BerriAI/litellm v1.71.2.dev3

on GitHub

What's Changed

• [Debug] Fix - debug langfuse clients started by @ishaan-jaff in #11221
• Helicone base url support + fix for embedding cache hits on str input by @krrishdholakia in #11211
• fix(utils.py): support non default params for audio transcription + fix calling azure o_series models by @krrishdholakia in #11212
• Add 'supports_parallel_function_calling' to all gemini models by @krrishdholakia in #11225
• fix the litellm CLA reference by @emmanuel-ferdman in #11230
• Update docker_quick_start.md – Replace gpt-3.5-turbo with gpt-4o in Proxy Getting Started Guide by @VigneshwarRajasekaran in #11223
• fix: bedrock ai21 jamba models will work now by @AnilAren in #11233
• Fix syntax error in Python example code in LiteLLM docs by @fadil4u in #11242
• [Feat]: Add Bedrock InvokeAgents as a /chat/completions route on LiteLLM by @ishaan-jaff in #11239
• [Feat]: Guardrails - Add streaming for bedrock post guard by @ishaan-jaff in #11247
• [Fix] Responses API - Session management by @ishaan-jaff in #11254
• Support dropping non-openai params when specified in additional_drop_params + Add VertexAI Anthropic support on /v1/messages by @krrishdholakia in #11246

New Contributors

• @VigneshwarRajasekaran made their first contribution in #11223
• @AnilAren made their first contribution in #11233
• @fadil4u made their first contribution in #11242

Full Changelog: v1.71.2.dev1...v1.71.2.dev3

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.71.2.dev3

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