lobehub/lobe-chat
120 source files scanned · 20 LLM call site(s) · ~2% of LLM spend looks recoverable (static heuristics · repo looks like an app)
[](https://tokenzero.sh/audit/lobehub/lobe-chat)
Models referenced
none detected
Findings
| Severity | Where | Finding | Est. |
|---|---|---|---|
| medium | packages/model-runtime/src/core/openaiCompatibleFactory/index.ts:1652 | LLM call inside a loop Per-item calls repeat the full prompt prefix for every element. If items are independent and latency-tolerant, the provider Batch API is 50% cheaper, and OpenAI Flex processing (`service_tier: "flex"`) gives the same 50% on ordinary calls without restructuring; if the prefix is shared, caching pays off immediately. Fix: Batch where possible, or set `service_tier: "flex"` on OpenAI calls that can wait; otherwise keep the shared prefix cache-formatted (TokenZero does this automatically). | 25% |
| medium | packages/model-runtime/src/core/openaiCompatibleFactory/createImage.ts:226 | LLM call inside a loop Per-item calls repeat the full prompt prefix for every element. If items are independent and latency-tolerant, the provider Batch API is 50% cheaper, and OpenAI Flex processing (`service_tier: "flex"`) gives the same 50% on ordinary calls without restructuring; if the prefix is shared, caching pays off immediately. Fix: Batch where possible, or set `service_tier: "flex"` on OpenAI calls that can wait; otherwise keep the shared prefix cache-formatted (TokenZero does this automatically). | 25% |
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