Build with Mavorium AI

One API for chat, writing, code and support bots. Sign in with your free Mavorium account and create an API key — keys are free, 25 requests a day are free, and after that you pay only for what you use from prepaid credit. No subscription.

API docs

The Mavorium API uses the common chat completions format, so most AI SDKs work by changing the base URL and key.

Base URL

https://www.mavorium.in/mavorium-console/v1

Authentication

Authorization: Bearer YOUR_API_KEY

Models

`mavorium-1`	Mavorium AI — free AI first, paid AI backup when you have credit (best value)
`mavorium-free`	Free AI only — cheapest, can be busy at peak times
`mavorium-pro`	Best quality — paid AI first (needs credit)

Examples

curl https://www.mavorium.in/mavorium-console/v1/chat/completions \
  -H "Authorization: Bearer $MAVORIUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mavorium-1",
    "messages": [
      {"role": "system", "content": "You are a friendly support agent."},
      {"role": "user", "content": "How do I reset my password?"}
    ],
    "max_tokens": 800
  }'

# pip install openai   (the Mavorium API speaks the same format)
from openai import OpenAI
client = OpenAI(base_url="https://www.mavorium.in/mavorium-console/v1", api_key="YOUR_API_KEY")
r = client.chat.completions.create(model="mavorium-1",
      messages=[{"role": "user", "content": "Write a tagline for a bakery"}])
print(r.choices[0].message.content)

// Run on your server (Node 18+). Never put the key in browser code.
const r = await fetch("https://www.mavorium.in/mavorium-console/v1/chat/completions", {
  method: "POST",
  headers: { "Authorization": "Bearer " + process.env.MAVORIUM_API_KEY, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "mavorium-1", messages: [{ role: "user", content: "Hello!" }] })
});
const data = await r.json();
console.log(data.choices[0].message.content);

<?php
$ch = curl_init('https://www.mavorium.in/mavorium-console/v1/chat/completions');
curl_setopt_array($ch, [CURLOPT_RETURNTRANSFER => true, CURLOPT_POST => true,
  CURLOPT_HTTPHEADER => ['Authorization: Bearer ' . getenv('MAVORIUM_API_KEY'), 'Content-Type: application/json'],
  CURLOPT_POSTFIELDS => json_encode(['model' => 'mavorium-1', 'messages' => [['role' => 'user', 'content' => 'Hello!']]])]);
$data = json_decode(curl_exec($ch), true);
echo $data['choices'][0]['message']['content'];

Response

{
  "id": "chatcmpl-…", "object": "chat.completion", "model": "mavorium-1",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "…"}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 21, "completion_tokens": 64, "total_tokens": 85},
  "mavorium": {"engine": "free", "free_request": false, "cost_inr": 0.0043, "balance_inr": 998.21}
}

Other endpoints

GET https://www.mavorium.in/mavorium-console/v1/models   — list models
GET https://www.mavorium.in/mavorium-console/v1/usage    — your credit balance, free requests left, prices

Pricing (pay as you go)

`mavorium-free`	₹50 per 1M tokens
`mavorium-1`	free-AI answers ₹50 per 1M · paid-AI answers ₹750 input / ₹3,000 output per 1M
`mavorium-pro`	₹750 input / ₹3,000 output per 1M tokens

Errors

`401`	Missing, wrong or deleted API key
`402`	No credit left (or not enough for this request) — add credit in the console
`429`	Too many requests per minute
`503`	AI busy — wait a few seconds and retry

Streaming: send "stream": true to get the answer as server-sent events (one chunk, then [DONE]). Limits: up to 4000 output tokens per request.