LiteLLM v1.109.0-dev.1

LiteLLM releases published LiteLLM v1.109.0-dev.1. This automated release-watch entry was generated from the project's official GitHub release feed and is kept separate from human-reviewed editorial analysis. Release notes: Verify this release cosign verify \ --key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \ ghcr.io/berriai/litellm:v1.109.0-dev.1 Same command for litellm-database , litellm-non root and the docker.io/litellm/ images What's new in 1.109.0-dev.1 704 PRs. 113 added, 312 fixed, 46 changed, 11 improved, 8 removed. 15 need action Action required Deployment: Update image verification to use the new cosign.pub key ( 48103 ) Chat completions: Guard chunk.choices 0 reads with if chunk.choices: when include usage is set ( 47109 ) Vertex AI and Gemini: Set drop params: true or stop sending temperature , top p and top k to Gemini 3.6 Flash, 3.5 Flash-Lite and newer ( 47645 ) Cost tracking and pricing: Read max input tokens and max output tokens instead of max tokens from the cost map ( 48471 ) Anthropic: Set max tokens on requests to unmapped…

• Review the official LiteLLM releases release notes before upgrading.
• Check compatibility, migration, and security notes against your current agent stack.
• Run focused regression tests before production rollout.