European-hosted · OpenAI-compatible · Cancel monthly

Rent a model.
Skip the GPU.

Qwen 3.8, served from Europe. No token limits, no per-request billing — just a flat monthly price and an OpenAI-compatible endpoint you can drop into any existing SDK.

Get an API key Read the docs

Base URL: broomy.laserraptor.eu/api/v1

Drop-in replacement

Point any OpenAI SDK at Broomy. Change two lines — base URL and API key — and your existing code works unchanged. Streaming, function calling, and vision input all supported.

✓262,144 token context window
✓Text + image input, text output
✓Server-sent events streaming
✓EU-hosted — no US or China routing

from openai import OpenAI

client = OpenAI(
    base_url="https://broomy.laserraptor.eu/api/v1",
    api_key="YOUR_API_KEY",
)

reply = client.chat.completions.create(
    model="qwen3.8-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)

Simple, flat pricing

One model. Two plans. No token limits.

Basic

Light use

€20/month

For occasional queries and small projects.

OpenAI-compatible chat completions
Unlimited tokens — no caps, no overage fees
1 concurrent request
European-hosted, EU-only routing
Cancel any month, no lock-in

Start with Basic

Recommended

Pro

Daily use

€50/month

For daily workloads and production apps.

Everything in Basic
3 concurrent requests
Priority queue during peak load
Higher throughput window
Direct support channel

Start with Pro

Prices are net, plus statutory VAT. Cancel any month — no lock-in, no auto-renewal surprises.

The model

Qwen 3.8 Flash

A Qwen 3.8 flash model running on European infrastructure. Slower than Claude or GPT-4, but unlimited tokens and a fraction of the price. Ideal for batch processing, code review, document analysis, and anything where throughput matters more than latency.

Context

262k tokens

Input

Text + images

Output

Text

Hosting

EU only

Questions

How does billing work?

Flat monthly fee. Pay once, get unlimited access for 30 days. No auto-renewal — you decide when to top up.

Basic or Pro?

Basic (€20) for light, occasional use with one concurrent request. Pro (€50) for daily workloads with three concurrent requests and priority queuing.

What does unlimited tokens mean?

No token cap and no overage charges. The only limit is how fast the model generates — throughput, not quota.

Are prices including VAT?

No — all prices are net, plus statutory VAT. Intended for business use.

Can I use the OpenAI SDK?

Yes. The API is fully OpenAI-compatible. Point any SDK at our base URL with your API key and it works.

Start building today.

No subscription minimums. No token limits. Just a model and an API key.

Get your API key

Rent a model.Skip the GPU.