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

LiteLLM v1.110.2 and v1.111.0rc3 fix Responses stream restarts

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.3

This release is published as ghcr.io/berriai/litellm:v1.111.0-rc.3. See the GitHub release and the full releases page.

v1.111.0rc3 is a release candidate on top of v1.111.0rc2. There are no new database migrations. The v1.111.0-rc.3 tag points at 5608526.

What's Changed​

  • Anthropic: Fixed temperature=1 returning 400 on Claude models that removed sampling params on Anthropic, Vertex AI and Azure AI, broken since v1.110.0-rc.2 - PR #52341
  • Responses API: Fixed streams retrying after output reached the client, which sent duplicate events and billed extra calls - PR #52461
  • Responses API: Fixed streams that fail after reasoning output restarting on a fallback group and sending a second response - PR #52616
  • Caching: Fixed GPT-6.2 system prompts missing the prompt cache on /v1/chat/completions and /v1/messages unless store: false - PR #52906
  • Cost tracking and pricing: Fixed forwarded Anthropic credentials on /v1/messages ignoring the deployment's custom prices, broken since v1.109.0 - PR #52313
  • Keys, teams and auth: Fixed 503s on a burst of first requests for new customer org aliases, which left their spend untracked - PR #52080
  • 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
  • Admin UI: Fixed SSO login redirecting to an http:// URL when the proxy runs behind TLS termination, broken since v1.108.0 - PR #52213
  • Deployment: Fixed each proxy worker opening six extra Postgres connections at boot - PR #52378
  • Performance: Fixed failed calls holding large request bodies in memory until a full GC, growing workers to several GiB - PR #52600

The changes are backported in PR #52462, PR #52470, PR #52691, PR #52752, PR #52764, PR #52914 and PR #52939.

Full Changelog​

https://github.com/BerriAI/litellm/compare/v1.111.0-rc.2...v1.111.0-rc.3

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