09Design the rate limits and usage tiers for a model API.▼mediumNewOpenAIAnthropicGoogle○ sign inRate limits protect capacity and fairness, and they shape the developer experience as much as any feature on the API. The interviewer wants limits by dimension, tiers that grow with trust, and clear behaviour when limits hit.Practise this question →Read answer →
28A customer set a $1,000 AI spend cap. Why did we let the bill reach $1,100?▼expertNewCursorGoogleReplit◆ premiumA dashboard shows settled charges while concurrent requests create new liabilities. Define what the cap promises, reconcile the exposure and decide how the product behaves when money is reserved.Practise this question →Read answer →
30Design a cheaper, slower tier for our model API. What discount, what turnaround promise, and how do you stop it eating standard revenue?▼mediumNewOpenAIAnthropicAmazon◆ premiumBatch pricing sells your idle GPU hours. Promise a completion window rather than a latency, make the API shape unsuitable for interactive use, and don't charge for work you couldn't do.Practise this question →Read answer →
39Our API is stateless. Should we store conversation state on the server, and what happens to customers who can't let us store anything?▼hardNewOpenAI◆ premiumServer-side state simplifies integration and can improve caching, but it means storing data and it does not make old tokens free. Offer it as an option with short retention and give zero-retention customers an equal stateless path.Practise this question →Read answer →