BerriAI/litellm v1.77.1.dev.1

on GitHub

What's Changed

• Optional labels field in Vertex AI request by @vvidovic in #9175
• fix: ensure Gemini calls include a user message (fixes #9733) by @ocraviotto in #12651
• feat: add a health_check_voice parameter in model_info by @dotmobo in #12416
• The parameter timestamp_granularities is broken for openai-like transcription by @dotmobo in #12414
• Fix/gcp model armor by @bjornjee in #14381
• [Performance] Use fastuuid for litellm_call_id by @Bobronium in #14346
• [Fix] Remove INFO level log from /messages endpoint by @ishaan-jaff in #14377
• Fix: Add supports_function_calling for GPT OSS in Bedrock provider by @pazevedo-hyland in #14375
• [Performance] Use _PROXY_MaxParallelRequestsHandler_v3 by default by @Bobronium in #14352
• Update proxy_cli.py help message by @dttran-glo in #14369
• [Security] Fix: Ensure .info() logs are not used for request/responses + Add code QA check for possible violations by @ishaan-jaff in #14386
• fix(internal_user_endpoints.py): ensure only proxy admin can update v… by @krrishdholakia in #14387

New Contributors

• @vvidovic made their first contribution in #9175
• @ocraviotto made their first contribution in #12651
• @dotmobo made their first contribution in #12416
• @bjornjee made their first contribution in #14381

Full Changelog: v1.77.0-nightly...v1.77.1.dev.1

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.77.1.dev.1

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