Title: Quickstart API LLM: la prima chiamata %E2%80%94 LLM EU
Canonical: https://llmeu.com/it/docs/quickstart/
Markdown mirror: https://llmeu.com/it/docs/quickstart.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

Inizia

- [Avvio rapido](/it/docs/quickstart/)
- [Console](/it/docs/console/)
- [Migrazione](/it/docs/migration/)
- [Riferimento API](/it/docs/api/)

Riferimento

- [Autenticazione](/it/docs/authentication/)
- [Endpoint](/it/docs/endpoints/)
- [Errori](/it/docs/errors/)
- [Limiti di frequenza](/it/docs/rate-limits/)
- [Streaming](/it/docs/streaming/)
- [Policy](/it/docs/policies/)
- [Routing e policy](/it/docs/routing/)
- [Residenza e regioni](/it/docs/residency/)
- [Prove e verifica](/it/docs/evidence/)
- [Compatibilit%C3%A0 OpenAI](/it/docs/openai-compat/)

Operazioni

- [Self-hosting](/it/docs/self-hosting/)

# Avvio rapido

- Create an account in the[console](https://app.llmeu.com/app/signup) and copy the API key %E2%80%94 it is shown once.
- Point any OpenAI-compatible client at `https://api.llmeu.com/v1`.
- Call `llmeu-auto` and read the `llmeu` block in the response.

## cURL

```
curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llmeu-auto",
    "messages": [{"role": "user", "content": "Say hello from EU hosting."}],
    "llmeu": {"residency": "eu-hosted", "task": "general"}
  }'
```

## Python

```
from openai import OpenAI

client = OpenAI(base_url="https://api.llmeu.com/v1", api_key="llmeu_live_xxxxxxxx.your-secret")

resp = client.chat.completions.create(
    model="llmeu-auto",
    messages=[{"role": "user", "content": "Say hello from EU hosting."}],
)
print(resp.choices[0].message.content)
print(resp.llmeu.inference_region, resp.llmeu.trace_id)
```

## JavaScript

```
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmeu.com/v1", apiKey: process.env.LLMEU_API_KEY });

const resp = await client.chat.completions.create({
  model: "llmeu-auto",
  messages: [{ role: "user", content: "Say hello from EU hosting." }],
});
console.log(resp.choices[0].message.content);
console.log(resp.llmeu.inference_region);
```

## Riferimento API

## Prove e verifica

Every response carries a `llmeu` block: `trace_id`, `model_used`, `inference_region`, `sovereignty_class`, `route_reason` and the retention that applied. Fetch the full row with `GET /platform/v1/traces/{id}`.

I prezzi sono registrati per endpoint e mostrati per milione di token. Un modello senza endpoint attivo %C3%A8 solo catalogo: non pu%C3%B2 essere chiamato qui e non viene addebitato nulla per esso.