LLM inference that tells you where it runs.

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://router.sokkan.ch/v1",  # the only change
    api_key=os.environ["SOKKAN_API_KEY"],
)
resp = client.chat.completions.create(
    model="qwen/qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello"}],
    extra_headers={"X-Data-Location": "EU"},
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://router.sokkan.ch/v1",  // the only change
  apiKey: process.env.SOKKAN_API_KEY,
});
const stream = await client.chat.completions.create(
  { model: "qwen/qwen3.8-27b", stream: true,
    messages: [{ role: "user", content: "Hello" }] },
  { headers: { "X-Data-Location": "EU" } },
);
for await (const chunk of stream)
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

curl https://router.sokkan.ch/v1/chat/completions \
  -H "Authorization: Bearer $SOKKAN_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Data-Location: CH" \
  -d '{
    "model": "moonshotai/kimi-k2.6",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'