OpenAI's models, called from your server while the app runs.
The OpenAI API lets your app call OpenAI's models from your server while it runs, for example to answer questions in a chatbot. You pay per token, the small chunks of text the model reads and writes, so cost grows with usage rather than a monthly plan.
Good for
Watch out for
| Build | Role | Plan | Monthly | Notes |
|---|---|---|---|---|
| AI chatbot app over your own content | AI APIgpt-5-mini for answers, free moderation | Usage only: gpt-5-mini $0.25 in / $2.00 out per 1M tokens; gpt-5-nano $0.05 / $0.40; omni-moderation free | usage | No free tier found. VAT treatment not recorded |
OpenAI vs Claude vs Gemini APIs for a chat feature
Small: gpt-6-luna ($0.10 in / $0.50 out per million tokens). Mid: gpt-6.1-sol ($2 / $10)
Prices are for short prompts. Long-context requests on the flagship models cost more.
Vercel
Hosting for web apps, built around Next.js.
Good for: Next.js apps, which it runs with no setup
Used in 9 builds, compared in 1
Netlify
Hosting for websites and web apps.
Good for: Static sites and simple web apps on a tight budget
Used in 5 builds, compared in 1
Supabase
A Postgres database with sign-in, file storage and row-level security in one project.
Good for: Getting a database and sign-in running in one place
Used in 7 builds, compared in 3
GitHub
Hosts your code; used here for secret and dependency checks.
Good for: Keeping your code safe and versioned
Used in 1 build