Get Your First AI API Key in India with UPI (Step-by-Step)

You can get a working AI API key on Velona in about five minutes: sign in with Google, add as little as ₹10 with UPI, create a key, and send your first request with the standard OpenAI SDK. No international credit card, no dollar billing.

The same key works with 300+ models, including GPT, Claude, Gemini, DeepSeek, Grok, Kimi and Qwen, so you only set this up once.

Step 1: Sign up

Go to velona.in/register and sign in with Google. You land on your dashboard straight away.

Step 2: Add money with UPI

Velona uses a prepaid rupee wallet instead of a dollar card.

Open Wallet in your dashboard.
Choose an amount. The minimum is ₹10.
Pay with UPI, RuPay, a domestic debit or credit card, or net banking.
Your balance updates as soon as the payment is confirmed.

How far does ₹10 go? On GPT-4o mini, a short chat reply (about 1,000 tokens in and 500 out) costs about ₹0.05, so ₹10 covers roughly 200 of them. On DeepSeek V4 Flash it covers well over 1,000. See every model's rupee price on the pricing page.

Step 3: Create your API key

Open API Keys and create a new key. Give it a name that matches your project.

Copy it straight away. For security, the full key is only shown once.
Set a budget on the key. Each key can have its own spending limit, so a bug or a runaway loop can't empty your wallet.
Use one key per project. Your usage page then shows exactly what each project costs.

Step 4: Make your first request

Velona is OpenAI-compatible. You use the official OpenAI SDK and only change two things: the base URL and the model ID.

Python

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["VELONA_API_KEY"],
    base_url="https://velona.in/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello from India!"}],
)

print(response.choices[0].message.content)

curl

curl https://velona.in/v1/chat/completions \
  -H "Authorization: Bearer $VELONA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello from India!"}]
  }'

Model IDs always follow the pattern provider/model. To try a different model, change only that value, for example deepseek/deepseek-v4-flash, anthropic/claude-sonnet-5 or google/gemini-2.5-flash. The model catalogue lists every ID with its price.

Want to try prompts before writing code? Use the browser chat first.

Common problems

"Insufficient balance" on the first request

Check that your UPI payment has confirmed in your wallet. It usually takes a few seconds and occasionally up to a minute.

"Invalid API key"

Make sure you copied the whole key with no spaces before or after it. If in doubt, create a new key on the API Keys page.

"Model not found"

Include the provider prefix. gpt-4o-mini will fail, openai/gpt-4o-mini works. Copy the exact ID from the model's page.

Requests work but cost more than expected

Open your usage page to see the tokens and rupee cost of every call. Long conversations resend earlier messages each time, so trim history and set max_tokens.

What to read next

Create your Velona account and send your first request in the next five minutes.

How to Get Your First AI API Key on Velona (Step-by-Step Guide)