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
- How I Use Claude Code | Philipp Spiessspiess.dev
- Best practices for Claude Code - Claude Code Docsanthropic.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Claude Code Cheat Sheetcc.storyfox.cz
- Prompting best practicesdocs.anthropic.com
- Explore the context window - Claude Code Docscode.claude.com
- Lessons from Building Claude Code: Prompt Caching Is Everythingx.com
- Thariq on X: "Lessons from Building Claude Code: Prompt Caching Is Everything " / Xx.com
- Don’t Outsource Your Thinkingteltam.github.io
- How I use Claude Code on large projectslocalcan.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- How We Use Claude Code Skills to Run 1,000+ ML Experiments a Dayhuggingface.co