Agent decision-making under resource constraints is bounded rationality reborn: Rational Metareasoning uses VOC rewards to save 20-37% of tokens, BATS proves that adding budget without budget awareness is futile, FrugalGPT cascades cut costs by up to 98%, and Speculative Actions reduce latency by 20%. The three constraints ultimately converge into a single Pareto curve, and the overarching trend is moving from humans tuning knobs to models making resource-rational decisions on their own.
Comparing six major Agent CLI subscription plans in 2026 (Claude Code, Cursor CLI, Codex, Kiro, Gemini CLI, OpenCode), and exploring multi-model routing patterns — routing simple tasks to cheaper models and complex tasks to flagship models, with real-world savings of 40-85%.
With multi-model routing, 70% of simple tasks are directed to cheap models, and only 10-15% of complex tasks use flagship models — saving 40-85% on inference costs in practice. This article covers the architecture and implementation of five major open-source tools.
OpenClaw has built-in two-stage fault tolerance with Auth rotation + Model Fallback, plus Prompt Caching for cost savings and comprehensive Token tracking.
RAG system costs come from LLM tokens, Embedding APIs, and vector search. Every stage has room for cost reduction, but you need to verify that optimizations don't sacrifice too much quality.