github BerriAI/litellm v1.108.11
1.108.11 (LTS)

56 minutes ago

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:v1.108.11

Same 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_effort to DeepSeek V4 Flash and Pro on azure_ai (#52070)
  • AWS Bedrock: Fixed guarded_text parts in system and assistant messages being dropped instead of checked by the guardrail (#51776)
  • AWS Bedrock: Fixed aborted Invoke streams on /v1/messages that 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" to gemini-4-hydrogen (#52060)
  • Other providers: Fixed Cohere embeddings ignoring COHERE_API_BASE and always calling api.cohere.ai (#52194)
  • Other providers: Fixed OpenRouter streams sending an empty choice after finish_reason: stop that broke strict clients (#52200)
  • Chat completions: Fixed LiteLLM's own MCP and fake_stream params reaching provider request bodies and causing 400s (#52225)
  • Responses API: Fixed 500 on /v1/responses when allowed_openai_params is 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, quality and 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 to http:// behind TLS termination, broken since v1.108.0 (#52213)
  • Deployment: Changed the UI image to slim nginx, which drops curl but keeps wget and nc (#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 generateContent support for custom providers registered in custom_provider_map (#51083)

Backport #51982 · Backport #52074 · Backport #52155 · Backport #52201 · Backport #52233 · Backport #52248 · Backport #52306 · Backport #52312 · Full changelog

Don't miss a new litellm release

NewReleases is sending notifications on new releases.