cost-aware-llm-pipeline

SKILL.md

Patterns for controlling LLM API costs while maintaining quality. Combines model routing, budget tracking, retry logic, and prompt caching into a composable pipeline.

Automatically select cheaper models for simple tasks, reserving expensive models for complex ones.

Track cumulative spend with frozen dataclasses. Each API call returns a new tracker — never mutates state.

Kostenoptimierungsmuster für die LLM-API-Nutzung – Modellrouting nach Aufgabenkomplexität, Budgetverfolgung, Wiederholungslogik und Prompt-Caching. Quelle: affaan-m/everything-claude-code.

Original anzeigen