static audit · 2026-10-25T22:33:48.582Z

Helicone/helicone

120 source files scanned · 7 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics · repo looks like an app)

$80per 10k runs today (gpt-4o, ~2000 prompt tokens)
$80per 10k runs with fixes applied

badge   ![TokenZero audit](https://tokenzero.sh/v1/badge/audit/aud_CNie1U0iq2cgb0Qa48xywQ.svg)

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

Models referenced

gpt-4o ×2 (cheaper sibling: gpt-4o-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