Metrics guide

Measuring token compression

Not all token compression is equal. Understanding the right metrics helps you evaluate whether compression is actually saving you money without hurting quality.

By Arjun Shah - Creator of SuperCompress - Updated 2026-07-03

Key metrics explained

MetricDefinitionTarget
Compression ratioTokens removed / original tokens60-85%
Oracle recall% of answer lines preserved100%
Cost savingsMonthly $ savedAs high as possible
Quality deltaAnswer accuracy change≥0% (no degradation)

Frequently asked questions

What compression ratio should I target?

Start with 65%. Higher ratios may start to impact quality.

How do I measure answer quality after compression?

A/B test: run 100 queries with and without compression, compare answers for factual accuracy.

Build with less context

Put compression in front of your next LLM call.

Use the hosted API or run SuperCompress locally. Keep the evidence, drop the token waste, and measure the savings before it reaches your model.

Get an API keyRead the guide