Simulating realistic Document summarization parameters (25,000 in / 600 out with 10% cache reuse). OpenRouter Auto-Best Router delivers a 65% cost reduction over Claude 3.5 Sonnet.
| Traffic Volume Tier | Claude 3.5 Sonnet Monthly | OpenRouter Auto-Best Router Monthly | Monthly Savings by picking OpenRouter Auto-Best Router |
|---|---|---|---|
| 1,000 reqs/mo (Dev/Testing) | $77.25 | $26.80 | Save $50.45 / mo |
| 10,000 reqs/mo (Small App) | $772.50 | $268.00 | Save $504.50 / mo |
| 100,000 reqs/mo (Growth Production) | $7,725.00 | $2,680.00 | Save $5,045.00 / mo |
| 1,000,000 reqs/mo (Scale SaaS) | $77,250.00 | $26,800.00 | Save $50,450.00 / mo |
OpenRouter Auto-Best Router is 65% cheaper for Document summarization workloads. At standard Document summarization parameter ratios (25,000 input tokens, 600 output tokens, 10% cache hit), OpenRouter Auto-Best Router costs $0.0268 per request compared to $0.0773 on Claude 3.5 Sonnet.
Claude 3.5 Sonnet offers a context window of 200,000 tokens (max output: 8,192), while OpenRouter Auto-Best Router offers 1,000,000 tokens (max output: 32,768).
At 100,000 requests per month, using OpenRouter Auto-Best Router saves $5,045.00 every month (or $60,540.00 annually) compared to Claude 3.5 Sonnet.
Long-context models pay off here — compare price per 1M tokens at your true document size. Summarize once, store the result; don't re-summarize unchanged documents. For batch backfills, nightly jobs can use cache-friendly request ordering.