static audit · 2026-10-25T22:34:40.910Z

ggerganov/llama.cpp

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

No recognised LLM call sites (OpenAI, Anthropic, Gemini, Vercel AI SDK, LangChain, LiteLLM). Calls behind custom wrappers are not detected.

badge   ![TokenZero audit](https://tokenzero.sh/v1/badge/audit/aud_GbNzj6GfZqQ54nn-4VuWDg.svg)

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

Models referenced

none detected

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