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

# Playground

> Chat with any of your endpoints before you wire it into a product.

The **Playground** lets you talk to any of your endpoints before you wire it into a
product. It is the quickest way to check how a fine-tuned version or a base model
answers.

<Frame caption="The Playground: a conversation with an endpoint, with a system prompt set on the right.">
  <img src="https://mintcdn.com/valkyrie-azumo/xmAOed5fcvjDfAgV/images/dashboard/playground.png?fit=max&auto=format&n=xmAOed5fcvjDfAgV&q=85&s=606a652fb2ff41a861a07a7422fd966e" alt="Valkyrie Playground screen" width="2880" height="1800" data-path="images/dashboard/playground.png" />
</Frame>

## Chat with an endpoint

<Steps>
  <Step title="Pick an endpoint">
    Choose one of your running endpoints in the **Endpoint** card. Base-model
    endpoints are marked **(base)**. **Open endpoint** takes you to its page.
  </Step>

  <Step title="Adjust the settings (optional)">
    Add a **System prompt** with instructions for every reply, and set the
    **Temperature** and **Max tokens**.
  </Step>

  <Step title="Send a message">
    Type a message and press **Enter** to send it. **Shift+Enter** adds a new line.
    Click **Clear** to start over.
  </Step>
</Steps>

If you have no running endpoint, the Playground shows links to deploy one. See
[Endpoints](/dashboard/endpoints).

<Tip>
  Getting an empty reply? Some models think before they answer, and that thinking
  counts toward **Max tokens**. If the limit is low, the model can use it all up
  before it writes the answer. Raise **Max tokens** (the default of 512 is enough
  for most questions) and send the message again.
</Tip>

<Note>
  Messages you send here are real requests to your endpoint, so the endpoint must be
  running. Comparing a fine-tuned version side by side with its base model is marked
  **Coming soon**.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.