Module 01 — Models & CLI overview

In this module

You'll know how to pick the right model for the right task (Claude, GPT-5.4, Gemini 3.1 Pro, open-source), you'll know the strengths and limits of every agentic CLI on the market, and you'll understand why Claude Code offers the deepest harness engineering.

1.1 — The Claude family: reasoning and long context

Anthropic ships three models in the Claude 4.6 family. Each targets a specific segment of the development workflow, and you'll find them directly in Claude Code via the --model flag or the /model command.

The three tiers

Model Target Context Typical use case
Opus 4.6 Deep reasoning 1M tokens Architecture, multi-file refactoring, complex decisions
Sonnet 4.6 Perf/cost ratio 1M tokens Daily development, code review, test generation
Haiku 4.5 Speed and minimal cost 200K tokens Classification, reformatting, lightweight subagent tasks

Picking the model in Claude Code

Claude Code
# Launch a session with Opus
claude --model opus

# Switch mid-session
/model sonnet

# Set a default model in /config
# Or specify model: haiku in a subagent's config

Key takeaways

• Opus 4.6 is the flagship model for complex reasoning and large-scale code tasks

• Sonnet 4.6 covers 80% of daily tasks at a cost significantly lower than Opus

• The 1M tokens window lets you analyze an entire project — architecture, tests, configuration — in a single pass

• Extended thinking gives Claude the ability to "think" before answering, step by step

• The safety-first approach (Constitutional AI) reduces hallucinations: Claude prefers to flag uncertainty rather than generate plausible but wrong code

In this module

  1. 1.1 — The Claude family: reasoning and long context Available
  2. 1.2 — The GPT family: the versatile giant
  3. 1.3 — The Gemini family: natively multimodal
  4. 1.4 — Open-source models: freedom and self-hosting
  5. 1.5 — Model comparison: decision grid
  6. 1.6 — Claude Code: the terminal-first agentic tool
  7. 1.7 — Codex CLI: OpenAI's answer
  8. 1.8 — Gemini CLI: Google's free entry
  9. 1.9 — Aider, Cline, Continue: the model-agnostic alternatives
  10. 1.10 — GitHub Copilot: the autocompletion pioneer
  11. 1.11 — Cursor: the AI-first IDE
  12. 1.12 — Windsurf, Augment and the rest: the expanding ecosystem
  13. 1.13 — Why this course focuses on Claude Code

Locked content

Unlock the full course to access this module.

Unlock

Already purchased? Recover access