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

LiteLLM v1.108.13 (LTS) fixes Unix-socket Postgres boot and GPT-6.2 caching

Released

tip

v1.108.13 is a patch release on the 1.108 LTS line. The lts image tag always points to the latest LTS release, so pull docker.litellm.ai/berriai/litellm:lts to stay on the newest LTS patch. See the LTS pilot.

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:1.108.13

This release is published as ghcr.io/berriai/litellm:v1.108.13. See the GitHub release and the full releases page.

v1.108.13 is a patch release on top of v1.108.12. There are no new database migrations. The v1.108.13 tag points at 7af0eac.

What's Changed​

  • Messages API: Fixed Claude Code's rotating billing header breaking prompt caching and inflating input tokens on non-Anthropic models - PR #52922
  • Caching: Fixed GPT-6.2 system prompts missing the prompt cache on /v1/chat/completions and /v1/messages unless store: false - PR #52906
  • Keys, teams and auth: Fixed JWT key mappings without jwt_issuer taking 5 minutes to apply when litellm_jwtauth.issuers is set, broken since v1.103.0 - PR #52350
  • Keys, teams and auth: Fixed /key/info letting a key with no user read other userless keys by hash or alias - PR #52838 and PR #52925
  • Deployment: Fixed proxy boot on Unix-socket Postgres like Cloud SQL, where the migration lock dialed localhost:5432 - PR #52797

The changes are backported in PR #52713, PR #52819, PR #52907 and PR #52919.

Full Changelog​

https://github.com/BerriAI/litellm/compare/v1.108.12...v1.108.13

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