Skip to content
AMD AMD Radeon Cloud Docs

Quickstart

Two things to try. They’re independent — do either one first.

Call a model API

Section titled “Call a model API”

The fastest way in. No instance, no credits.

Open the Token Factory, sign in, and pick any model under Public Free Model APIs. The detail dialog shows your API key. Copy it.

Terminal window
curl https://developer.amd.com.cn/radeon/api/v1/chat/completions \
  -H "Authorization: Bearer $RADEON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "DeepSeek-V4-Flash",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

The same key works for every shared model — change the model field to switch. To see what’s available:

Terminal window
curl https://developer.amd.com.cn/radeon/api/v1/models \
  -H "Authorization: Bearer $RADEON_API_KEY"

From Python, point the OpenAI SDK at the same base URL:

from openai import OpenAI


client = OpenAI(
    base_url="https://developer.amd.com.cn/radeon/api/v1",
    api_key="rc-...",
)


response = client.chat.completions.create(
    model="DeepSeek-V4-Flash",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(response.choices[0].message.content)

Full details in the API reference.

Launch a GPU instance

Section titled “Launch a GPU instance”
  1. Sign in at radeon-global.anruicloud.com — see Sign in.
  2. Open Profile and create a template under My Templates. Give it a title and a container image. Set storage to Persistent (PVC) if you want files to survive. See Create a template.
  3. Click Launch on the template row.
  4. When the dialog reads Your workspace is ready (100%), click Open Notebook for JupyterLab, or connect over SSH.

Confirm the GPU is visible from a terminal inside the instance:

Terminal window
rocm-smi

You should see one or more Radeon GPUs listed.