Forem: Sagar Sunil Bhedodkar

Toon 1.1.8 — Unlock Complex Nested Array Support for Laravel

Sagar Sunil Bhedodkar — Sat, 20 Dec 2025 14:10:57 +0000

🚀 Announcing Toon v1.1.8!

Toon is the Laravel-native token-optimized object notation (TOON) library designed to convert PHP arrays and JSON into a compact, human-readable, AI-ready format. With v1.1.8, Toon now fully supports complex nested arrays, enabling developers to handle deep structures efficiently while saving tokens and maintaining readability.

✨ Highlights of v1.1.8

inlineScalar now recursively handles nested arrays
Fully compatible with structures like users, profiles, orders, and more
Maintains TOON's compact, human-readable format
Boosts AI prompt efficiency, reduces token usage, and lowers API costs

🔹 Example Usage

PHP Array

$data = [
    'user' => [
        'id' => 101,
        'name' => 'Jane Developer',
        'roles' => ['admin', 'editor'],
    ],
    'orders' => [
        [
            'order_id' => 'ORD-1001',
            'items' => [
                ['sku'=>'SKU-11','name'=>'Keyboard','qty'=>1,'price'=>1200],
                ['sku'=>'SKU-22','name'=>'Mouse','qty'=>2,'price'=>399],
            ],
            'payment'=>['method'=>'upi','status'=>'paid','amount'=>1998],
        ],
    ],
];

TOON Output

user: id:101 name:Jane Developer roles: admin editor orders: items[1]{order_id,items,payment}: ORD-1001,0:sku:SKU-11,name:Keyboard,qty:1,price:1200,1:sku:SKU-22,name:Mouse,qty:2,price:399,method:upi,status:paid,amount:1998

Deeply nested arrays like items are fully supported, making TOON perfect for AI prompts and complex data workflows.

🔹 Installation

composer require sbsaga/toon

GitHub: https://github.com/sbsaga/toon
Packagist: https://packagist.org/packages/sbsaga/toon

🔹 Why It Matters

Reduces token usage by ~60-70% compared to JSON
Keeps your data human-readable for debugging and logging
Perfect for ChatGPT, Gemini, Claude, OpenAI, and other LLM integrations
Maintains backward compatibility for existing TOON structures

🔹 Quick Tip

You can convert your arrays with:

$toon = Toon::convert($data);
$stats = Toon::estimateTokens($toon);
print_r($stats);

This will give you an estimate of the token savings while keeping data compact.

💡 Pro Tip: Share your feedback, examples, or questions on the GitHub Discussions — your input drives the next improvements in TOON!

Experience token-efficient, readable AI-ready data now with Toon v1.1.8.

🚀 TOON for Laravel — A Complete Tutorial to Make AI Prompts Cheaper & Faster

Sagar Sunil Bhedodkar — Sun, 23 Nov 2025 15:41:17 +0000

🧠 TOON for Laravel — Make LLMs Cheaper, Faster & Friendlier

✨ Compress your prompts, not your ideas! ✨

AI costs money. Every token counts. That’s why I built TOON — a Laravel package that turns heavy JSON into light, readable, reversible notation for LLMs like ChatGPT, Gemini, Claude, and Mistral.

This tutorial is human-friendly, full of real examples, and easy to follow. Whether you’re a beginner or production-level developer — you’ll walk away with something useful. 🚀

📌 Why TOON Exists — The Real Problem

Sending big chunks of JSON to LLMs = 🧨 higher costs + slower responses. TOON solves this by:

📉 Reducing token usage by 60–75%
🔁 Keeping data reversible (TOON ⇄ JSON)
👀 Staying human-readable
⚡ Fully integrated with Laravel (Facade + Commands)

💡 “AI doesn’t need verbose data — it needs clean, structured context.”

🔥 TL;DR — Quick Summary

Step	Action
1️⃣	`composer require sbsaga/toon`
2️⃣	Use `Toon::convert()` before sending API requests
3️⃣	Measure token savings via `estimateTokens()`
4️⃣	Use in AI prompts & Artisan commands

🧪 Before vs After (Real Example)

❌ JSON (7.7 KB)

{
  "messages": [
    {"id": 1, "done": false},
    {"id": 2, "done": true},
    ...
  ]
}

✅ TOON (2.5 KB)

messages:
  items[2]{id,done}:
    1,false
    2,true

💥 67% smaller — SAME DATA — lower cost, faster AI.

⚙️ Installation

composer require sbsaga/toon

(Optional) Publish config

php artisan vendor:publish --provider="Sbsaga\Toon\ToonServiceProvider" --tag=config

Created file: config/toon.php

return [
  'enabled' => true,
  'escape_style' => 'backslash',
  'min_rows_to_tabular' => 2,
  'max_preview_items' => 200,
];

🚀 Usage — Most Common Pattern

use Sbsaga\Toon\Facades\Toon;

$data = [...];
$toon = Toon::convert($data);
$stats = Toon::estimateTokens($toon);

🧠 This alone can show you EXACT cost savings before using AI APIs.

🤖 Example — Sending to OpenAI

$prompt = "System: analyze this data\n" . $toon;

$response = Http::withToken(env('OPENAI_KEY'))->post(...);

$decoded = Toon::decode($response['choices'][0]['message']['content'] ?? '');

📊 Benchmark Route — Try It Yourself

Route::get('/toon-benchmark', function () {
  $json = json_decode(file_get_contents(storage_path('app/sample.json')), true);
  $jsonEncoded = json_encode($json, JSON_PRETTY_PRINT);
  $toonEncoded = Toon::convert($json);

  return [
    'json_size' => strlen($jsonEncoded),
    'toon_size' => strlen($toonEncoded),
    'saving_percent' => 100 - (strlen($toonEncoded) / strlen($jsonEncoded) * 100),
  ];
});

📦 Artisan Commands

php artisan toon:convert storage/test.json
php artisan toon:convert storage/test.toon --decode --pretty

🧠 AI Prompt Templates (Copy & Use)

You are an AI assistant. If you return structured data, use TOON format:

user: Sagar
items[2]{role,message}:
  user,Hello
  assistant,Hi there

Convert this JSON into TOON format and keep it reversible:
{ ... }

🛠️ Best Practices

✔ Use estimateTokens() before API calls
✔ Keep labels meaningful — AI understands better
✔ Use TOON for logs, chat history, search results
✔ Add fallback to raw JSON when needed

🧭 Ideal Use Cases

Use Case	Benefit
🤖 AI prompt engineering	Lower token usage
🔍 Log analysis	More readable than JSON
⚙ Debugging	Great for dev tools
📦 Microservices	Send smaller payloads

❤️ Contribute & Support

⭐ Star the repo — it helps a lot!
🐛 Report issues on GitHub
📌 Suggestions welcome

GitHub: https://github.com/sbsaga/toon
Packagist: https://packagist.org/packages/sbsaga/toon

🎯 Final Thought

🧠 “AI doesn’t need more data — it needs better data.”
That’s what TOON delivers. Try it, benchmark it — your AI will thank you. 🙌

🚀 Token Estimation for AI Prompts in Laravel — TOON

Sagar Sunil Bhedodkar — Sun, 23 Nov 2025 14:40:35 +0000

Write cleaner prompts. Spend fewer tokens. Build smarter AI apps.

🧠 What Problem Does It Solve?

Every time your Laravel app sends data to an AI model — it costs tokens. More tokens = more cost + less context.
But most developers don’t know how heavy their prompt really is.

That’s why TOON includes a built-in Token Estimator — a lightweight tool to quickly measure your prompt before sending it to an LLM.

✨ What Is TOON?

TOON (Token-Optimized Object Notation) is a compact, human-readable data format built for Laravel. It converts PHP arrays / JSON into an AI-friendly format that reduces token usage and improves context clarity.

And now — it can also estimate the token weight of that data.

🔢 Token Estimation — The Feature You Actually Need

TOON gives you a native, zero-dependency PHP method to estimate token usage:

use Sbsaga\Toon\Facades\Toon;

$prompt = Toon::convert($data);            // Converts JSON/PHP array to TOON format
$stats  = Toon::estimateTokens($prompt);   // Estimates token usage

dd($stats);

Example Output:

{
  "words": 20,
  "chars": 182,
  "tokens_estimate": 19
}

💡 Why This Helps Developers

✔ Spot heavy prompts instantly
✔ Reduce AI costs before making API calls
✔ Keep more context inside model limits
✔ Works locally, in CI, or before production
✔ No external tokenizer — fully PHP native

🧭 Practical Use Cases

Use Case	How TOON Helps
Local development	Measure prompt size while designing AI requests
CI check	Fail build if prompt > 3,000 tokens
Debugging	Compare JSON vs TOON format side-by-side
Optimization	Remove unnecessary data & observe impact
LLM cost control	Save real money over large requests

📌 Important Note

This is an approximate estimation, not a billing-accurate tokenizer.
It is model-agnostic, fast, and perfect for comparison / debugging.

🧪 Try It in 20 Seconds

composer require sbsaga/toon

📌 Ready-to-Use Tags (Paste into Medium / Dev.to)

laravel, php, ai, prompt-engineering, chatgpt, openai, ai-tooling, laravel-dev

🧠 “Compress your prompts, not your ideas.” — TOON helps you talk to AI efficiently.

Introducing TOON for Laravel — A Smarter, Token-Efficient Way to Talk to AI

Sagar Sunil Bhedodkar — Sat, 08 Nov 2025 20:35:50 +0000

🧠 TOON for Laravel — Compress your prompts, not your ideas

📝 License: MIT

⚡ Laravel: 9+

🐘 PHP: 8.1+

✨ Why TOON?

When building AI-powered Laravel apps, developers often struggle with massive JSON data, expensive token usage, and hard-to-read prompts. That’s where TOON comes in — a Laravel-native data compressor designed to make your AI payloads smaller, cleaner, and easier to understand. 💡

"Compress your prompts, not your ideas."

TOON transforms verbose JSON or PHP arrays into a compact, human-readable format that reduces token cost by up to 70%, while preserving every bit of data.

🚀 Quick Overview

Feature	Description
🔁 Bidirectional Conversion	Convert JSON ⇄ TOON effortlessly
🧩 Readable & Compact	YAML-like syntax with improved readability
💰 Token Efficient	Save up to 70% of AI token costs
⚙️ Laravel Native	Seamlessly integrates with facades, commands & service providers
📊 Built-in Analytics	Analyze compression & token estimates
🧠 AI Ready	Works perfectly with ChatGPT, Gemini, Claude & OpenAI APIs

🧠 What Makes TOON Different?

Unlike typical compression tools, TOON focuses on AI efficiency rather than binary storage. It’s designed for prompt engineering, where readability still matters. You can send structured data to your LLMs while keeping payloads light.

✅ Human-friendly like YAML, but optimized for tokenization.
✅ Built for Laravel developers — not just another JSON formatter.
✅ 100% reversible — decode TOON back into JSON with no loss.

💻 Installation & Setup

composer require sbsaga/toon

Once installed, TOON auto-registers its service provider and facade. Optionally, you can publish its config:

php artisan vendor:publish --provider="Sbsaga\\Toon\\ToonServiceProvider" --tag=config

Config File: config/toon.php

return [
    'enabled' => true,
    'escape_style' => 'backslash',
    'min_rows_to_tabular' => 2,
    'max_preview_items' => 200,
];

🧩 Convert JSON → TOON

use Sbsaga\Toon\Facades\Toon;

$data = [
    'user' => 'Sagar',
    'message' => 'Hello, how are you?',
    'tasks' => [
        ['id' => 1, 'done' => false],
        ['id' => 2, 'done' => true],
    ],
];

echo Toon::convert($data);

Output:

user: Sagar
message: Hello\, how are you?
tasks:
  items[2]{done,id}:
    false,1
    true,2

🔄 Convert TOON → JSON

$toon = <<<TOON
user: Sagar
tasks:
  items[2]{id,done}:
    1,false
    2,true
TOON;

print_r(Toon::decode($toon));

📊 Real-World Benchmark

Metric	JSON	TOON	Reduction
Size (bytes)	7,718	2,538	🔻 67.12% smaller
Tokens (est.)	1,930	640	💸 ~66.8% fewer tokens

💡 Less data = fewer tokens = lower API bills. Simple math, massive savings.

JSON (7.7 KB)
██████████████████████████████████████████████████████████████████████████

TOON (2.5 KB)
█████████████████

🧪 Quick Laravel Benchmark Route

use Illuminate\Support\Facades\Route;
use Sbsaga\Toon\Facades\Toon;

Route::get('/toon-benchmark', function () {
    $json = json_decode(file_get_contents(storage_path('app/users.json')), true);
    $toon = Toon::convert($json);

    return response()->json([
        'json_size' => strlen(json_encode($json)),
        'toon_size' => strlen($toon),
        'saving_percent' => round(100 - (strlen($toon) / strlen(json_encode($json)) * 100), 2),
        'toon_preview' => $toon,
    ]);
});

🧰 Artisan Commands

php artisan toon:convert storage/data.json
php artisan toon:convert storage/data.toon --decode
php artisan toon:convert storage/data.json --output=storage/result.toon

🌍 Real Use Cases

Use Case	Benefit
🤖 AI Prompt Engineering	Compress structured inputs for ChatGPT & Gemini
💬 LLM Context Management	Fit more data within token limits
🧾 Readable Logging	Store structured data compactly
⚙️ Microservice Communication	Reduce payload size across services

🔑 SEO & AI Integration Keywords

laravel, php, ai, chatgpt, openai, llm, gemini, mistral, anthropic, laravel-ai, laravel-openai, laravel-llm, php-ai, token-optimizer, prompt-engineering, api-optimization, backend-optimization, laravel-packages, php-development, web-development, json-compression, data-compression, efficient-coding, developer-tools, performance-optimization, api-integration, php-8.1

❤️ Final Thoughts

If you build AI tools with Laravel, TOON is a game-changer. It helps you:

🚀 Send more context without hitting token limits
🧩 Keep your data clean, readable, and reversible
💸 Save real money on AI API usage

🧠 “Compress your prompts, not your ideas.” — Let your code (and AI) breathe.

📦 GitHub: https://github.com/sbsaga/toon

📦 Packagist: https://packagist.org/packages/sbsaga/toon

Built with ❤️ for Laravel Developers who love clean, smart AI integrations.