static audit · 2026-10-25T22:34:01.062Z

confident-ai/deepeval

120 source files scanned · 54 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics)

$2.2per 10k runs today (gpt-5-nano, ~2000 prompt tokens)
$2.2per 10k runs with fixes applied

badge   ![TokenZero audit](https://tokenzero.sh/v1/badge/audit/aud_GF3m-QVxdBnOcfA3eTMf6g.svg)

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

Models referenced

gpt-5-nano ×7
gpt-3.5-turbo ×1

Findings

SeverityWhereFindingEst.
infotypescript/examples/prompt/example-prompt-pull.ts:20Unrecognised model id "gpt-3.5-turbo"
Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers.
Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`.		0%

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