Phase 0: LLM Fast Track · 45 min · OpenAI SDK · Anthropic SDK · Python

LLM APIs in Practice

Model selection is not a one-time decision — it's an ongoing engineering discipline.

Hiring signal: Model routing and API selection appear in every AI engineer system design interview.

What you will learn

Call OpenAI, Anthropic, and Google Gemini APIs using their official Python SDKs
Apply a 5-dimension model selection framework (quality, latency, cost, privacy, scale)
Implement a tiered routing strategy that sends requests to the right model for the task

The Problem

A team ships a product on GPT-4 Turbo. Three months later OpenAI deprecates the model version, the bill triples after a pricing change, and the competitor released the same feature using Claude Haiku at 1/20th the cost. This isn't bad luck — it's an engineering failure: the team never built model selection as a system. They hardcoded a single model ID and called it done.

What you'll build
A unified LLM client that wraps multiple providers behind a single interface, plus a model router that picks the right tier for each task type. By the end of this lesson, you can swap models without changing application code.

The Modern LLM Landscape (2026)

The market has stratified into four tiers. Knowing which tier fits which job is the first skill of an AI engineer.

Tier	Models	Cost (input/1M tokens)	Best for
Frontier	Claude Opus 5, GPT-5, Gemini 2.5 Pro	2–15 USD	Complex reasoning, nuanced judgment
Workhorse	Claude Haiku 4.5, GPT-5 mini, Gemini 2.5 Flash	0.10–0.30 USD	High-volume, structured tasks
Open-weight	Llama 3.3 70B, Mistral, DeepSeek V3	~0 (self-hosted)	Privacy-sensitive, cost-sensitive at scale
Edge/Small	Phi-4, Gemma 3	~0	On-device, ultra-low latency

The key insight: frontier ≠ correct choice. A workhorse model handles 90% of production tasks at 1/20th the cost. You should be able to justify your model choice across five dimensions.

Model names and prices move fast
Tier table last reviewed August 2026. Specific model names and per-token prices change every few months — always check the provider's current pricing page before you commit to a number. The tiering is the durable idea; the names in it are not.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The 5-Dimension Selection Framework, Calling the APIs — Unified Pattern, Build It, What to Practice — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.