BerriAI/litellm v1.61.2-nightly

on GitHub

What's Changed

• Improved wildcard route handling on /models and /model_group/info by @krrishdholakia in #8473
• (Bug fix) - Using include_usage for /completions requests + unit testing by @ishaan-jaff in #8484
• add sonar pricings by @themrzmaster in #8476
• (bug fix) PerplexityChatConfig - track correct OpenAI compatible params by @ishaan-jaff in #8496
• (fix #2) don't block proxy startup if license check fails & using prometheus by @ishaan-jaff in #8492
• ci(config.yml): mark daily docker builds with -nightly by @krrishdholakia in #8499
• (Redis Cluster) - Fixes for using redis cluster + pipeline by @ishaan-jaff in #8442
• Litellm UI stable version 02 12 2025 by @krrishdholakia in #8497
• fix: fix test by @krrishdholakia in #8501
• enables no auth for SMTP by @krrishdholakia in #8494
• UI Fixes p2 by @krrishdholakia in #8502
• add phoenix docs for observability integration by @exiao in #8522
• Added custom_attributes to additional_keys which can be sent to athina by @vivek-athina in #8518
• (UI) fix log details page by @ishaan-jaff in #8524
• Add UI Support for Admins to Call /cache/ping and View Cache Analytics (#8475) by @tahaali-dev in #8519
• LiteLLM Improvements (02/13/2025) p1 by @krrishdholakia in #8523

Full Changelog: v1.61.1...v1.61.2-nightly

## Docker Run LiteLLM Proxy

```
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.61.2-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