Getting started

Quickstart

Three steps to your first successful call. Every example uses a model that is online right now.

#1. Create an API key

The key is shown only once. Keep it on your server, never in a web page.

Every request goes to this address:

#2. Copy one request

Replace YOUR_API_KEY with your key, then run it.

API_KEY="${API_KEY:-YOUR_API_KEY}"

curl --fail-with-body -sS https://www.aisplice.store/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "GPT-5.6 Luna",
  "messages": [
    {
      "role": "user",
      "content": "Say hello."
    }
  ],
  "stream": false
}'

Already use the OpenAI SDK?

Change only base_url and api_key. Keep your existing client, message format, streaming parser, and retry wrapper.

#3. Check the answer

A 200 answer like this means you are connected.

response.json

{
  "id": "chatcmpl_xxx",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hello!"
      }
    }
  ]
}

Go further with this task →

All options, results and errors on one page.

Use it in Cursor, Cline or Cherry Studio →

Same address and key, no code.

Still stuck?

Send us the request ID or the error message and we will look into it.

NextUse it in an app