BerriAI/litellm v1.61.9-nightly

on GitHub

What's Changed

• Pass router tags in request headers - x-litellm-tags + fix openai metadata param check by @krrishdholakia in #8609
• (Fix) Redis async context usage for Redis Cluster + 94% lower median latency when using Redis Cluster by @ishaan-jaff in #8622
• add openrouter/google/gemini-2.0-flash-001 by @HeMuling in #8619
• feat: add oss license check for related packages by @krrishdholakia in #8623
• fix(model_cost_map): fix json parse error on model cost map + add uni… by @krrishdholakia in #8629
• [Feature]: Redis Caching - Allow setting a namespace for redis cache by @ishaan-jaff in #8624
• Cleanup ui filter icon + pass timeout for Sagemaker messages API by @krrishdholakia in #8630
• Add Elroy to projects built with litellm by @elroy-bot in #8642
• Add OSS license check to ci/cd by @krrishdholakia in #8626
• Fix parallel request limiter on proxy by @krrishdholakia in #8639
• Cleanup user <-> team association on /team/delete + Fix bedrock/deepseek_r1/ translation by @krrishdholakia in #8640
• (Polish/Fixes) - Fixes for Adding Team Specific Models by @ishaan-jaff in #8645

New Contributors

• @HeMuling made their first contribution in #8619
• @elroy-bot made their first contribution in #8642

Full Changelog: v1.61.8-nightly...v1.61.9-nightly

## Docker Run LiteLLM Proxy

```
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.61.9-nightly

Don't want to maintain your internal proxy? get in touch 🎉

Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results