👋Welcome to ModelSync's API Documentation

New to APIs? Don't worry!

We've made the documentation as beginner-friendly as possible.

Simply, follow the Quick Start Guide to start generating with AI in seconds or check out the Brief Overview to learn more.

🚀Quick Start Guide

1Get Your API Key

Get API Key →

2Add Your API Key to Requests

Include your API key in the header of every request:

Authorization: Bearer $YOUR_API_KEY

3Make Your API Call

Make a POST request to our API endpoint with your prompt details:

curl -X POST "https://api.modelsync.ai/v1/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d {
    "model": "Llama-3.3-70B-Instruct",
    "prompt": "Write a hello world message"
  }

4Get Your Response

The API will return a JSON response with your generated results:

{
    "id": "cmpl-19md72cf353",
    "object": "text_completion",
    "created": 1703262150,
    "model": "Llama-3.3-70B-Instruct",
    "choices": [
        {
            "text": "Hello, World! This is a simple example of AI-generated text.",
            "index": 0,
            "logprobs": null,
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 5,
        "completion_tokens": 13,
        "total_tokens": 18
    }
}

🔎Brief Overview

ModelSync provides OpenAI-compatible API access to open source AI models. This means any existing OpenAI client, application, or API call works without modification.

The service runs on vLLM, an open-source engine designed for efficient LLM inference and serving. See vLLM's documentation for technical details.