BerriAI/litellm v1.44.15

on GitHub

What's Changed

• Bedrock Embeddings refactor + model support by @krrishdholakia in #5462
• Fix response_format={'type': 'json_object'} not working for Azure models by @simonsanvil in #5468
• LiteLLM minor fixes + improvements (31/08/2024) by @krrishdholakia in #5464
• (gemini): Fix Cloudflare AI Gateway typo. by @Manouchehri in #5429
• [PRICING] Add pricing for ft:gpt-3.5-turbo-* by @kiriloman in #5471
• Azure Service Principal with Secret authentication workflow. (#5131) by @krrishdholakia in #5437
• LiteLLM Minor Fixes + Improvements by @krrishdholakia in #5474
• [Feat] Add AI21 /chat API by @ishaan-jaff in #5478
• [Feat] Track Usage for /streamGenerateContent endpoint by @ishaan-jaff in #5480
• [Feat-Proxy] track imagen /predict in LiteLLM spend logs by @ishaan-jaff in #5481
• [Feat] track embedding /predict in spend logs by @ishaan-jaff in #5482
• feat(router.py): Support Loadbalancing batch azure api endpoints by @krrishdholakia in #5469
• fix(router.py): fix inherited type by @krrishdholakia in #5485

Full Changelog: v1.44.14...v1.44.15

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.15

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