OpenAI GPT OSS (ROCm 7)

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. Now on ROCm 7.

Software Included

Creating an App using the Control Panel

Click the Deploy to DigitalOcean button to create a Droplet based on this 1-Click App. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

Creating an App using the API

In addition to creating a Droplet from the OpenAI GPT OSS (ROCm 7) 1-Click App using the control panel, you can also use the DigitalOcean API. As an example, to create a 4GB OpenAI GPT OSS (ROCm 7) Droplet in the SFO2 region, you can use the following curl command. You need to either save your API access token) to an environment variable or substitute it in the command below.

curl -X POST -H 'Content-Type: application/json' \
         -H 'Authorization: Bearer '$TOKEN'' -d \
        '{"name":"choose_a_name","region":"sfo2","size":"s-2vcpu-4gb","image": "amd-openaigptossrocm"}' \
        "https://api.digitalocean.com/v2/droplets"

Getting Started After Deploying OpenAI GPT OSS (ROCm 7)

This 1-Click exposes three interfaces for GPT OSS model!

• You can open a WebUI interface in your browser by visiting:

  • http://your_droplet_public_ipv4

  To authenticate in WebUI use the email and password provided when you SSH into your droplet.

• You can access the vLLM inferencing API directly at:

  • http://your_droplet_public_ipv4:8000

    A bearer token for the GPT OSS inferencing API is provided when you SSH into your droplet.

• Finally, from within this Droplet:

  curl -X POST "http://localhost:8001/v1/chat/completions" \
    -H "Content-Type: application/json" \
    --data '{
      "model": "openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "What is the capital of France?"
        }
      ]
    }'