Recommended
The sensible default
The best balance of capability, privacy, and money for the constraints you chose.
- Hardware
- $0 new
- API / month
- $4–$6
- Runs locally
- 27%
- Breaks even
- —
MachineCurrent machineWhatever you already own
Use small local models where practical and spend only on hosted inference.
Model routes
Why it fits
- Avoids capital expense until your real token usage justifies hardware.
- Routine work stays on the economical route while difficult jobs have a clear fallback.
Reality check
- Treat hardware prices as planning allowances and check a live listing first.
- API estimate assumes 70% input / 30% output and excludes caching discounts.