Checking status…

Leyoda Inference

A private, sovereign large-language-model API — running on Leyoda's own hardware. Your model, your data, no third-party clouds. OpenAI-compatible, so it drops into any existing tool.

Base URL

https://llm.leyoda.eu/v1

Model

Qwen3-30B-A3B

Auth

Bearer API key

Quick start — curl

# OpenAI-compatible chat completion
curl https://llm.leyoda.eu/v1/chat/completions \
  -H "Authorization: Bearer $LEYODA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"Qwen3-30B-A3B","messages":[{"role":"user","content":"Hello"}]}'

Quick start — Python (openai SDK)

from openai import OpenAI

client = OpenAI(base_url="https://llm.leyoda.eu/v1", api_key="$LEYODA_API_KEY")
resp = client.chat.completions.create(
    model="Qwen3-30B-A3B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

View status Request an API key