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

# API Playground

> Configure routing strategies, fallbacks, retries, and reliability behavior for model requests.

## Overview

The **Transform Request Playground** helps you understand how a generic request sent to LLMGrid is transformed into a provider‑specific API call. This is useful for debugging, validation, and learning how routing and normalization work under the hood.

***

## Purpose

This view is designed to:

* Visualize request normalization
* Show how model aliases and parameters are mapped
* Help developers debug provider‑specific behavior
* Validate request structure before production use

***

## Layout

The screen is divided into two panels:

* **Original Request** (left)
* **Transformed Request** (right)

A **Transform** action generates the provider‑specific output.

***

## Original Request

The **Original Request** panel shows the request payload as it is submitted to the LLMGrid API.

### What it contains

* Model reference (for example, a logical or routed model)
* Messages or input payload
* Optional parameters such as temperature or max tokens

This request matches what you would send to the LLMGrid `/chat/completions` or equivalent endpoint.

**Example structure**

```json theme={null}
{
  "model": "openai/gpt-4o",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ]
}
``
```