Mintplex-Labs/anything-llm
120 source files scanned · 18 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics)
[](https://tokenzero.sh/audit/mintplex-labs/anything-llm)
Models referenced
none detected
Findings
| Severity | Where | Finding | Est. |
|---|---|---|---|
| low | server/utils/agents/aibitat/providers/helpers/anthropicTooled.js:177 | Tool definitions sent without a cache breakpoint Tool schemas render before the system prompt in the cached prefix. Without a breakpoint on the last tool they are billed in full on every call. Fix: TokenZero marks the last tool automatically; manually, add `cache_control` to the last tool definition. | 8% |
| low | server/utils/agents/aibitat/providers/helpers/anthropicTooled.js:321 | Tool definitions sent without a cache breakpoint Tool schemas render before the system prompt in the cached prefix. Without a breakpoint on the last tool they are billed in full on every call. Fix: TokenZero marks the last tool automatically; manually, add `cache_control` to the last tool definition. | 8% |
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