static audit · 2026-10-25T22:34:33.985Z

guidance-ai/guidance

100 source files scanned · 1 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics · repo looks like a library)

Library/SDK layout detected (Python package "guidance" is an LLM SDK/framework): call sites are most likely pass-through wrappers where the caller chooses the model and prompt, so findings are downgraded one level and the estimate is discounted.

$55per 10k runs today (gpt-5, ~2000 prompt tokens)
$55per 10k runs with fixes applied

badge   ![TokenZero audit](https://tokenzero.sh/v1/badge/audit/aud_UwjxiJCrc6UnLhCLoUnlwg.svg)

repo badge   [![LLM spend audited by TokenZero](https://tokenzero.sh/v1/badge/repo/guidance-ai/guidance.svg)](https://tokenzero.sh/audit/guidance-ai/guidance)

Models referenced

gpt-5 ×1 (cheaper sibling: gpt-5-mini)

Findings

No token-waste patterns detected in the scanned files.

Fix all of it with one line

OPENAI_BASE_URL=https://tokenzero.sh/v1
ANTHROPIC_BASE_URL=https://tokenzero.sh

Keys pass through untouched. Cache formatting and exact caching are on by default; cascade routing stays opt-in. How it works