LiteLLM is moving to Rust 🦀Read the latest updates.›

LiteLLM v1.108.4 (LTS) fixes Bedrock pass-through guardrails and video polls

tip

v1.108.4 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

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:1.108.4

Pip

pip install litellm==1.108.4

This release is published as ghcr.io/berriai/litellm:v1.108.4. See the GitHub release and the full releases page.

v1.108.4 is a patch release on top of v1.108.3. There are no new database migrations. The v1.108.4 tag points at e6f080f.

What's Changed

• AWS Bedrock: Fixed 400s from GLM, GPT-6 Luna and Nova 2 on Bedrock when the conversation carries Claude's signed thinking - PR #50399
• AWS Bedrock: Changed /bedrock pass-through routes to enforce the model's guardrailConfig over any guardrail the caller sends - PR #47429
• Vertex AI and Gemini: Fixed Vertex AI Claude batches failing with 404 at create - PR #50365
• Messages API: Fixed chatgpt/ models on /v1/messages dropping encrypted reasoning between turns - PR #50456
• Messages API: Fixed /v1/messages to OpenAI sending background: true upstream, which billed full runs that came back empty - PR #50462
• Embeddings, images and audio: Fixed /v1/videos polls failing with per-model keys or hitting the wrong provider account with a 404 - PR #44614
• Routing and fallbacks: Fixed team keys being served by a proxy-wide wildcard instead of the team's own BYOK wildcard deployment - PR #48490
• SDK: Fixed completion(), responses() and messages with tools failing with No module named 'mcp' on a base install, broken since v1.106.0 - PR #45961

Full Changelog

https://github.com/BerriAI/litellm/compare/v1.108.3...v1.108.4