Question 1

What is context compaction and why does it cost money?

Accepted Answer

A long-running agent accumulates context — tool results, messages, reasoning — until it approaches the model's context window. To keep going it compacts: it feeds the entire current context to the model and asks for a compressed summary, then continues from that summary instead of the full history. The catch is that summarising means re-reading everything, so each compaction event bills the whole context as input tokens plus a small output for the summary. A single compaction of a 150,000-token context costs the same as 150,000 input tokens, and a long agent that compacts several times can spend a fifth to a third of its total tokens on this housekeeping alone.

Question 2

How many times will my agent compact?

Accepted Answer

It depends on how fast context grows and where the trigger sits. If each step adds a few thousand tokens of tool output and the agent compacts when it reaches, say, 140,000 tokens then resets to a 25,000-token summary, it will compact roughly every time it climbs that gap again. A run that adds 8,000 tokens per step and compacts at 140k will fire a compaction about every fifteen steps. This calculator simulates the run step by step, counts the compactions, and separates the productive cost from the compaction overhead so you can see the split.

Question 3

How do I reduce compaction overhead?

Accepted Answer

Three levers move it. Compacting later (a higher trigger) means fewer, bigger compactions but more expensive productive steps because the context you re-read every turn is larger — there is a genuine sweet spot rather than always-higher-is-better. Resetting to a smaller summary buys more runway between compactions. And routing the summarisation itself to a cheaper model, or using prompt caching so the re-read prefix is billed at a discount, cuts the per-event cost directly. The table on this page sweeps the trigger threshold so you can see how total cost bends, and never compacting at all is shown too — usually the worst option because context then grows without bound and every step pays for it.

Question 4

Is compaction cheaper than just using a bigger context window?

Accepted Answer

Often yes, because the alternative to compaction is carrying the full history on every single step, and input cost grows with the square of the run length when nothing is ever trimmed. Compaction caps that growth: after each summary the per-step context drops back down, so productive cost stays roughly linear instead of quadratic. You pay a lump sum at each compaction event, but you avoid re-reading an ever-larger transcript thousands of times. For very short runs the overhead is not worth it; for long autonomous agents it usually pays for itself many times over, which this calculator lets you confirm for your own numbers.

Calculadora de custos de compactação de contexto

Onde a compactação compensa – acionando o gatilho

A limpeza que ninguém orçamenta

Como funciona esta calculadora

Perguntas frequentes

O que é compactação de contexto e por que custa dinheiro?

Quantas vezes meu agente irá compactar?

Como posso reduzir a sobrecarga de compactação?

A compactação é mais barata do que apenas usar uma janela de contexto maior?