> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Groq

> Learn how to use Groq with Agno.

Groq offers blazing-fast API endpoints for large language models.

See all the Groq supported models [here](https://console.groq.com/docs/models).

* We recommend using `llama-3.3-70b-versatile` for general use
* We recommend `llama-3.1-8b-instant` for a faster result.
* We recommend using `llama-3.2-90b-vision-preview` for image understanding.

#### Multimodal Support

With Groq we support `Image` as input

## Authentication

Set your `GROQ_API_KEY` environment variable. Get your key from [here](https://console.groq.com/keys).

<CodeGroup>
  ```bash Mac theme={null}
  export GROQ_API_KEY=***
  ```

  ```bash Windows theme={null}
  setx GROQ_API_KEY ***
  ```
</CodeGroup>

## Example

Use `Groq` with your `Agent`:

<CodeGroup>
  ```python agent.py theme={null}
  from agno.agent import Agent, RunResponse
  from agno.models.groq import Groq

  agent = Agent(
      model=Groq(id="llama-3.3-70b-versatile"),
      markdown=True
  )

  # Print the response in the terminal
  agent.print_response("Share a 2 sentence horror story.")

  ```
</CodeGroup>

<Note> View more examples [here](../examples/models/groq). </Note>

## Params

<Snippet file="model-groq-params.mdx" />

`Groq` is a subclass of the [Model](/reference/models/model) class and has access to the same params.