API Documentation

OpenAI/v1Anthropic/anthropic

Sign up, mint a key, copy one request — and see your first reply. Follow the four steps in order.

1. 1

   Create an account

   New users get free Stars on sign-up — plenty to run this Quickstart end to end.

   Sign up / log in
2. 2

   Create an API key

   Open the console and create a key. The full key is shown only once, so copy it right away and keep it safe.

   Open API Keys
3. 3

   Copy the minimal request

   Set LUMART_API_KEY to the key you just created, then run one of these. Same code as the OpenAI SDK — only base_url changes.

   cURL

   Copy

   cURLJavaScriptPython

   curl https://lumart.ai/v1/chat/completions \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer $LUMART_API_KEY" \
     -d '{
       "model": "lumart-chat",
       "messages": [{"role":"user","content":"Hello Lumart!"}]
     }'

4. 4

   See your first reply

   A successful call returns a standard chat completion object — the reply is in choices[0].message.content.

   Expected response · JSON

   {
     "id": "chatcmpl-abc123",
     "object": "chat.completion",
     "created": 1700000000,
     "model": "lumart-chat",
     "choices": [
       {
         "index": 0,
         "message": { "role": "assistant", "content": "Hello! How can I help you today?" },
         "finish_reason": "stop"
       }
     ],
     "usage": { "prompt_tokens": 9, "completion_tokens": 9, "total_tokens": 18 }
   }

   Want token-by-token streaming? Add "stream": true and read the response as Server-Sent Events.