Title: LLM API quickstart: dit f%C3%B8rste kald %E2%80%94 LLM EU Canonical: https://llmeu.com/da/docs/quickstart/ Markdown mirror: https://llmeu.com/da/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 Kom i gang - [Hurtig start](/da/docs/quickstart/) - [Konsol](/da/docs/console/) - [Migrering](/da/docs/migration/) - [API-reference](/da/docs/api/) Reference - [Autentificering](/da/docs/authentication/) - [Endepunkter](/da/docs/endpoints/) - [Fejl](/da/docs/errors/) - [Hastighedsgr%C3%A6nser](/da/docs/rate-limits/) - [Streaming](/da/docs/streaming/) - [Politikker](/da/docs/policies/) - [Routing og politik](/da/docs/routing/) - [Residens og regioner](/da/docs/residency/) - [Bevis og verifikation](/da/docs/evidence/) - [OpenAI-kompatibilitet](/da/docs/openai-compat/) Drift - [Selvhosting](/da/docs/self-hosting/) # Hurtig start - 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); ``` ## API-reference ## Bevis og verifikation 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}`. Priser registreres pr. endpoint og vises pr. million tokens. En model uden et live endpoint er kun katalog: den kan ikke kaldes her, og der opkr%C3%A6ves intet for den.