Migration Guide

Migration Guide

Macyou's Deployment API is fully OpenAI-compatible. Migrating from OpenAI (or any OpenAI-compatible provider) requires only two changes: the base URL and the API key.

From OpenAI

Python

# Before (OpenAI)
from openai import OpenAI
client = OpenAI(api_key="sk-...")

# After (Macyou)
from openai import OpenAI
client = OpenAI(
    base_url="https://your-deployment.macyou.co/api/v1",
    api_key="mcy_live_YOUR_KEY",
)

# Everything else stays the same
response = client.chat.completions.create(
    model="llama-4-scout",
    messages=[{"role": "user", "content": "Hello!"}],
)

Node.js / TypeScript

// Before (OpenAI)
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "sk-..." });

// After (Macyou)
const client = new OpenAI({
  baseURL: "https://your-deployment.macyou.co/api/v1",
  apiKey: "mcy_live_YOUR_KEY",
});

// Everything else stays the same
const response = await client.chat.completions.create({
  model: "llama-4-scout",
  messages: [{ role: "user", content: "Hello!" }],
});

curl

# Just change the URL and key
curl https://your-deployment.macyou.co/api/v1/chat/completions \
  -H "Authorization: Bearer mcy_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama-4-scout","messages":[{"role":"user","content":"Hello!"}]}'

From LangChain

from langchain_openai import ChatOpenAI

# Just set the base_url and api_key
llm = ChatOpenAI(
    base_url="https://your-deployment.macyou.co/api/v1",
    api_key="mcy_live_YOUR_KEY",
    model="llama-4-scout",
)

response = llm.invoke("Explain the RAG pattern.")

From LlamaIndex

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    api_base="https://your-deployment.macyou.co/api/v1",
    api_key="mcy_live_YOUR_KEY",
    model="llama-4-scout",
    is_chat_model=True,
)

Key Differences from OpenAI

• Dedicated hardware — your model runs on your own Mac Mini, not shared infrastructure. Latency is consistent.
• No per-token billing — you pay a flat monthly fee for the deployment, not per token.
• Data stays on your machine — requests never leave your dedicated server.
• Model selection — each deployment runs one model. UseGET /api/v1/modelsto see what's available.
• API key format — Macyou keys use the mcy_live_prefix instead of sk-.

Environment Variables

We recommend using environment variables to make switching between providers seamless:

# .env
OPENAI_API_BASE=https://your-deployment.macyou.co/api/v1
OPENAI_API_KEY=mcy_live_YOUR_KEY

Many OpenAI SDK wrappers and frameworks automatically read these environment variables, so no code changes are needed.