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

# AI Cost Optimisation

> The Optimisation engine finds ways to cut your AI cost without changing what your app does.

It analyses your real traffic and surfaces two kinds of savings, each on its own page with its own savings figure and impact simulation. It also checks that the caching you already run works as expected:

<Columns cols={2}>
  <Card title="Model benchmarking" icon="flask" href="/product/model-benchmark">
    Swap to a cheaper model that performs as well.
  </Card>

  <Card title="Prompt caching optimisation" icon="database" href="/product/prompt-caching">
    Capture prompt prefixes your provider prices cheaper.
  </Card>

  <Card title="Prompt caching analyzer" icon="magnifying-glass" href="/product/caching-analyzer">
    What your provider should have cached but did not.
  </Card>
</Columns>

<Warning>
  Optimisations replay your prompt content, which requires `capture message content` in the [auto-instrument](/quickstart#install-and-instrument) step to be set to True (default).
</Warning>