API documentation

Lumi exposes an OpenAI-compatible API. Point any OpenAI SDK at our base URL and use your Lumi API key. Usage is billed per token from your USD credit balance.

Get an API key Pricing

Base URL & auth

Base URL: https://ai.harsaniq.top/api/v1

Header: Authorization: Bearer YOUR_KEY

cURL

curl https://ai.harsaniq.top/api/v1/chat/completions \
  -H "Authorization: Bearer $LUMI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lumi-default",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.harsaniq.top/api/v1",
    api_key="YOUR_LUMI_API_KEY",
)

resp = client.chat.completions.create(
    model="lumi-default",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node (openai SDK)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://ai.harsaniq.top/api/v1",
  apiKey: process.env.LUMI_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "lumi-default",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Endpoints

POST /v1/chat/completions— streaming & non-streaming
GET /v1/models — list models

Rate limit: 120 requests/minute per key. Set "stream": true for token streaming. A 402 means you are out of credits.