Build with LLMs, starting for free
Which models you can call for free today, what a real workload would cost, copy-paste starter code, and a roadmap from your first prompt to shipping evaluated AI features.
Free LLMs right now
Token cost calculator
Quickstart
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openrouter/auto",
"messages": [{"role": "user", "content": "Write 5 test cases for a login form."}]
}'Get a key at openrouter.ai and keep it in an environment variable. Never put it in front-end code.
Free tiers & playgrounds
One API for hundreds of models; models tagged :free cost nothing within daily limits.
Gemini API key in a minute, with a rate-limited free tier.
Very fast inference for open models, with a free rate-limited tier.
Try frontier and open models free for prototyping with your GitHub account.
Inference Providers with monthly free credits, plus thousands of open models.
Serverless models at the edge with a daily free allocation.
La Plateforme offers a free experiment tier for building and testing.
Run open models on your own machine. Free, private and offline.
Free tiers change often. Check each provider's pricing page before you rely on one.
AI engineer roadmap
1Foundations0/4 2Prompting0/4 3RAG0/4 4Agents & tools0/4 5Evals & testing0/4 6Ship it0/4