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

LiteLLM v1.108.2 (LTS) fixes Bedrock service tiers and Claude PDF input

tip

v1.108.2 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:1.108.2

Pip

pip install litellm==1.108.2

This release is published as ghcr.io/berriai/litellm:v1.108.2. See the GitHub release and the full releases page.

v1.108.2 is a patch release on top of v1.108.1. There are no new database migrations. The v1.108.2 tag points at 831a14c.

What's Changed

• OpenAI: Fixed openai/ deployments with an empty api_key sending OPENAI_ADMIN_KEY as the bearer token - PR #50218
• AWS Bedrock: Fixed Converse service_tier so unsupported tiers answer 400 and reserved, auto and standard_only are honored - PR #50360
• AWS Bedrock: Fixed Invoke dropping the per-turn-control-2026-07-01 beta on Claude 4.5 and newer - PR #50362
• Vertex AI and Gemini: Fixed chirp text-to-speech ignoring vertex_location, so US and EU deployments call their multi-region host - PR #50392
• Chat completions: Fixed response_format: json_object on openai/responses/* and azure/responses/* answering 400 about the word json - PR #50267
• Chat completions: Fixed base64 PDFs sent to Claude as image_url answering 400, and Bedrock JSON schema calls dropping thinking - PR #50280
• Responses API: Fixed /v1/responses/compact returning 500 when a during_call guardrail is on by default - PR #50274
• Embeddings, images and audio: Fixed audio transcription errors echoing the full provider reply, transcript included, to clients and logs - PR #50325
• MCP: Changed hosted MCP tools that a translated route cannot run to return a clear 400, or be dropped with drop_params - PR #50348
• Routing and fallbacks: Fixed groups that accept unmatched tags rejecting requests after affinity or cooldown filtering - PR #48470
• Routing and fallbacks: Fixed prompt caching routing not pinning follow-ups to one deployment when turn_off_message_logging is on - PR #50276
• Cost tracking and pricing: Fixed spend rows being dropped and valid keys getting 401 while Postgres restarts or shuts down - PR #50132

Full Changelog

https://github.com/BerriAI/litellm/compare/v1.108.1...v1.108.2