anth-cost-tuning
Installation
SKILL.md
Anthropic Cost Tuning
Overview
Optimize Claude API spend through model routing, prompt caching, the Message Batches API, and real-time cost tracking. The four biggest levers: model selection (4-19x), prompt caching (10x input), batches (2x), and max_tokens discipline.
Pricing Reference (per million tokens)
| Model | Input | Output | Cache Read | Cache Write |
|---|---|---|---|---|
| Claude Haiku | $0.80 | $4.00 | $0.08 | $1.00 |
| Claude Sonnet | $3.00 | $15.00 | $0.30 | $3.75 |
| Claude Opus | $15.00 | $75.00 | $1.50 | $18.75 |
Message Batches: 50% off all model pricing for async processing.