BerriAI/litellm v1.46.0

on GitHub

What's Changed

• [Fix] Performance - use in memory cache when downloading images from a url by @ishaan-jaff in #5657
• [Feat - Perf Improvement] DataDog Logger 91% lower latency by @ishaan-jaff in #5687
• (models): Added missing gemini experimental models + fixed pricing for gemini-1.5-pro-exp-0827 by @F1bos in #5693
• LiteLLM Minor Fixes and Improvements (09/13/2024) by @krrishdholakia in #5689
• LiteLLM Minor Fixes and Improvements (09/14/2024) by @krrishdholakia in #5697
• Update model_prices_and_context_window.json by @Ahmet-Dedeler in #5700
• [Feat] Add max_completion_tokens param by @ishaan-jaff in #5691
• [Feat] Stable Prs - Sep 14th (Sambanova API) by @ishaan-jaff in #5703
• [Fix] Router cooldown logic - use % thresholds instead of allowed fails to cooldown deployments by @ishaan-jaff in #5698
• [Feat-Prometheus] Track exception status on litellm_deployment_failure_responses by @ishaan-jaff in #5706
• [Feat-Prometheus] Add prometheus metric for tracking cooldown events by @ishaan-jaff in #5705

New Contributors

• @Ahmet-Dedeler made their first contribution in #5700

Full Changelog: v1.45.0...v1.46.0

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.46.0

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