On this page
Test before you integrate
In the Playground you chat directly with both dedicated instances and models on the Router. So you try out prompts, compare models and check behaviour before you wire a model into your application.
From test to insight
Every chat runs over the same infrastructure as your production traffic. Afterwards you see per-request usage, latency and cost in your activity log, so testing and measuring happen in one place.
Who is it for?
- Developers who want to try a model quickly
- Teams comparing models side by side
- Anyone refining prompts for production
From Playground to code
Like a model in the Playground? The same call works from your code, through the same Router:
from openai import OpenAI
client = OpenAI(
base_url="https://hostyourai.com/api/v1",
api_key="hyai-...",
)
resp = client.chat.completions.create(
model="llama-3.3-70b",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)Ready to integrate? Read the guide Migrate your OpenAI client to the EU Router.
What you set translates one to one into code
Everything you configure in the Playground also exists as an API parameter. What works in your test works literally the same in production:
| In the Playground | In your code |
|---|---|
| Model choice | model |
| System instruction | Message with role system |
| Creativity | temperature |
| Maximum length | max_tokens |
| Continuing a conversation | Sending the full messages array |
From the Model Garden you open a model preselected in the Playground, handy for putting candidates side by side quickly.
Questions about the Playground
Is the Playground free?
The Playground itself costs nothing extra; you only pay the tokens of your test requests, at the same rates as the API. See the pricing page.
Which models can I chat with?
All Router models from the catalog and your own dedicated instances, in the same interface.
Can I test a system instruction?
Yes. You set a system instruction, temperature and maximum length and see how the model responds right away. You then use the same values in your API call.
Does my test run over the same infrastructure as production?
Yes. Every Playground chat goes through the same Router and the same EU GPUs as your production traffic, so what you test is representative.
Does my test data stay in the EU?
Yes. Playground requests also run on European GPUs and there is no training on your data.
How do I go from test to production?
Copy your settings into an API call with your hyai- key through the OpenAI-compatible API. More detail: the migration guide above.