Qwen 3.8 27B API in Australia
Alibaba’s small dense Qwen: open, multimodal and unusually strong at coding for 27 billion parameters. Priced in Australian dollars for teams in Australia, on the same key as every other model.
Qwen 3.8 27B API pricing in Australia
In Australian dollars, the currency your card is charged in, with the published US dollar rate beside each.
For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost A$6.02 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.
Prices are our published US dollar rates converted at A$1.47 to the dollar, our rate for October — the same rate your card is charged.
About Qwen 3.8 27B
Qwen 3.8 27B is the compact member of Alibaba’s Qwen 3.8 generation — 27 billion parameters, dense, open under Apache 2.0 — and it punches well above its size. Alibaba reports 61.7% on SWE-bench Pro, above its own figure for Claude Opus 4.6, plus 89.2% on GPQA Diamond and 84.3% on the OSWorld computer-use test.
It reads images and video as well as text, holds 262K tokens natively, and thinks by default with adjustable effort. Its design mixes fast linear-attention layers with full attention, which keeps long inputs cheap to process.
What is Qwen 3.8 27B good for?
- Coding agents at a low price.
- Operating desktop software.
- Reading documents, images and video.
Where to be careful
- Every headline score is Alibaba’s own.
- Stretching it to a million tokens can hurt quality on shorter texts.
Specs
qwen3.8-27bUsing Qwen 3.8 27B from Australia
Roar AI provides access to Qwen 3.8 27B through the Roar AI gateway, charged in Australian dollars on one bill with every other model. Requests from Australia go through our gateway in Singapore today; a gateway in Sydney is coming. Developers can use Qwen 3.8 27B alongside other supported models without a separate integration for every provider.
Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="qwen3.8-27b",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Where is Qwen 3.8 27B processed?
Requests to Qwen 3.8 27B are processed in Singapore, outside Australia. The model directory says where each model is processed.
Questions
How much does Qwen 3.8 27B cost in Australia?
Input is A$0.6689 per 1M tokens; output is A$4.01 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost A$6.02. Prices are our published US dollar rates converted at A$1.47 to the dollar, our rate for October — the same rate your card is charged. The rate is published and does not change from one request to the next.
Is Qwen 3.8 27B open source?
Its weights are open under the Apache 2.0 licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.
Try Qwen 3.8 27B
on one key
Sign up, get a key and call it with the SDK you already use. Pay in your local currency, on one bill.