HN
login
Show HN: Does per-step reasoning effort save money in Claude Code?github.com

Per-step reasoning effort for Claude Code, chosen by Jev, without breaking the prompt cache. Unofficial. - ifoster01/jev-effort

4 points•ifoster41901•7 days ago•2 comments•
#effort#step#code#reasoning#claude#claude code#reasoning effort#step reasoning

2 comments

ethan19986 days ago
If you change reasoning during a session, LLM needs to recompute KV cache. Maybe I get it wrong, but I don't think it can save money.
ifoster41901about 21 hours ago
The newer models from both OpenAI and Anthropic allow you to dynamically change reasoning effort without resetting cache

Read the full thread on Hacker News →

Related stories