When an upstream provider returns a 429: Too Many Requests, how do you implement a "Circuit Breaker" pattern so your entire application doesn't crash?

How would you implement a "Token Quota" system to prevent a single user or a bug in your code from spending $1,000 on API calls in an hour?

How does reducing the precision of model weights from 16-bit to 4-bit impact your infrastructure costs?

You have a task that requires complex reasoning 10% of the time and simple extraction 90% of the time. How do you architect a "Router" to save costs?