Most AI products are two hundred lines of glue around one API call.
A1 · Building With Model APIs
The call itself is the easy part. What separates a demo from a product is a key nobody can copy, streaming that feels instant, retries that do not double your bill, and an eval set that blocks a merge before a prompt change reaches anyone. This chapter builds all of it around one small support feature, prices every request in cents, and turns a wait into a number you can plan with. By the end you choose a model with your own test instead of a leaderboard.
- Anatomy of a Request
- Where the Key Lives
- Streaming
- Structured Outputs
- Tool Calling in Production
- Prompt Caching
- Cost and Latency Budgets
- Retries and Fallbacks
- Seeing What Happened
- Evals in CI
- Choosing a Model