Frosty AI Quick Start Guide

To get deployed in minutes, use the Quickstart Wizard found at the bottom of the left-hand menu inside the Frosty AI platform. The wizard will guide you step-by-step through setting up your first workspace, connecting providers, and configuring routers.

1. Create a Workspace

Set up a collaborative environment to organize Routers and Providers. In the left-hand menu, select Workspaces and click Create Workspace.

2. Connect a Provider

Link an LLM provider like OpenAI or Anthropic to access models.
Learn how to get an API key from your provider: OpenAI, Anthropic, Mistral AI.

3. Set Up Your Router

Configure Routers to select the best LLM for your tasks. Frosty AI intelligently routes requests based on cost, performance, or custom-defined rules, allowing you to optimize workflows seamlessly. When you configure your route, you can set models for task-specific needs like cost, performance, and future-proofing by setting a failover provider.

4. Connect Frosty to Your App or Workflow

Once your router is configured, you can start sending prompts using any of the following integration options:

✅ Option 1: Use the Python SDK

Install the SDK using pip:

pip install frosty-ai

Example Usage

# Import Frosty SDK
from frosty_ai import Frosty

def main():
    router_id = "[YOUR_ROUTER_ID]"
    router_key = "[YOUR_ROUTER_KEY]"

    try:
        # Create an instance of the Frosty class
        frosty_sdk = Frosty(router_id, router_key)

        # Make a text generation request
        chat_result = frosty_sdk.chat([{
            "role": "user",
            "content": "Tell me a 10-word joke about the weather."
        }])

        print(f"Text generation result: {chat_result}")

    except Exception as e:
        print(f"An error occurred: {e}")

if __name__ == "__main__":
    main()

✅ Option 2: Use the API Directly

Call Frosty’s /chat API from any platform or language.
See the API Documentation .

✅ Option 3: Ma ke.com Integration

Build no-code workflows with Frosty AI and Make. Connect apps like Google Sheets, Notion, Slack, and more — no code required.

✅ Option 4: Use the n8n Integration

Use Frosty's custom n8n node to integrate AI into your self-hosted workflows. Perfect for dev teams who want more automation control.

✅ Option 5: Explore Frosty AI Templates

Explore the Launchpad for ready-to-use templates:

Python SDK Starter
REST API Starter (JavaScript, Go)
Make.com Scenarios (Google Sheets, Google Docs)
n8n Node Installer

5. Optimize & Validate

Use Frosty’s real-time analytics to:

Monitor token usage
Compare costs and model performance
Analyze routing efficiency

Continuously refine your AI workflows to optimize for quality, speed, and cost.

🎉 You're all set!
Now you can explore advanced Frosty features like dynamic routing, failover models, and cost/performance optimization.

📖 To learn more, visit gofrosty.ai

Quick Start Guide for Frosty AI