此内容尚未提供您的语言版本,正在以英文显示。

Llm Cost Optimizer

插件已验证活跃

Use when you need to reduce LLM API spend, control token usage, route between models by cost/quality, implement prompt caching, or build cost observability for AI features. Triggers: 'my AI costs are

1 个 Skill 0 个 MCP

目的

Reduce LLM API spend and control token usage by intelligently routing requests, implementing prompt caching, and providing cost observability for AI features.

功能

Reduce LLM API spend
Control token usage
Route between models by cost/quality
Implement prompt caching
Build cost observability for AI features

使用场景

Use when LLM API costs are a concern
Use to optimize token usage for AI features
Use to select appropriate models based on cost and quality
Use to implement prompt caching for repeated queries

非目标

Improving prompt quality or effectiveness
RAG pipeline design
Designing generic AI endpoints without cost considerations

安装

/plugin install llm-cost-optimizer@alirezarezvani-claude-skills

包含 1 个扩展

Skill (1)

LLM Cost Optimizer 技能

Use proactively whenever LLM API costs come up -- or should. Triggers include: 'my AI costs are too high', 'optimize token usage', 'which model should I use', 'LLM spend is out of control', 'implement prompt caching', 'we're about to launch an AI feature', 'build me an AI endpoint'. Don't wait for an explicit cost complaint -- if someone is building an AI feature, designing an LLM endpoint, or choosing between models, cost architecture belongs in the conversation. Apply immediately when any of these are true: a system prompt appears that exceeds a few hundred tokens, all requests are hitting the same model, max_tokens is not set, or no per-feature cost logging exists. NOT for RAG pipeline design (use rag-architect). NOT for improving prompt quality or effectiveness (use senior-prompt-engineer).