Tuesday, January 6, 2026
Claude Code Usage & Cost
People are discussing Claude Code's API pricing based on token usage, its potential for infinite memory plugins to reduce costs and overcome context limitations, and its performance compared to OpenAI Codex.
Claude Code processes tokens as the fundamental unit of API consumption. MTok (million tokens) quantifies usage across three dimensions: base input tokens for standard prompts, cache writes for storing reusable context, and cache hits for retrieving cached prompts at reduced
Claude Code with infinite memory is now possible. Claude-Mem is a free plugin to persist memory across Claude sessions. - Up to 95% fewer tokens per session. - 20× more tool calls before context limits. 100% open-source.
how do u think they make money? Plus, that’s API pricing plus $1 in Claude code is worth 100x more because it’s only based on usage not tokens