STORY · PRODUKTER_

Claude Code uses 33,000 tokens before reading your prompt

An analysis from Systima shows that Claude Code sends significantly more tokens to the Anthropic API before actually processing the user's question, compared to OpenCode. The test documented that Claude Code had poorer cache strategy and higher overhead than the alternative.

WHY IT MATTERS

It affects users' actual costs when using AI coding agents, and suggests that Claude Code's implementation has inefficiencies that make it more expensive to run in practice even though the model's API price is identical.

SOURCES

MACHINE-GENERATED SUMMARY This summary is written by machine from the sources below. We sort and explain — but we are a way into the field, not the final word. Check the source when something matters to you.