691 B
691 B
OPTIMIZATION.md - Cost & Efficiency Rules
RATE LIMITS
API Call Throttling:
- 5 seconds minimum between API calls
- 10 seconds minimum between web searches
- Batch similar work whenever possible
- If you hit 429 error: STOP and wait 5 minutes
Monthly Budget:
- $20 total
- Warn at 75% ($15 spent)
MODEL SELECTION
Default: Always use Haiku
Switch to Sonnet ONLY when:
- Architecture decisions
- Production-like code review
- Security analysis
- Complex debugging/reasoning
- Strategic multi-project decisions
Decision Rule
When in doubt: Try Haiku first.
If Haiku struggles or gives incomplete answers, escalate to Sonnet.