BerriAI/litellm v1.61.3.dev1

on GitHub

What's Changed

• docs(perplexity.md): removing return_citations documentation by @miraclebakelaser in #8527
• (docs - cookbook) litellm proxy x langfuse by @ishaan-jaff in #8541
• UI Fixes and Improvements (02/14/2025) p1 by @krrishdholakia in #8546
• (Feat) - Add /bedrock/meta.llama3-3-70b-instruct-v1:0 tool calling support + cost tracking + base llm unit test for tool calling by @ishaan-jaff in #8545
• fix(general_settings.tsx): filter out empty dictionaries post fallbac… by @krrishdholakia in #8550
• (perf) Fix memory leak on /completions route by @ishaan-jaff in #8551
• Org Flow Improvements by @krrishdholakia in #8549
• feat(openai/o_series_transformation.py): support native streaming for o1 by @krrishdholakia in #8552
• fix(team_endpoints.py): fix team info check to handle team keys by @krrishdholakia in #8529
• build: ui build update by @krrishdholakia in #8553

Full Changelog: v1.61.3...v1.61.3.dev1

## Docker Run LiteLLM Proxy

```
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.61.3.dev1

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