Maximizing the value of your Claude Code sessions | Claude by Anthropic
claude.com · 2,200 words · saved by 1 readers
Practical tips for how to run efficient sessions that get the most value from every token.
Input and output tokens A request goes through the GPU in two phases, and they cost different amounts. First, during prefill, the model reads your request and context: the system prompt, your CLAUDE.md, your message, and everything that's been added to the conversation since (the files Claude has read and the output of the commands it ran). Those are your input tokens. Then, during decode, it writes output tokens: its thinking, the tool calls it makes, and the text you see. This happens one token at a time; a 200-token response is 200 runs of the model, one after the other. Per token,…
saved by
related reading
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- How I Use Claude Code | Philipp Spiessspiess.dev
- Claude Code Cheat Sheetcc.storyfox.cz
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Explore the context window - Claude Code Docscode.claude.com
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Don’t Outsource Your Thinkingteltam.github.io
- Thariq on X: "Lessons from Building Claude Code: Prompt Caching Is Everything " / Xx.com
- Prompting best practicesdocs.anthropic.com
- GitHub - ykdojo/claude-code-tips: 40+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills for everydgithub.com
- Portal by Spotify cut my Claude Code token usage by 90% | Spotify Engineeringengineering.atspotify.com
- Claude Code is My Computer | Peter Steinbergersteipete.me