- Developers who want to try a model quickly
- Teams comparing models side by side
- Anyone refining prompts for production
Playground 03 Serve
AI Playground
Test any model right in your browser, then track every request in your activity log.
GLM
DeepSeek
Qwen
Kimi
Mistral
Llama
gpt-oss
Gemma
Loes
Nemotron
Claude Code
Codex
OpenCode
Cursor
Cline-
Loes
-
OpenAI SDK
Anthropic SDK
What it does Playground
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.
Read more
02 Playground
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.
03 Playground
Who is it for?
04 Playground
From Playground to code
Like a model in the Playground? The same call works from your code, through the same Router:
python
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.
05 Playground
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
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.
Everything you need for AI
From model hosting to a customer-facing API, it is built for developers and businesses who want their AI running on infrastructure they actually control, inside the EU.
EU-hosted
100%
Your data and your models stay on European GPUs. GDPR-friendly by design.
Verified models, ready to serve
700+
Llama, Qwen, DeepSeek, Mistral, FLUX and plenty more. Pick one and it is warm in minutes, with no DevOps on your end.
OpenAI & Anthropic compatible
2 SDK
Point your existing client at the Router and keep your tools. No rewrite, no lock-in.
From zero to a warm endpoint in minutes
No infra to manage. Pick a model, get an OpenAI-compatible URL, ship.
01
Pick a model
Choose from the Model Garden or paste any HuggingFace ID. Set the VRAM and pick an EU GPU.
02
Get your endpoint
We deploy vLLM, run readiness probes, and hand you a warm OpenAI- and Anthropic-compatible URL plus an API key.
03
Route and ship
Point your client at the Router. It auto-routes to a warm instance and logs every request.
Built for teams that can't send data away
If a US cloud is off the table, HostYourAI gives you the same developer experience on European infrastructure.
01
Public sector & government
Citizen data that legally has to stay in the EU, with full auditability.
02
Regulated enterprise
Finance, healthcare and legal teams under GDPR, DORA and the AI Act.
03
EU SaaS & scale-ups
Ship AI features your customers trust, without a US sub-processor.
04
Agencies & integrators
Deliver private AI for clients on infrastructure you can stand behind.
Private by Default
HostYourAI keeps your models, prompts and data on European GPUs. It is built for teams that care about compliance, reliability and real control.
- EU-hosted
- GDPR-friendly
- OpenAI-compatible
- vLLM-powered
- No lock-in
Full data sovereignty
EU
GPUs and data stay inside Europe, and so do your prompts.
Models you can audit
Open
Run open-weight models and see exactly what runs.
No monthly fee
€0
Prepaid credit per token or per minute, so you pay only for what you run.
Your keys, your models
Yours
Your keys, your models and your data. Move whenever you want.
Model garden
Works with 700+ open models
Text and image models on dedicated EU GPUs. Every model tested on our own hardware.
The platform
One platform, four layers
Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.
Related pages
Explore more about EU-hosted AI on HostYourAI.
Dedicated GPU Instances
Deploy any open model on a dedicated European GPU with vLLM. Your own endpoint, encrypted upstream keys, idle when nobody is online.
Read moreOpenAI-compatible API
A drop-in OpenAI-compatible API on European GPUs. Change only the base URL and run open models, GDPR-friendly, without rewriting your code.
Read moreFine-Tuning LLM
Fine-tune LLMs for your specific use case. LoRA, QLoRA, full fine-tuning on dedicated GPUs.
Read moreEurope's AI infrastructure.
Come build with us.
Start with one key today. Add dedicated GPUs when your workload needs them.
