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

# Playground

> Try a deployed model or agent in the dashboard before you integrate it in code

Two playgrounds live in the dashboard. Both use your account session (not a long-lived API key you paste yourself).

## Model playground

Open [Playground](https://platform.synapsai.cloud/playground). Pick a **Ready** or **Sleeping** model. The UI switches endpoints to match the pipeline, including:

* Chat / completions
* Embeddings
* Images
* Speech and transcriptions
* Text and token classification

Use it to sanity-check a launch, then copy the request into [Examples](/examples/introduction) or an [integration](/guides/integrations).

Navbar **Playground** in these docs points at this route.

## Agent playground

Open [Agent playground](https://platform.synapsai.cloud/agent-playground) after you [deploy an agent](/guides/agents). It streams the same AG-UI events as `POST /v1/agent/{agent_id}/run`. Tools, MCP, and knowledge bases come from the saved agent, not from extra request tools.

## Next steps

<Columns cols={2}>
  <Card title="Inference" icon="code" href="/guides/inference-quickstart">
    Call the same model from Python or cURL.
  </Card>

  <Card title="Examples" icon="file-code" href="/examples/introduction">
    Pipeline-specific request bodies.
  </Card>
</Columns>


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