Get Started with Any AI Model 🚀
Whether you want free local models or premium cloud APIs, this guide walks you through setting up any AI model in three straightforward steps. No prior experience required.
Choose Your Model Type
🆓 Free Local Models
Run models directly on your Mac. Completely free, private, and works offline.
- ✅ Ollama — Easiest option (recommended)
- ✅ LM Studio — GUI interface
- ✅ llama.cpp — Command line
Best for: Learning, experimentation, privacy-sensitive work
⭐ Premium Cloud APIs
Access powerful models via API. Pay per use or monthly subscription.
- ✅ OpenAI — GPT-4, GPT-4o, o1
- ✅ Anthropic — Claude 3.5/3.7 Sonnet
- ✅ Google — Gemini Pro/Ultra
- ✅ xAI — Grok
Best for: Production apps, maximum capability
Install & Configure
🦙 Option A: Ollama (Recommended for Beginners)
- 1. Download Ollama from ollama.ai
- 2. Run the installer (it's a simple .dmg file for Mac)
-
3.
Open Terminal and test:
ollama run llama3.2 -
4.
Download models as needed:
ollama pull mistral
Popular models: llama3.2 (3B), mistral (7B), mixtral (8x7B), codellama (code)
🤖 Option B: OpenAI API
- 1. Create account at platform.openai.com
- 2. Go to API Keys → Create new secret key
- 3. Add $5-10 credit (Settings → Billing)
- 4. Use key in your orchestration tools
Pricing: GPT-4o ~$0.005/1K tokens, GPT-4 ~$0.03/1K tokens
🧠 Option C: Anthropic (Claude)
- 1. Create account at console.anthropic.com
- 2. Go to API Keys → Create key
- 3. Add credit (minimum $5)
- 4. Start using Claude 3.5/3.7 Sonnet
Pricing: Claude 3.5 Sonnet ~$0.003/1K tokens (very affordable!)
Connect to Your Orchestrator
Once your model is installed or API key is ready, connect it to your AI orchestration framework (LangChain, CrewAI, OpenClaw, etc.).
🔧 Example: LangChain Configuration
from langchain_openai import ChatOpenAI
# For OpenAI
llm = ChatOpenAI(
model="gpt-4o",
api_key="your-api-key-here",
temperature=0.7
)
# For Ollama (local)
from langchain_ollama import ChatOllama
llm = ChatOllama(
model="llama3.2",
base_url="http://localhost:11434"
)✅ Test Your Connection
Before building complex workflows, test that your model works:
# Test Ollama
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Hello!"
}'
# Test OpenAI
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'🔧 Troubleshooting
Ollama won't start
Make sure the Ollama app is running (check menu bar). Restart with ollama serve
API key errors
Double-check your key has no extra spaces. Verify billing is set up and you have credit.
Model too slow (local)
Try smaller models (3B instead of 70B). M-series Macs handle up to 34B models well.
Rate limit errors (API)
You've hit usage limits. Wait a minute or upgrade your plan. Add retry logic to your code.
🎉 Ready to Build!
You've successfully set up your AI model. Now explore our AI Models page to see 200+ available models across 50+ providers, or jump into the AI Toolkit to start building orchestration workflows.