---
title: "LiteLLM v1.106.6 and v1.105.7 fix the gzip performance regression"
url: "/release_notes/v1.106.6/v1-106-6"
canonical_url: "https://docs.litellm.ai/release_notes/v1.106.6/v1-106-6"
type: "release-notes"
last_updated: "2026-10-30"
summary: "The proxy gzips only dashboard analytics responses and compresses them on a worker thread, so gzip no longer slows down inference requests."
related:
  - "/release_notes/v1.107.0rc1/v1-107-0-rc-1"
  - "/release_notes/v1.106.5/v1-106-5"
---
# LiteLLM v1.106.6 and v1.105.7 fix the gzip performance regression

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

## 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:1.106.6
```

**Pip**

```bash
pip install litellm==1.106.6
```

This release is published as [`ghcr.io/berriai/litellm:v1.106.6`](https://github.com/BerriAI/litellm/pkgs/container/litellm). See the [GitHub release](https://github.com/BerriAI/litellm/releases/tag/v1.106.6) and the full [releases page](https://github.com/BerriAI/litellm/releases).

:::danger Breaking Changes

**Inference and other endpoints outside the dashboard analytics routes no longer return gzip responses.** The proxy ignores `Accept-Encoding: gzip` on those routes, so their responses are larger on the wire. LiteLLM has no setting to restore the old behavior. If you need compressed responses, turn on compression in a reverse proxy or load balancer in front of the proxy. See [PR #46712](https://github.com/BerriAI/litellm/pull/46712).

:::

`v1.106.6` is a patch release on top of [`v1.106.5`](/release_notes/v1.106.5/v1-106-5). It fixes the gzip performance regression on `stable/1.106.x` that the [`v1.106.5`](/release_notes/v1.106.5/v1-106-5) notes warn about. There are no new database migrations. The `v1.106.6` tag points at [`61c6ab7`](https://github.com/BerriAI/litellm/commit/61c6ab78393ef45683dd7d963d2a315bd845e20b).

### What's Changed

- The proxy only gzips responses from the dashboard analytics routes, such as the Usage and Cost Optimization pages, and compresses them on a worker thread instead of the event loop. Requests sent with `Accept-Encoding: gzip`, which most HTTP clients and the OpenAI SDKs send by default, no longer slow down other requests on the same worker - [PR #46712](https://github.com/BerriAI/litellm/pull/46712)

The change and the version bump are backported in [PR #48680](https://github.com/BerriAI/litellm/pull/48680).

## Full Changelog

https://github.com/BerriAI/litellm/compare/v1.106.5...v1.106.6

## Related pages

- [v1.107.0rc1](https://docs.litellm.ai/release_notes/v1.107.0rc1/v1-107-0-rc-1.md)
- [v1.106.5](https://docs.litellm.ai/release_notes/v1.106.5/v1-106-5.md)