Skip to content

LiteLLM 1.109 development preview adds stream fallback controls

Updated LiteLLM

Summary

The prerelease adds a chat UI, streaming continuation and offline mode, with configuration migrations that need review.

Category
Agent infra
Date
Pricing
Not stated in the sources we cited.

LiteLLM published 1.109.0-dev.1 on October 28, 2026. It is explicitly a development prerelease, not a stable-version recommendation.

New preview capabilities

The release adds a chat interface with a model hub, continuation on configured fallbacks after an interrupted stream, an offline-mode setting for automatic fetches, and a default-deny option for agent access.

Review migration requirements

Its upgrade notes call out a new image-verification key, changed cost-map token-limit fields, configuration-based GCS logging and revised timeout error handling. Treat these as migration work, not an effortless drop-in upgrade. Read the complete release notes for your providers.

Separate stable backports 1.103.10, 1.104.8, 1.105.6 and 1.106.5 narrow rejected-request logging and use proxy-configured GCS credentials. Those do not bring the entire preview feature set to stable branches.

Model access and provider billing remain separate; no benchmark, universal compatibility or zero-cost inference claim is made.

See the litellm hub.

More from LiteLLM

View all

Questions

What is LiteLLM?

According to its docs, LiteLLM is an open-source library that gives you a single, unified interface to call 100+ LLMs using the OpenAI format.

Is LiteLLM open source?

The docs describe it as an open-source library, but the GitHub API does not report a recognized license for the repository.

Filed on Agent Radar. Claims in this note are limited to the sources above.