GLM-5.3-Flash API in Australia
Z.ai’s fast, low-cost GLM, and the first in the series to see images and video. Priced in Australian dollars for teams in Australia, on the same key as every other model.
GLM-5.3-Flash 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$1.82 — 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 GLM-5.3-Flash
GLM-5.3-Flash is the volume tier of GLM-5.3 and the first GLM-5 model to take images and video as well as text. Before Z.ai put its name on it, it ran anonymously as “Ox Alpha” and drew more than 50 trillion tokens of traffic in five days. Z.ai reports 63.4% on DeepSWE, well up on GLM-5.2’s 46.2%.
Its weights are open under MIT. Like its bigger sibling, it always thinks before answering, which costs some speed on simple calls.
What is GLM-5.3-Flash good for?
- Cheap, high-volume coding agents.
- Reading screenshots, documents and video inside agent loops.
- Long tool-use sessions where cost per task matters.
Where to be careful
- Thinking cannot be switched off.
- Its scores are Z.ai’s own, apart from one independent index.
Specs
glm-5.3-flashUsing GLM-5.3-Flash from Australia
Roar AI provides access to GLM-5.3-Flash 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 GLM-5.3-Flash 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="glm-5.3-flash",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Where is GLM-5.3-Flash processed?
Requests to GLM-5.3-Flash are processed on international infrastructure, outside Australia. The model directory says where each model is processed.
Questions
How much does GLM-5.3-Flash cost in Australia?
Input is A$0.2867 per 1M tokens; output is A$0.9555 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost A$1.82. 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 GLM-5.3-Flash open source?
Its weights are open under the MIT licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.
Try GLM-5.3-Flash
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.