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

# Playground

> Start a short-lived service from a checkpoint, chat with it, and compare two, at /playground.

Short-lived model trials at `/playground`. A session has a TTL and is reclaimed on its own.

For a stable endpoint with tokens, recovery and revisions, use a
[Model Deployment](https://docs.tuneplane.ai/en/console/deployments.md) instead.

![TunePlane playground](https://mintcdn.com/starforge/GatXR2rI5-_Vm4_H/images/console/playground.png?fit=max\&auto=format\&n=GatXR2rI5-_Vm4_H\&q=85\&s=60e3f28ece1f524a4193cb0099f2ba19)

Playground: start a vLLM service from a training export or an HF id.

## What you can do

### Start a session

1. Choose a model: the **training artifacts** dropdown (runs with an hf\_export), or directly enter an HF id / shared-storage path;
2. Choose GPU count (= tensor parallelism) and TTL;
3. Launch. The status card updates in real time: starting → ready → remaining TTL.

### Chat

Streaming output, with a system prompt, temperature and max tokens you can change between turns.

The conversation lives on the page and nowhere else: a refresh clears it, and nothing is stored.
Use a [Model Deployment](https://docs.tuneplane.ai/en/console/deployments.md) with Reflow when you want the exchange kept.

### Compare two side by side

Pick two ready services side by side: the same input is sent to both simultaneously and the outputs render in parallel — alignment differences between SFT vs GRPO, or v1 vs v2, become directly visible.

### Manage your sessions

The page lists **all of my services**: endpoint address, GPUs occupied, remaining TTL, renew / stop buttons. Services are automatically reclaimed when their TTL expires (guarding against "started it and forgot to shut it down").

## When the page is not there

The Playground is a premium feature an administrator enables per role, and it runs only on
`node` and `kubernetes` Fleets. Node sessions reserve a host port and report the selected Node's workload address; the control plane must be able to reach that address and port. Slurm is unsupported.

> [!WARNING]
>
> A Playground session offers no availability contract and no stable address. Do not point a
> production or durable internal application at one.

## Next

[Chatting with a checkpoint](https://docs.tuneplane.ai/en/guides/playground.md) ·
[Deployments](https://docs.tuneplane.ai/en/console/deployments.md) · [Models](https://docs.tuneplane.ai/en/console/models.md)


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