# 2 Alibaba models · example with qwen35-122b-a10b
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="qwen35-122b-a10b",
messages=[{"role": "user", "content": "Halo!"}])Qwen 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 3.916 | Rp 3,92 |
| Cached input | 1,000 × Rp 3.916 | Rp 3,92 |
| Output | 500 × Rp 39.160 | Rp 19,58 |
| One request | Rp 27,41 | |
A month (500 requests/day × 30)
Rp 411.180
An estimate: you are billed per request for the tokens actually used.
Qwen API
The Qwen API is programmatic access to the Qwen models by Alibaba. Helipod offers Qwen3.5 122B A10B with reasoning and a 262 thousand token context, and the fast Qwen3 Next Instruct with a 131 thousand token context.
Qwen is called with the OpenAI or Anthropic SDK and one Helipod API key, without an Alibaba Cloud account. Usage is billed per token in Rupiah from your Helipod balance.
A separate account, dollar billing and an international credit card.
The same Alibaba models, billed in Rupiah from one balance.
Advantages
Comparison
| Direct from Alibaba | Helipod AI Gateway | |
|---|---|---|
| Billing currency | Dollars (USD) | Rupiah, per token |
| Payment | International credit card | QRIS / virtual account |
| Other models | Alibaba models only | Claude, GPT, Gemini, DeepSeek, etc. |
| SDK | Alibaba SDK | OpenAI & Anthropic SDKs |
| Spend cap per key | Per organization | Per API key, monthly |
| Request history | Alibaba 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
Compare every model in the AI Gateway price list.