# Cutting LLM costs (/ai--llm-cost-optimizer)

/ai--llm-cost-optimizer is a Claude Code skill in the AI & Agents section. Measures where your app spends tokens, then applies model routing, caching and prompt compression, keeping each change only if an eval shows quality holds.

- Web version: https://skills.sgomez.dev/en/s/ai--llm-cost-optimizer
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/ai/llm-cost-optimizer.md
- Updated 10 Jul 2026

## How to ask for it

- `/ai--llm-cost-optimizer our Claude API bill spiked, help me bring it down`
- `/ai--llm-cost-optimizer add caching so we don't repeat identical model calls`
- `/ai--llm-cost-optimizer route simple queries to a cheaper model`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install ai-skills@claude-skills-collection
```

## Permissions

- Reads: `**/*`
- Writes: `**/*`
- Runs: —
- Network: No
- Destructive: No

## Author's description

Cut LLM costs: model routing, caching, prompt compression, batching without quality loss

- [How we review this](https://skills.sgomez.dev/en/methodology.md)