Getting started

Quickstart

Three steps to your first model response. After that you can wire up an editor or SDK — the principle is the same everywhere.

Three steps

Create an API key in your dashboard → /dashboard/keys. The key is shown once — save it immediately.
Top up your balance — by card or crypto on the top-up page.
Send a request, naming the model id in the model field:

curl

curl https://api.alicode.store/v1/chat/completions \
  -H "Authorization: Bearer sk-ali-•••" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4o","messages":[{"role":"user","content":"hi"}]}'

◆

The model field is an id from the catalog. The full list of enabled models is in GET /v1/models — take an id from there. See “How to choose a model” for details.

What you get back

The response is in the standard OpenAI shape. The model text is in choices[0].message.content, and the request token counter is in usage.

response.json

{
  "model": "openai/gpt-4o",
  "choices": [{ "message": { "role": "assistant", "content": "Hello!" } }],
  "usage": { "prompt_tokens": 12, "completion_tokens": 8, "total_tokens": 20 }
}