Get Started in 5 Minutes
Start using Komilion's intelligent model routing, tool execution, and voice capabilities.
Get your API key
Existing customers — generate from your dashboard. New here? Join the waitlist for full launch.
Join the launch waitlist
New signups are paused while we polish the full launch. Join the waitlist and we'll bring you in when the doors reopen. Existing customers — log in as usual.
Generate your API key
Go to Dashboard → API Keys and click "Generate New Key"
Save your key
Your key looks like: ck_your-api-key-here
Install the SDK
Use the official OpenAI SDK (Komilion is compatible)
npm install openai💡 Komilion is OpenAI SDK compatible - no special SDK needed!
Make Your First Request
Just point the OpenAI SDK to Komilion
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "ck_your-api-key-here",
baseURL: "https://www.komilion.com/api/v1",
});
const response = await client.chat.completions.create({
model: "neo-mode/balanced", // Let Komilion choose the best model
messages: [
{ role: "user", content: "Explain quantum computing in simple terms" }
],
// neo-mode/* skips the clarification step and answers directly
skipClarification: true,
});
console.log(response.choices[0].message.content);Choose Your Policy
Balance cost vs quality with a single parameter
Cost-first
Cheapest options, great for high-volume tasks
model: "neo-mode/frugal"Best Value (Default)
Optimal cost/quality trade-off for most use cases
model: "neo-mode/balanced"Quality-first
Top models for complex reasoning and important tasks
model: "neo-mode/premium"Framework Guides
Copy-paste configs for popular tools and frameworks
Drop-in replacement — just change 2 lines
from openai import OpenAI
client = OpenAI(
base_url="https://www.komilion.com/api/v1",
api_key="ck_your-api-key-here",
)
response = client.chat.completions.create(
model="neo-mode/balanced",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)