Skip to content
andr[ai]d

// AI Engineering

Prompt Caching Explained

Oct 1, 2026 · 4 min read · 👁 –

#models#cost

Sample content: placeholder post for the v1 design.

Sample content. This is a placeholder post for the first version of the site.

Why this matters

How prompt caching works, when it saves tokens and money, and how to use it in your agent workflows. This section is filler text that shows how long-form reading looks on Andraid, with comfortable line length and spacing.

A quick example

const agent = createAgent({ model: 'frontier-model', tools: [search, shell] });
for await (const step of agent.run('Fix the failing test')) {
  console.log(step.type, step.summary);
}

Comparison

Model Context Tool use Price / 1M tokens
Model A 200K Excellent $3.00
Model B 1M Good $1.25
Open-weight C 128K Fair Self-hosted

Takeaways

  • Measure on your own tasks, not just leaderboards.
  • Use prompt caching and small models where possible.
  • Keep the harness simple until it hurts.