Maximizing the value of your Claude Code sessions
- Input and output tokensA 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).
- Then, during decode, it writes output tokens: its thinking, the tool calls it makes, and the text you see.
Unverified
- Input and output tokensA 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).
- Then, during decode, it writes output tokens: its thinking, the tool calls it makes, and the text you see.
Sources: Claude