Retrieval (RAG)
Answering from retrieved passages, where the answer must stay inside the supplied context and a reranker usually matters as much as the generator.
Le routeur associe une tâche à des modèles candidats, puis applique votre politique : d'abord la région, puis le prix, puis le modèle avec le meilleur résultat documenté.
Prefer a generator with documented citation behaviour and a long context window, keep the embedding and reranker models inside the same residency boundary, and route document extraction to a dedicated OCR model.
{"model":"llmeu-auto","messages":[{"role":"user","content":"…"}],"llmeu":{"task":"rag"}}Recommandé
No first-party endpoint yet
No first-party endpoint serves this task yet. The models listed below are catalogued for reference and run under their own provider’s terms.