static audit · 2026-10-25T22:30:49.419Z

langchain-ai/langgraph

120 source files scanned · 14 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics)

$4.8per 10k runs today (gpt-4o-mini, ~2000 prompt tokens)

$4.8per 10k runs with fixes applied

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

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

Models referenced

claude-3-sonnet-20240229 ×3
gpt-4o-mini ×3
gpt-3.5-turbo ×1
gpt-4o ×1 (cheaper sibling: gpt-4o-mini)

Findings

Severity	Where	Finding	Est.
info	`examples/chatbot-simulation-evaluation/simulation_utils.py:51`	Unrecognised 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%
info	`libs/cli/examples/graphs_reqs_b/graphs_submod/agent.py:15`	Unrecognised model id "claude-3-sonnet-20240229" 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