model-manager
notestone ์ ์
Productivity & Tasks์์ฝ
**๐ฐ Optimize Your API Costs: Route Simple Tasks to Cheaper Models.**.
์ค๋ช
์ด ์คํฌ์ด ํ๋ ์ผ
Routes AI tasks to cost-appropriate models based on task complexity. Fetches real-time pricing from OpenRouter and classifies tasks into simple, coding, creative, or complex categories. Integrates with a companion benchmarks skill for data-driven model selection.
Instead of manually tracking model pricing and capabilities across providers, it automates routing decisions and updates cost data in real time.
์ฌ์ฉ ์์
- Routing translation jobs to cheaper models to cut API costs
- Comparing current OpenRouter model prices before starting a project
- Setting a budget cap with alerts for a team's monthly API spend
- Generating a 30-day cost report to audit model usage
- Automatically switching to a stable fallback when a cheap model fails repeatedly
์์ ์ํฌํ๋ก
User asks: plan 'translate this product description to French'
- 1
Fetches current model pricing from OpenRouter
- 2
Classifies the task as simple content work
- 3
Identifies GPT-4o-mini or Gemini Flash as cost-optimal choices
- 4
Returns recommended model with estimated cost and savings percentage
Routing recommendation: use GPT-4o-mini at $0.60/1M tokens (96% cheaper than premium models)
์๊ตฌ ์ฌํญ
- OpenRouter API key
์ค์น
clawhub install notestone/model-managerCLI ๋ช ๋ น์ ์คํํ๊ฑฐ๋, ํ๋กฌํํธ๋ฅผ Claude Code, Cursor, Codex ๋ฑ ์ฌ์ฉํ๋ ์ฝ๋ฉ ์์ด์ ํธ์ ๋ถ์ฌ๋ฃ์ผ์ธ์.