---
title: "LiteLLM v1.109.3 and v1.106.12 fix GPT-6.2 caching on stored requests"
url: "/release_notes/v1.106.12/v1-106-12"
canonical_url: "https://docs.litellm.ai/release_notes/v1.106.12/v1-106-12"
type: "release-notes"
last_updated: "2026-11-19"
summary: "GPT-6.2 caches system prompts on Chat Completions and Messages requests with store on or unset, and userless keys stop reading each other's key info."
related:
  - "/release_notes/v1.107.0rc4/v1-107-0-rc-4"
  - "/release_notes/v1.106.11/v1-106-11"
---
# LiteLLM v1.109.3 and v1.106.12 fix GPT-6.2 caching on stored requests

> 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:1.106.12
```

**Pip**

```bash
pip install litellm==1.106.12
```

This release is published as [`ghcr.io/berriai/litellm:v1.106.12`](https://github.com/BerriAI/litellm/pkgs/container/litellm). See the [GitHub release](https://github.com/BerriAI/litellm/releases/tag/v1.106.12) and the full [releases page](https://github.com/BerriAI/litellm/releases).

`v1.106.12` is a patch release on top of [`v1.106.11`](/release_notes/v1.106.11/v1-106-11). There are no new database migrations. The `v1.106.12` tag points at [`c6dd3dd`](https://github.com/BerriAI/litellm/commit/c6dd3dd3288dc52c24f2ecf028a3ab9bc8057854).

### What's Changed

- **Caching:** Fixed GPT-6.2 system prompts missing the prompt cache on `/v1/chat/completions` and `/v1/messages` unless `store: false` - [PR #52906](https://github.com/BerriAI/litellm/pull/52906)
- **Keys, teams and auth:** Fixed `/key/info` letting a key with no user read other userless keys by hash or alias - [PR #52838](https://github.com/BerriAI/litellm/pull/52838) and [PR #52925](https://github.com/BerriAI/litellm/pull/52925)
- **Deployment:** Changed dnspython, tornado, filelock, soupsieve and opentelemetry to newer releases - [PR #52936](https://github.com/BerriAI/litellm/pull/52936) and [PR #53032](https://github.com/BerriAI/litellm/pull/53032)
- **Deployment:** Changed the Docker images to a newer Wolfi base image - [PR #53033](https://github.com/BerriAI/litellm/pull/53033)

The changes are backported in [PR #52924](https://github.com/BerriAI/litellm/pull/52924) and [PR #52936](https://github.com/BerriAI/litellm/pull/52936).

## Full Changelog

https://github.com/BerriAI/litellm/compare/v1.106.11...v1.106.12

## Related pages

- [v1.107.0rc4](https://docs.litellm.ai/release_notes/v1.107.0rc4/v1-107-0-rc-4.md)
- [v1.106.11](https://docs.litellm.ai/release_notes/v1.106.11/v1-106-11.md)
