fast-paced digital world, businesses that can provide quick and accurate responses to customer inquiries have a competitive advantage. Low latency LLMs can help businesses respond to customer inquiries more quickly, potentially leading to increased sales and customer loyalty.\n\n4. Better decision-making: Low latency LLMs can provide real-time insights and recommendations, enabling businesses to make better decisions more quickly. This can be particularly important in industries such as finance, healthcare, and logistics, where quick decision-making can have a significant impact on business outcomes.\n\n5. Scalability: Low latency LLMs can handle a higher volume of requests, making them more scalable than high-latency models. This is particularly important for businesses that experience spikes in traffic or have a large user base.\n\nIn summary, low latency LLMs are essential for real-time applications, providing a better user experience, enabling quick decision-making, and improving scalability. As the demand for real-time NLP applications continues to grow, the importance of low latency LLMs will only become more critical."
        },
        "finish_reason": "stop",
        "logprobs": null
      }
    ],
    "usage": {
      "prompt_tokens": 24,
      "completion_tokens": 377,
      "total_tokens": 401,
      "prompt_time": 0.009,
      "completion_time": 0.774,
      "total_time": 0.783
    }
  }
  ```

  ```json 400 theme={null}
  {
    "error": "error message"
  }
  ```
</ResponseExample>