Documentation

Comprehensive guides and API documentation for the Micro AI platform

Migrating to Micro AI

Complete guide for software developers to migrate their applications to use local and online LLMs through Micro AI

Quick Setup

API Key Required: Contact elie.r@sirenanalytics.com to get your Micro AI API key.

Base URL

https://microai.staging.sirenanalytics.com/llm_router/v1

Replace OpenAI's base URL with your Micro AI endpoint

Authentication

Bearer your-microai-key

Use Micro AI generated keys (not OpenAI keys)

Migration Examples

PythonBefore → After

❌ Before (OpenAI)

from openai import OpenAI

client = OpenAI(
    api_key="sk-proj-xxx"  # OpenAI key
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Hello"}]
)

✅ After (Micro AI)

from openai import OpenAI

client = OpenAI(
    base_url="https://microai.staging.sirenanalytics.com/llm_router/v1",
    api_key="microai-key-xxx",  # Micro AI key
    timeout=60  # Increased timeout
)

response = client.chat.completions.create(
    model="openai/gpt-4.1",  # Local model
    messages=[{"role": "user", "content": "Hello"}]
)

JavaScriptBefore → After

❌ Before (OpenAI)

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'sk-proj-xxx'  // OpenAI key
});

const response = await openai.chat.completions.create({
  model: 'gpt-4.1',
  messages: [{ role: 'user', content: 'Hello' }]
});

✅ After (Micro AI)

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://microai.staging.sirenanalytics.com/llm_router/v1',
  apiKey: 'microai-key-xxx',  // Micro AI key
  timeout: 60000  // Increased timeout
});

const response = await openai.chat.completions.create({
  model: 'openai/gpt-4.1',  // Local model
  messages: [{ role: 'user', content: 'Hello' }]
});

cURLRaw HTTP Request

curl -X POST "https://microai.staging.sirenanalytics.com/llm_router/v1/chat/completions" \
  -H "Authorization: Bearer microai-key-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 150
  }'