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

# Playground

> Test any model interactively in the dashboard.

The playground is an interactive chat interface in the dashboard for trying
models, tuning parameters, and prototyping prompts, without writing code.

<Note>
  The playground runs in the [dashboard](https://platform.omnia-voice.com/dashboard).
  Every run is metered and billed exactly like a production API call, so what you
  see in the playground matches what your integration will cost.
</Note>

## What you can do

<CardGroup cols={2}>
  <Card title="Try any model" icon="cubes">
    Pick any model in your catalog and chat with it.
  </Card>

  <Card title="Tune parameters" icon="sliders">
    Adjust temperature, max tokens, and other generation settings live.
  </Card>

  <Card title="Tools & JSON" icon="screwdriver-wrench">
    Test tool/function calling and structured (JSON) output.
  </Card>

  <Card title="See real cost" icon="wallet">
    Each response shows its tokens and exact cost, deducted from your wallet.
  </Card>
</CardGroup>

## Logged traffic, without writing code

When [request logging](/reference/request-logging) is on for your workspace,
playground chats are logged **exactly like production traffic**: the exchange
goes through the gateway's own pipeline: secret-scrubbed, stamped with your
retention window, and visible in Logs within seconds. Each response shows a
quiet "Logged to your workspace" chip once the log has actually landed (and an
honest note instead when logging is off or the log failed; a logging hiccup
never affects the chat itself).

Set a **Tag** on your playground session ("support", "extraction", …) and the
traffic is labeled everywhere tags work: filters, datasets, judge
populations. Different system prompts form separate
[segments](/concepts/segments) automatically.

This makes the playground the fastest way to try the whole improvement
workflow before integrating: chat a few times → grade the exchanges in Review → create
and calibrate a judge → run a comparison, all on traffic you generated in the
dashboard.

## From playground to code

Once a prompt works in the playground, reproduce it in your app with the same
model id and parameters; the playground uses the same inference path as the API.
See [Chat completions](/inference/chat) to move it into code.

## Billing

Playground usage draws from your prepaid wallet just like API usage. It's the
easiest way to sanity-check a model's cost and behavior before wiring it into
production.