Quickstart
Call open-weight models through Qloud's OpenAI-compatible API in a few minutes.
Qloud Serverless gives you open-weight models through an OpenAI-compatible API. Point any OpenAI client at Qloud, pay per token from prepaid credit, and switch models by changing one string.
Get an API key
Create an account
Sign up at dashboard.qloud.sh.
Get access for your organization
Redeem a referral code, or apply for access, from the dashboard. Until your organization is approved you can explore everything, but not create keys or add credit.
Add credit
Buy prepaid credit under Billing.
Create a key
Create a key under API keys. The secret is shown once, so store it in a secret manager.
Keep keys on your server. Never put them in browser code, mobile apps, URLs or support messages.
Connect
| Setting | Value |
|---|---|
| Base URL | https://api.qloud.sh/v1 |
| Authentication | Authorization: Bearer $QLOUD_API_KEY |
| Endpoints | POST /chat/completions, POST /completions, GET /models |
Send a request
curl https://api.qloud.sh/v1/chat/completions \
-H "Authorization: Bearer $QLOUD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "DeepSeek-V4-Flash-0731",
"messages": [{"role": "user", "content": "Say hello in five words."}],
"max_tokens": 256
}'Every response carries an x-qlo-request-id header. Keep it with your logs; it is the fastest way for us to find a request.