> ## Documentation Index
> Fetch the complete documentation index at: https://promptlayer-cursor-pro-221-issue-resolution-task-071d.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Playground

The Playground is a native way to create and run new LLM requests all through PromptLayer. Your run history will be tracked in the sidebar. The Playground is most useful as a tool to "replay" and debug old requests.

## Replay requests

The Playground allows PromptLayer users to rerun previous LLM requests. Simply click "Open in Playground" on any historical request.

<div style={{width: '90%'}}>
  <img src="https://mintcdn.com/promptlayer-cursor-pro-221-issue-resolution-task-071d/HYrmZ_o9JW2lLh6x/images/playground/open-in-playground.png?fit=max&auto=format&n=HYrmZ_o9JW2lLh6x&q=85&s=84a38350274c7704cde5fb5b1da53adf" alt="Open in Playground screenshot" width="1248" height="498" data-path="images/playground/open-in-playground.png" />
</div>

## OpenAI Tools

The Playground fully supports [OpenAI function calling](https://platform.openai.com/docs/guides/function-calling). These tools can be accessed directly from the Playground interface and can be incorporated into your requests as needed. *Not even OpenAI's playground does this 👀*

<div style={{width: '70%'}}>
  <img src="https://mintcdn.com/promptlayer-cursor-pro-221-issue-resolution-task-071d/HYrmZ_o9JW2lLh6x/images/playground/tools.png?fit=max&auto=format&n=HYrmZ_o9JW2lLh6x&q=85&s=5b1f969b034d50596324d7800dac710c" alt="Tools dialogue" width="1740" height="1200" data-path="images/playground/tools.png" />
</div>

## Image Generation

The Playground supports image generation across multiple providers:

* **OpenAI Images API** — Select "Images API" in the API dropdown to use models like `gpt-image-1`, `dall-e-3`, and `dall-e-2`. Write a text prompt and receive generated images directly in the output.
* **OpenAI Responses API** — Add the `image_generation` built-in tool to let the model generate images during a conversation.
* **Google Gemini** — Select a Gemini image model (e.g., `gemini-2.5-flash-image`) to generate images natively within chat responses.

Generated images are displayed with a rich card showing generation parameters, the revised prompt (when available), and the image itself. See the full [Image Generation guide](/features/image-generation) for details.

<img src="https://mintcdn.com/promptlayer-cursor-pro-221-issue-resolution-task-071d/HYrmZ_o9JW2lLh6x/images/image-generation-playground.png?fit=max&auto=format&n=HYrmZ_o9JW2lLh6x&q=85&s=1f791d876a8dbe1c83c5fef5eb6bde90" alt="Playground with generated image output" width="2836" height="1362" data-path="images/image-generation-playground.png" />

## Custom models

The Playground also supports the use of custom models for LLM requests. This means you can use a fine-tuned model or a dedicated OpenAI instance.