BerriAI/litellm v1.44.1

on GitHub

Guardrails on LiteLLM Proxy are now Free 🔥

Start here: https://docs.litellm.ai/docs/proxy/guardrails/quick_start

What's Changed

• Allow not displaying feedback box by @msabramo in #4868
• Fix app_version in helm build by @mikstew in #4649
• feat(azure.py): support 'json_schema' for older models by @krrishdholakia in #5296
• fix(cost_calculator.py): only override base model if custom pricing is set by @krrishdholakia in #5287
• feat(azure.py): support dynamic azure api versions by @krrishdholakia in #5284
• Fix helm chart job by @mikstew in #5297
• [Fix Router] - Don't cooldown Default Provider deployment by @ishaan-jaff in #5302
• [Fix] Router - Do not retry on 404 errors from LLM API providers by @ishaan-jaff in #5298
• [Fix Router] Don't retry errors when healthy_deployments=0 by @ishaan-jaff in #5299
• [Fix] Router - don't recursively use the same fallback by @ishaan-jaff in #5301
• [Fix Docker] Maintain separate docker image for running as non-root user by @ishaan-jaff in #5306
• [Feat-Proxy] Make Guardrails Free / OSS - Lakera AI, Aporia AI 🛡️ by @ishaan-jaff in #5303
• [Docs] - v2 Guardrails are now Free / Open Source by @ishaan-jaff in #5309

New Contributors

• @mikstew made their first contribution in #4649

Full Changelog: v1.43.19...v1.44.1

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.1

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