Quickstart - Michi Documentation

This guide will walk you through setting up your account, generating API credentials, and making your first request using Javascript, Python, or standard CLI tools.

Step 1: Generate an API Key

Sign in to your Michi Dashboard.
Create a new Project.
Under API Keys, generate a new key.

Ensure you copy the API key immediately and store it securely. You will use it to authorize requests as a Bearer token.

Step 2: Choose Your Platform

Select your preferred language below to view the client implementation code:

💻 Javascript / Node.js

First, install the standard openai library:

npm install openai

Initialize the client with the Michi endpoint:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MICHI_API_KEY, // Your Michi Key
  baseURL: "https://api.michiai.co"
});

async function run() {
  const stream = await client.chat.completions.create({
    model: "openai/gpt-4o-mini", // Route to GPT-4o Mini
    messages: [{ role: "user", content: "How does routing work?" }],
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || "");
  }
}

run();

🐍 Python

Install the package:

pip install openai

Implement the completions request:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MICHI_API_KEY"),
    base_url="https://api.michiai.co"
)

response = client.chat.completions.create(
    model="claude/claude-3-5-sonnet", # Route to Claude 3.5 Sonnet
    messages=[
        {"role": "user", "content": "Explain fallbacks in routing."}
    ]
)

print(response.choices[0].message.content)

🛠️ CLI / Curl

For shell scripting or command line utilities:

curl -X POST https://api.michiai.co/chat/completions \
  -H "Authorization: Bearer $MICHI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [
      {
        "role": "user",
        "content": "Hi! Pick the most cost-effective model."
      }
    ]
  }'

Step 3: Monitor Live Telemetry

Once you make your first request, open the Logs tab in your dashboard to view:

Exact response latencies (in milliseconds)
Total prompt & completion tokens
Dynamic cost calculation based on selected models
Routing status (e.g. which model was selected)

​Step 1: Generate an API Key

​Step 2: Choose Your Platform

​💻 Javascript / Node.js

​🐍 Python

​🛠️ CLI / Curl

​Step 3: Monitor Live Telemetry

Step 1: Generate an API Key

Step 2: Choose Your Platform

💻 Javascript / Node.js

🐍 Python

🛠️ CLI / Curl

Step 3: Monitor Live Telemetry