M

model-routing

Single-header C++17: pick a model per prompt from a complexity score and a cost, latency, quality or budget strategy. Part of llm-cpp.

Case study of a pre-alpha Algebra I tutoring platform focused on hybrid AI/deterministic architecture, multi-provider LLM evaluation, safety controls, and measured cost/latency tradeoffs.

Route each subagent to the cheapest capable model - about 70% off execution-tier tokens in our tests (Claude Code / any multi-tier agent platform)