# 7 Google models · example with gemini-3-6-flash
import os
from openai import OpenAI
client = OpenAI(base_url="https://ai.helipod.io/v1",
api_key=os.environ["HELIPOD_AI_KEY"])
r = client.chat.completions.create(
model="gemini-3-6-flash",
messages=[{"role": "user", "content": "Halo!"}])Gemini API pricing
Final prices in Rupiah per 1 million tokens. Cached = prompt tokens the provider already has in its cache (repeated system prompts, long documents).
Cost calculator
Per request
| Fresh input | 1,000 × Rp 26.700 | Rp 26,7 |
| Cached input | 1,000 × Rp 2.670 | Rp 2,67 |
| Output | 500 × Rp 133.500 | Rp 66,75 |
| One request | Rp 96,12 | |
A month (500 requests/day × 30)
Rp 1.441.800
An estimate: you are billed per request for the tokens actually used.
Gemini API
The Gemini API is programmatic access to Google's Gemini models: Pro, Flash and Flash Lite. Gemini is known for its very long context and its ability to read images.
On Helipod, Gemini is called with the OpenAI or Anthropic SDK you already use, without a Google Cloud account or the Google SDK. You are billed per token in Rupiah from your Helipod balance.
A separate account, dollar billing and an international credit card.
The same Google models, billed in Rupiah from one balance.
Advantages
Comparison
| Direct from Google | Helipod AI Gateway | |
|---|---|---|
| Billing currency | Dollars (USD) | Rupiah, per token |
| Payment | International credit card | QRIS / virtual account |
| Other models | Google models only | Claude, GPT, Gemini, DeepSeek, etc. |
| SDK | Google SDK | OpenAI & Anthropic SDKs |
| Spend cap per key | Per organization | Per API key, monthly |
| Request history | Google dashboard | Helipod console, prices recorded |
The Helipod team is happy to help you pick the right service.
Use cases
FAQ
Other models on the Helipod AI Gateway, with the same API key
All models & calculatorCompare every model in the AI Gateway price list.