Skip to main content
LiteLLM is moving to Rust Read the latest updates.

LiteLLM v1.110.1, v1.111.0rc2 and v1.106.11 fix GPT-6.2 prompt caching

Released

Deploy this version​

docker run \
-e LITELLM_MASTER_KEY=sk-<paste-a-long-random-key> \
-e DATABASE_URL=postgresql://<user>:<password>@<host>:5432/<dbname> \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
docker.litellm.ai/berriai/litellm:1.111.0-rc.2

This release is published as ghcr.io/berriai/litellm:v1.111.0-rc.2. See the GitHub release and the full releases page.

v1.111.0rc2 is a release candidate on top of v1.111.0rc1. There are no new database migrations. The v1.111.0-rc.2 tag points at e527244.

What's Changed​

  • OpenAI: Fixed GPT-6.2 prompt caching for system prompts sent to /v1/chat/completions or /v1/messages with store: false - PR #52599 and PR #52694

The change is backported in PR #52657.

Full Changelog​

https://github.com/BerriAI/litellm/compare/v1.111.0-rc.1...v1.111.0-rc.2

LiteLLM Enterprise
SSO/SAML, audit logs, spend tracking, multi-team management, and guardrails, built for production.
Learn more →