> ## 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.

# Cohere

> Learn how to use Cohere models in Agno.

Leverage Cohere's powerful command models and more.

[Cohere](https://cohere.com) has a wide range of models and is really good for fine-tuning. See their library of models [here](https://docs.cohere.com/v2/docs/models).

We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

* `command` model is good for most basic use-cases.
* `command-light` model is good for smaller tasks and faster inference.
* `command-r7b-12-2024` model is good with RAG tasks, complex reasoning and multi-step tasks.

Cohere also supports fine-tuning models. Here is a [guide](https://docs.cohere.com/v2/docs/fine-tuning) on how to do it.

Cohere has tier-based rate limits. See the [docs](https://docs.cohere.com/v2/docs/rate-limits) for more information.

## Authentication

Set your `CO_API_KEY` environment variable. Get your key from [here](https://dashboard.cohere.com/api-keys).

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

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

## Example

Use `Cohere` with your `Agent`:

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

  agent = Agent(
      model=Cohere(id="command-r-08-2024"),
      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/cohere). </Note>

## Params

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

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