API Quickstart
Get from zero to a working AI request in under a minute.
Why use GenCMS instead of direct provider APIs?
- Automatic routing — one
/api/v1/chat/completionsendpoint; setmodel: "auto"and we pick a capable model for your prompt. - Cost optimization — usage is metered on our stack; responses include a
gencmsobject with cost, latency, and savings vs a premium baseline so savings stay visible. - Fallback — if a provider errors, configured fallbacks can take over without changing your client code.
- Analytics — per-key usage, dashboard analytics, and model telemetry (compare, leaderboard) are built in — not bolted on.
-
Step 1 — Get an API key
Create a key in your dashboard. You’ll use it as a Bearer token.
Go to API keys -
Step 2 — Make your first call
Replace
YOUR_KEYwith your key.curl https://gen-cms.com/api/v1/chat/completions \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "auto", "messages":[{"role":"user","content":"Hello"}] }' -
Step 3 — Done
You just made your first AI request.