03 Model garden Serve

Loes World

Name: Loes World hosting (EU)
Brand: HostYourAI
Price: 0.25 EUR
Availability: InStock

curl

$ curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hyai/loes-qwen3-14b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

Serve Model garden vLLM ready

hyai/loes-qwen3-14b

text->text · hostyourai · sovereign EU

Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain

Sovereign EU model fine-tuned by HostYourAI on loes-xl-pre.

Router: Router · available
Dedicated: Dedicated · available
Input (per 1M tokens): €0.25
Output (per 1M tokens): €0.40

66KContext window

48GBMinimum VRAM

POST /api/v1/chat/completions 200 OK

Specifications

Context window	65,536 tokens
Minimum VRAM	48 GB
Architecture	Qwen3ForCausalLM (vLLM)
License	open-weights
Modality	text->text
Publisher	hostyourai ↗

Pricing

Shared router · per token

€0.25Input (per 1M tokens)

€0.40Output (per 1M tokens)

Dedicated GPU · per hour

from €2,21 per hourYour own vLLM instance on European cloud (48 GB VRAM), billed per minute.

Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.

✓ Verified working on 28-07-2026, responded in 196 ms on our EU infrastructure.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

~78.4 / 100 · Estimate

Our own finetune: the number of its base model, Qwen/Qwen3.8-27B.

Range 75.9 to 81.0

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 07-11-2026

Questions

Frequently asked questions

Can I run Loes World in the EU?

Yes. HostYourAI runs Loes World on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting Loes World GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does Loes World cost?

Via the shared EU router you pay €0.25 per million input tokens and €0.40 per million output tokens, with no fixed costs. For high volume or isolation you can also run Loes World on a dedicated GPU instance, billed per minute.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.