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

# Requesty

> Use Requesty AI gateway with Agno agents.

<Badge icon="code-branch" color="orange">
  <Tooltip tip="Introduced in v2.1.0" cta="View release notes" href="https://github.com/agno-agi/agno/releases/tag/v2.1.0">v2.1.0</Tooltip>
</Badge>

Requesty AI is an LLM gateway with AI governance, providing unified access to various language models with built-in governance and monitoring capabilities.

Learn more about Requesty's features at [requesty.ai](https://www.requesty.ai).

## Authentication

Set your `REQUESTY_API_KEY` environment variable. Get your key from Requesty.

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

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

## Example

Use `Requesty` with your `Agent`:

<CodeGroup>
  ```python agent.py theme={null}
  from agno.agent import Agent
  from agno.models.requesty import Requesty

  agent = Agent(model=Requesty(id="openai/gpt-4o"), markdown=True)

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

  ```
</CodeGroup>

<Note> View more examples [here](/models/providers/gateways/requesty/usage/basic-stream). </Note>

## Params

| Parameter    | Type            | Default                           | Description                                                       |
| ------------ | --------------- | --------------------------------- | ----------------------------------------------------------------- |
| `id`         | `str`           | `"openai/gpt-4.1"`                | The id of the model to use through Requesty                       |
| `name`       | `str`           | `"Requesty"`                      | The name of the model                                             |
| `provider`   | `str`           | `"Requesty"`                      | The provider of the model                                         |
| `api_key`    | `Optional[str]` | `None`                            | The API key for Requesty (defaults to REQUESTY\_API\_KEY env var) |
| `base_url`   | `str`           | `"https://router.requesty.ai/v1"` | The base URL for the Requesty API                                 |
| `max_tokens` | `int`           | `1024`                            | The maximum number of tokens to generate                          |

`Requesty` also supports the params of [OpenAI](/reference/models/openai).