BerriAI/litellm v1.44.2

on GitHub

What's Changed

• openrouter/anthropic/claude-3.5-sonnet: supports_assistant_prefill:true by @paul-gauthier in #5315
• fix/docs: was missing a beta model from openrouter of claude sonnet by @thiswillbeyourgithub in #5314
• docs - use litellm on gcp cloud run by @ishaan-jaff in #5317
• Qdrant Semantic Caching by @haadirakhangi in #5018
• [Feat-Proxy] Add Qdrant Semantic Caching Support by @ishaan-jaff in #5324
• feat(user_api_key_auth.py): allow team admin to add new members to team by @krrishdholakia in #5308
• feat(proxy_server.py): support disabling storing master key hash in db by @krrishdholakia in #5322
• Support LangSmith parent_run_id, trace_id, session_id by @MarkRx in #5323
• add checksum/config pod annotation by @mikstew in #5318
• Fixed code snippet import typo in Structured Output docs by @beltranaceves in #5304
• Add the "stop" parameter to the mistral API interface by @the-crypt-keeper in #5253
• [Feat] add vertex multimodal embedding support by @ishaan-jaff in #5326
• [Feat-Proxy] Make LiteLLM Proxy (Gateway) compatible with VertexAI SDK 🔥 by @ishaan-jaff in #5327

New Contributors

• @haadirakhangi made their first contribution in #5018
• @MarkRx made their first contribution in #5323
• @beltranaceves made their first contribution in #5304
• @the-crypt-keeper made their first contribution in #5253

Full Changelog: v1.44.1...v1.44.2

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.2

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