Introduction

ModelPilot is a platform that makes deploying AI models simple, fast, and cost-effective. Deploy text, image, video, and multimodal models with just a few clicks, complete with optimized web interfaces and persistent storage.

Key Features:

Quick Deployment: Deploy AI models with our step-by-step wizard or use "Deploy Recommended" for one-click setup
Multiple Model Types: Support for text generation, image creation, video generation, multimodal, and embedding models
Persistent Storage: Your models, data, and generated content persist between sessions
Pay As You Go: Only pay for the compute resources you use every 10 minutes
Privacy Controls: Fine-grained privacy settings and zero-data retention options for sensitive workloads
Ready-to-Use Interfaces: Text models include OpenWebUI for chat, Image/Video models include ComfyUI with pre-built workflows

Getting Started

Creating an Account

To get started with Modelpilot.ai, follow these steps:

Visit the homepage and click "Sign Up Free"
Create an account with email/password or use Google/GitHub login
You'll be taken to your dashboard
Add credits through the billing page to start deploying models

Quick Deploy Guide

One of Modelpilot's most powerful features is our "Deploy Recommended" functionality that:

Analyzes your selected model and automatically determines the optimal infrastructure
Configures all settings including compute, memory, storage, and model parameters
Deploys in seconds with just one click, skipping manual configuration steps

Steps for Quick Deployment:

Select a model type (Text, Image, Video, Multimodal, Embedding)
Choose from pre-configured models or enter a Hugging Face model ID
Click "Deploy Recommended" for optimal settings, or customize manually
Monitor deployment progress through the dashboard
Access your running model through the provided web interface URL

Billing & Cost Management

Modelpilot uses a straightforward credit-based billing system:

Credits: The basic unit of payment (1 credit = $1.00 USD)
10-Minute Billing: All deployments are billed in 10-minute increments
Pay for What You Use: Only running deployments incur charges

Model Types & Interfaces

Text Generation Models

Text models deploy with OpenWebUI, providing a chat interface similar to ChatGPT:

Interactive chat interface
Adjustable parameters (temperature, max tokens, etc.)
Conversation history
Model switching and configuration
Available models: DeepSeek R1, Qwen3, QwQ, Mistral, Gemma 3, LLaMA 3.3, Magistral, and more

Image Generation Models

Image models deploy with ComfyUI, a node-based workflow interface:

Visual workflow editor
Pre-built workflows for common tasks
Custom node connections and parameters
Real-time image generation
Available models: Z Image Turbo, Flux Dev/Schnell, Stable Diffusion 3.5, SDXL, Qwen Image Gen

Video Generation Models

Video models also use ComfyUI with specialized video workflows:

Text-to-video and image-to-video workflows
Video parameter controls (resolution, frames, duration)
Preview and progress monitoring
Video download and sharing
Available models: Wan 2.1 and Wan 2.2 series

Using Your Deployments

Dashboard Operations

Manage your deployments through the dashboard:

Start/Stop: Control when your deployments are running (and being billed)
Access: Get direct links to your model interfaces
Monitor: View deployment status and resource usage
Logs: Debug issues with deployment logs

Deployment States

Your deployments go through several states:

Building: Docker image is being created (no billing)
Starting: Container is launching (no billing)
Running: Ready to use (billing active)
Stopped: Not running (no compute billing)

Data Persistence

Your data automatically persists between sessions:

Model weights and configurations
Generated images, videos, and other outputs
Chat history and conversation data
Custom workflows and settings
Files remain available when you restart deployments

API Integration

OpenAI-Compatible Endpoints

ModelPilot provides OpenAI-compatible API endpoints for easy migration from OpenAI services. Access your deployed models programmatically using familiar OpenAI API patterns.

Chat Completions: Use /api/v1/chat/completions with your deployed text models
Health Monitoring: Check deployment status with /api/deployments/{podId}/health
API Keys: Create API keys in your dashboard with proxy permissions
Drop-in Replacement: Compatible with OpenAI SDK and most libraries

→ View complete API documentation with examples

Quick Migration Example

// Before (OpenAI)
const openai = new OpenAI({
  apiKey: 'sk-...',
  baseURL: 'https://api.openai.com/v1'
});

// After (ModelPilot)
const openai = new OpenAI({
  apiKey: 'mp_live_your_api_key',
  baseURL: 'https://your-domain.com/api/v1'
});

// Same code works for both!
const response = await openai.chat.completions.create({
  model: 'mistral',  // Your deployed model
  messages: [{ role: 'user', content: 'Hello' }]
});

Documentation