Agentic Workflow Cost Forecaster

Forecasts per-workflow and monthly spend for agentic AI systems across current provider tiers (Opus 5, Sonnet 5, Haiku 4.5, GPT-5.6 Sol/Terra/Luna, Gemini 3.1 pro / 3 flash) — decomposes prompt vs. completion vs. cached vs. tool-call tokens, models retry and self-repair overhead, prices multi-provider routing, and produces a scenario table and per-tier break-even chart so teams can pick a default tier without benchmarking every model