Playground

A web-based tool for testing prompts, comparing models, and inspecting request details without writing code.

The Radium Playground is on the product roadmap but not yet available. In the meantime, you can test prompts with the Python SDK or cURL using your API key.

Test prompts today

You can replicate much of what a playground will offer by calling the API directly:

from openai import OpenAI

client = OpenAI(api_key="YOUR_RADIUM_API_KEY", base_url="https://api.radium.cloud/v1")

response = client.chat.completions.create(
    model="clarke-1.0",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    temperature=0.7,
    max_tokens=1024,
)
print(response.choices[0].message.content)

What the playground will offer

When launched, the Radium Playground will provide:

Model comparison — Run the same prompt against hal-1.0, clarke-1.0, and tycho-1.0 side by side
Request inspection — View full request/response payloads, token breakdowns, latency, and estimated cost
Scenario library — Save, share, and fork prompts with your team
History — Review, rerun, or export past playground requests

Next steps