cuopt-routing-api-python

Intelligent model selection middleware for AI agents. Route tasks to the best model, manage context, and cut API costs 40-70%.

Route any prompt to the best-performing LLM using peer-reviewed council rankings from LLM Council

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user…

Routage automatique vers le modèle optimal selon le type de question (local gratuit vs API payant)