Title: Start rapid API LLM: primul apel %E2%80%94 LLM EU
Canonical: https://llmeu.com/ro/docs/quickstart/
Markdown mirror: https://llmeu.com/ro/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

%C3%8Encepe%C8%9Bi

- [Ghid rapid](/ro/docs/quickstart/)
- [Consol%C4%83](/ro/docs/console/)
- [Migrare](/ro/docs/migration/)
- [Referin%C8%9B%C4%83 API](/ro/docs/api/)

Referin%C8%9B%C4%83

- [Autentificare](/ro/docs/authentication/)
- [Endpoint-uri](/ro/docs/endpoints/)
- [Erori](/ro/docs/errors/)
- [Limite de rat%C4%83](/ro/docs/rate-limits/)
- [Streaming](/ro/docs/streaming/)
- [Politici](/ro/docs/policies/)
- [Rutare %C8%99i politic%C4%83](/ro/docs/routing/)
- [Reziden%C8%9B%C4%83 %C8%99i regiuni](/ro/docs/residency/)
- [Dovezi %C8%99i verificare](/ro/docs/evidence/)
- [Compatibilitate OpenAI](/ro/docs/openai-compat/)

Operare

- [G%C4%83zduire proprie](/ro/docs/self-hosting/)

# Ghid rapid

- 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);
```

## Referin%C8%9B%C4%83 API

## Dovezi %C8%99i verificare

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}`.

Pre%C8%9Burile sunt %C3%AEnregistrate per endpoint %C8%99i afi%C8%99ate per milion de tokeni. Un model f%C4%83r%C4%83 endpoint activ este doar de catalog: nu poate fi apelat aici %C8%99i nu se percepe nimic pentru el.