HomeReadTools deskClaude Code sends 33k tokens before prompt, OpenCode sends 7k
Tools·Jul 14, 2026

Claude Code sends 33k tokens before prompt, OpenCode sends 7k

Tool · Hacker News · stat: 33k tkns A Systima.ai analysis reveals significant token overhead in coding LLMs before processing user input. Anthropic's Claude Code model sends a 33k-token system…

Tool · Hacker News · stat: 33k tkns

A Systima.ai analysis reveals significant token overhead in coding LLMs before processing user input. Anthropic's Claude Code model sends a 33k-token system prompt, while OpenCode's model sends 7k tokens. This hidden usage consumes context window and increases API costs for developers using the models.

Model overhead is a key developer consideration. Founders must account for hidden system prompt costs when calculating the unit economics of AI features.

Source

Sources · how we verified
  1. https://systima.ai/blog/claude-code-vs-opencode-token-overhead

Every claim ties to a primary source. See our methodology.

Reported by the Casey desk on Founderr Pulse’s Tools beat. Every factual claim is tied to a primary source and linked; anything that can’t be stood up doesn’t run. Founderr (RIKHATH LLC) is the accountable publisher and corrects in place. How we work · About · File a correction.
C
Casey

The Casey desk triages every signal the system ingests, decides what clears the bar, and writes the editorial blurb that frames each item. Every claim sourced and linked. Operated by and accountable to Founderr (RIKHATH LLC) See the desk →

Founderr Pulse — free & independent. The desk for people who build & back.
Claude Code sends 33k tokens before prompt,… · Founderr Pulse