Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Verify this release
cosign verify \
--certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
ghcr.io/berriai/litellm:v1.108.11Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
What's new in 1.108.11 (LTS)
22 PRs. 1 added, 14 fixed, 2 changed. No action needed to upgrade
Changes
- Azure: Fixed 400 when sending
reasoning_effortto DeepSeek V4 Flash and Pro onazure_ai(#52070) - AWS Bedrock: Fixed
guarded_textparts in system and assistant messages being dropped instead of checked by the guardrail (#51776) - AWS Bedrock: Fixed aborted Invoke streams on
/v1/messagesthat kept generating billed output tokens upstream (#52210) - Vertex AI and Gemini: Fixed 500 when the chat history has an earlier tool call with null or truncated arguments (#50020)
- Vertex AI and Gemini: Fixed 400 when sending
reasoning_effort: "xhigh"togemini-4-hydrogen(#52060) - Other providers: Fixed Cohere embeddings ignoring
COHERE_API_BASEand always calling api.cohere.ai (#52194) - Other providers: Fixed OpenRouter streams sending an empty choice after
finish_reason: stopthat broke strict clients (#52200) - Chat completions: Fixed LiteLLM's own MCP and
fake_streamparams reaching provider request bodies and causing 400s (#52225) - Responses API: Fixed 500 on
/v1/responseswhenallowed_openai_paramsis a string or tuple (#52203) - Messages API: Fixed streamed thinking blocks ending without
signature_delta, so clients dropped them on the next tool step (#52117) - Embeddings, images and audio: Fixed custom image handlers not receiving
n,size,qualityand the other OpenAI image params (#52051) - Keys, teams and auth: Changed team model writes so only proxy admins can set
os.environ/values, team admins now get 403 (#51874) - Admin UI: Fixed SSO login detouring through
/sso/key/generate/and redirecting tohttp://behind TLS termination, broken since v1.108.0 (#52213) - Deployment: Changed the UI image to slim nginx, which drops
curlbut keepswgetandnc(#52298) - SDK: Fixed valid Messages and OCR requests with dict-subclass inputs failing when
LITELLM_RUST=true(#51812) - Performance: Fixed proxy pods running out of memory when clients retry 429s with large request bodies (#51428)
- Other: Added native
generateContentsupport for custom providers registered incustom_provider_map(#51083)
Backport #51982 · Backport #52074 · Backport #52155 · Backport #52201 · Backport #52233 · Backport #52248 · Backport #52306 · Backport #52312 · Full changelog