LiteLLM 1.100.0-rc.1 routes housekeeping calls to the cheapest tier and splits cache savings by who earned them.

The RC published August 30 adds a complexity_router rule sending client housekeeping calls to the cheapest model tier, and reports prompt caching savings as two numbers, total and gateway-attributed, so you can tell what the proxy saved you from what the provider would have cached anyway. It also drops and self-heals empty thinking blocks on the Anthropic /v1/messages bridge. (GitHub)