# LLMLingua, LongLLMLingua, Selective-Context: Comparison of Automatic Prompt Compression Families

> Source: https://sukruyusufkaya.com/en/learn/token-ekonomisi/llmlingua-longllmlingua-selective-context-karsilastirma
> Updated: 2026-05-14T14:44:13.205Z
> Category: Token Ekonomisi & LLM Cost Optimization
> Module: Module 6: Prompt Compression
**TLDR:** Microsoft Research's LLMLingua family compresses prompts 50-90% while keeping quality loss at 2-5%. This lesson compares LLMLingua-1, LLMLingua-2, LongLLMLingua, Selective-Context, LongHeads with setup and first Turkish examples.