> ## Documentation Index
> Fetch the complete documentation index at: https://agent-harness101.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Token levers

> There are several levers. Model routing is one strategy.

## The question

Our agent is consuming too many tokens. How would you reduce it?

## The answer

There are several levers. Model routing is one strategy.

* Prune / compact — old context

* Retrieve better — read less

* Cache — reusable context

* Reduce outputs — dedupe logs

* Subagents — isolate exploration

* Model routing — match cost to reasoning

* **90%** — max cost reduction from prompt caching — Anthropic’s own published figure

* **85%** — max latency reduction on long, cached prompts

* **1 of 6** — caching is one lever — routing is the one this deck traces next

### Source

[Anthropic docs — prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching) — Only the cache lever gets numbers here because it’s the one with an official published figure. The other five are real, common patterns — no invented percentages attached.

<Tip>
  **Design decision:** One optimization strategy among several — *routing is covered next.*
</Tip>

## Continue the walkthrough

<Card title="Enforce with a hook" icon="arrow-right" href="/cost/enforce-with-a-hook">
  Continue to topic 7 of 14.
</Card>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.