# OpenAI GPT OSS (ROCm 7)

Generated on 6 Oct 2025 from [the OpenAI GPT OSS (ROCm 7) catalog page](https://marketplace.digitalocean.com/apps/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

| Package | Version | License |
|---|---|---|
| ROCm (host system) | 7.0 | [LICENSE](https://rocm.docs.amd.com/en/latest/about/license.html) |
| ROCm (in Docker image) | 7.0 | [LICENSE](https://rocm.docs.amd.com/en/latest/about/license.html) |
| vLLM (in Docker image) | 0.9.2 | [LICENSE](https://github.com/vllm-project/vllm/blob/main/LICENSE) |
| OpenAI GPT-OSS | 0.0.8 | [Apache License 2.0](https://github.com/openai/gpt-oss/blob/main/LICENSE) |

## Deploying this Offering using the Control Panel

Click the **Deploy to DigitalOcean** button to deploy this offering. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

[![Deploy OpenAI GPT OSS (ROCm 7) to DO](https://www.deploytodo.com/do-btn-blue.svg)](https://cloud.digitalocean.com/droplets/new?image=amd-openaigptossrocm)

## 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?"
        }
      ]
    }'
  ```