---
title: "LiteLLM v1.108.3 (LTS) fixes Bedrock api_base and large MCP tool results"
url: "/release_notes/v1.108.3/v1-108-3"
canonical_url: "https://docs.litellm.ai/release_notes/v1.108.3/v1-108-3"
type: "release-notes"
last_updated: "2026-11-09"
summary: "Fixes Bedrock deployments with an empty api_base, MCP tool results over 1 MiB, and model-level post_call guardrails that ran twice."
related:
  - "/release_notes/v1.108.4/v1-108-4"
  - "/release_notes/v1.108.2/v1-108-2"
---
# LiteLLM v1.108.3 (LTS) fixes Bedrock api_base and large MCP tool results

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt

:::tip

`v1.108.3` 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](/docs/enterprise/lts_pilot).

:::

## Deploy this version

**Docker**

```bash
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:1.108.3
```

**Pip**

```bash
pip install litellm==1.108.3
```

This release is published as [`ghcr.io/berriai/litellm:v1.108.3`](https://github.com/BerriAI/litellm/pkgs/container/litellm). See the [GitHub release](https://github.com/BerriAI/litellm/releases/tag/v1.108.3) and the full [releases page](https://github.com/BerriAI/litellm/releases).

`v1.108.3` is a patch release on top of [`v1.108.2`](/release_notes/v1.108.2/v1-108-2). There are no new database migrations. The `v1.108.3` tag points at [`b7d579f`](https://github.com/BerriAI/litellm/commit/b7d579fab2818968322ef96e5b8e98dc8178fafc).

### What's Changed

- **AWS Bedrock:** Fixed every request failing on a Bedrock deployment with `api_base: ""`, which answered 500 or 400 - [PR #50449](https://github.com/BerriAI/litellm/pull/50449)
- **MCP:** Fixed tool results over 1 MiB failing with `SSE stream ended without a response`, broken since v1.103.0 - [PR #47034](https://github.com/BerriAI/litellm/pull/47034)
- **Guardrails:** Fixed model-level `post_call` guardrails checking each response twice and calling the moderation provider twice - [PR #50463](https://github.com/BerriAI/litellm/pull/50463)

## Full Changelog

https://github.com/BerriAI/litellm/compare/v1.108.2...v1.108.3

## Related pages

- [v1.108.4](https://docs.litellm.ai/release_notes/v1.108.4/v1-108-4.md)
- [v1.108.2](https://docs.litellm.ai/release_notes/v1.108.2/v1-108-2.md)